diff --git a/图像识别CV/pythoncv_learn/10007.jpg b/图像识别CV/pythoncv_learn/10007.jpg new file mode 100644 index 0000000..48309b0 Binary files /dev/null and b/图像识别CV/pythoncv_learn/10007.jpg differ diff --git a/图像识别CV/pythoncv_learn/10008.jpg b/图像识别CV/pythoncv_learn/10008.jpg new file mode 100644 index 0000000..b6afa7a Binary files /dev/null and b/图像识别CV/pythoncv_learn/10008.jpg differ diff --git a/图像识别CV/pythoncv_learn/10009.jpg b/图像识别CV/pythoncv_learn/10009.jpg new file mode 100644 index 0000000..19435b8 Binary files /dev/null and b/图像识别CV/pythoncv_learn/10009.jpg differ diff --git a/图像识别CV/pythoncv_learn/10044.jpg b/图像识别CV/pythoncv_learn/10044.jpg new file mode 100644 index 0000000..26b5aff Binary files /dev/null and b/图像识别CV/pythoncv_learn/10044.jpg differ diff --git a/图像识别CV/pythoncv_learn/10049.jpg b/图像识别CV/pythoncv_learn/10049.jpg new file mode 100644 index 0000000..4dcdcd8 Binary files /dev/null and b/图像识别CV/pythoncv_learn/10049.jpg differ diff --git a/图像识别CV/pythoncv_learn/10061.jpg b/图像识别CV/pythoncv_learn/10061.jpg new file mode 100644 index 0000000..04f1c29 Binary files /dev/null and b/图像识别CV/pythoncv_learn/10061.jpg differ diff --git a/图像识别CV/pythoncv_learn/10069.jpg b/图像识别CV/pythoncv_learn/10069.jpg new file mode 100644 index 0000000..e774b8f Binary files /dev/null and b/图像识别CV/pythoncv_learn/10069.jpg differ diff --git a/图像识别CV/pythoncv_learn/10076.jpg b/图像识别CV/pythoncv_learn/10076.jpg new file mode 100644 index 0000000..fd1556c Binary files /dev/null and b/图像识别CV/pythoncv_learn/10076.jpg differ diff --git a/图像识别CV/pythoncv_learn/FastFeatureDetector.py b/图像识别CV/pythoncv_learn/FastFeatureDetector.py new file mode 100644 index 0000000..ed475fa --- /dev/null +++ b/图像识别CV/pythoncv_learn/FastFeatureDetector.py @@ -0,0 +1,53 @@ +import cv2 as cv +import numpy as np + +img = cv.imread('10069.jpg') +img = cv.resize(img, (800, 800)) + +''' +# 用默认值初始化FAST对象 +fast = cv.FastFeatureDetector_create() + +# 寻找并绘制关键点 +kp = fast.detect(img,None) +img2 = cv.drawKeypoints(img, kp, None, color=(255,0,0)) + +# 打印所有默认参数 +print( "Threshold: {}".format(fast.getThreshold()) ) +print( "nonmaxSuppression:{}".format(fast.getNonmaxSuppression()) ) +print( "neighborhood: {}".format(fast.getType()) ) +print( "Total Keypoints with nonmaxSuppression: {}".format(len(kp)) ) +cv.imshow('fast_true', img2) + +# 关闭非极大抑制 +fast.setNonmaxSuppression(0) +kp = fast.detect(img,None) +print( "Total Keypoints without nonmaxSuppression: {}".format(len(kp)) ) +img3 = cv.drawKeypoints(img, kp, None, color=(255,0,0)) +cv.imshow('fast_false', img2) + +cv.waitKey(0) +cv.destroyAllWindows() +''' + +''' +gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY) +gray = np.float32(gray) +dst = cv.cornerHarris(gray,2,3,0.04) +#result用于标记角点，并不重要 +dst = cv.dilate(dst,None) +#最佳值的阈值，它可能因图像而异。 +img[dst>0.01*dst.max()]=[0,0,255] +cv.imshow('dst',img) +''' + +gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY) +corners = cv.goodFeaturesToTrack(gray,25,0.01,10) +corners = np.int0(corners) +for i in corners: + x,y = i.ravel() + cv.circle(img,(x,y),3,255,-1) +cv.imshow('dst',img) + +cv.waitKey(0) +cv.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/detection_chessboard_v1.py b/图像识别CV/pythoncv_learn/detection_chessboard_v1.py new file mode 100644 index 0000000..15e996b --- /dev/null +++ b/图像识别CV/pythoncv_learn/detection_chessboard_v1.py @@ -0,0 +1,372 @@ +import cv2 +import numpy as np +import math + +image=cv2.imread('10076.jpg') +image = cv2.resize(image, (800, 800)) + +grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +cv2.imshow('grayImage', grayImage) + +edgeImage = grayImage + +# 直方图均衡 +edgeImage = cv2.equalizeHist(edgeImage) +cv2.imshow('equalizeHist', edgeImage) + +''' +# 自适应直方图均衡 +clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) +edgeImage = clahe.apply(edgeImage) +cv2.imshow('createCLAHE', edgeImage) +''' + +# 二值化 +h, w = edgeImage.shape[:2] +m = np.reshape(edgeImage, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, binary = cv2.threshold(edgeImage, mean, 255, cv2.THRESH_BINARY) +image_binary = 255 - binary +cv2.imshow('image_binary', image_binary) + +''' +# 双边滤波 +edgeImage = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('bilateralFilter', edgeImage) +''' + +''' +# 中位模糊 +edgeImage = cv2.medianBlur(edgeImage,5) +cv2.imshow('medianBlur', edgeImage) +''' + +# 高斯模糊 +edgeImage = cv2.GaussianBlur(grayImage, (3, 3), 1) +cv2.imshow('GaussianBlur', edgeImage) + +''' +# 平均 +edgeImage = cv2.blur(edgeImage,(5,5)) +cv2.imshow('blur', edgeImage) +''' + +# 边缘检测 +canny = cv2.Canny(edgeImage, 20, 80) +cv2.imshow('Canny', canny) + +kernel = np.ones((5,5),np.uint8) +dilate = cv2.dilate(canny,kernel,iterations = 1) +cv2.imshow('dilate', dilate) + +''' +# 轮廓检测 +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 1): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +cv2.imshow('laplacian', laplacian) + +# 二值化 +h, w = laplacian.shape[:2] +m = np.reshape(laplacian, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, laplacian_binary = cv2.threshold(laplacian, mean, 255, cv2.THRESH_BINARY) +cv2.imshow('laplacian_binary', laplacian_binary) + +sobelx = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测竖线, 6: HoughLines检测竖线, 8:检测横线) + sobelx = cv2.Sobel(sobelx,cv2.CV_8U,1,0,ksize=5) + # sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +cv2.imshow('sobelx', sobelx) + +sobely = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测横线, 6: HoughLines检测横线, 8:检测竖线) + sobely = cv2.Sobel(sobely,cv2.CV_8U,0,1,ksize=5) + # sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) +cv2.imshow('sobely', sobely) + +binary_1 = cv2.bitwise_and(dilate, laplacian_binary) +cv2.imshow('binary_1', binary_1) + +sobelx_binary = cv2.bitwise_and(sobelx, binary_1) +cv2.imshow('sobelx_binary', sobelx_binary) + +sobely_binary = cv2.bitwise_and(sobely, binary_1) +cv2.imshow('sobely_binary', sobely_binary) + +lineXImage = sobelx_binary +lineYImage = sobely_binary + +''' +# 侵蚀 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.erode(edgeImage,kernel,iterations = 1) +cv2.imshow('erode', edgeImage) +''' + +''' +# 扩张 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +''' +# 开运算 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_OPEN, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 闭运算 +kernel = np.ones((5,5),np.uint8) +morphologyEx = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', morphologyEx) +''' + +''' +# 形态学梯度 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_GRADIENT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 顶帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_TOPHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 黑帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_BLACKHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 锐化 +cv2.imshow('edgeImage + edgeImage', edgeImage + edgeImage) +''' + +def isVerticalLine(line): + x1,y1,x2,y2 = line[0] + + if (x2-x1) == 0 : + x_angle = 90 + else: + xielv = (y2-y1)/(x2-x1) + x_angle = xielv * (180 / math.pi) + x_angle = x_angle % 180 + + if x_angle > 67.5 and x_angle < 112.5 : + return True + else: + return False + +def isHorizontalLine(line): + x1,y1,x2,y2 = line[0] + + if (x2-x1) == 0 : + x_angle = 90 + else: + xielv = (y2-y1)/(x2-x1) + x_angle = xielv * (180 / math.pi) + x_angle = x_angle % 180 + + if x_angle < 22.5 or x_angle > 157.5 : + return True + else: + return False + +def findHoughEdge(edgeImage, isLinesP=True): + if isLinesP: + lines = findLinesP(edgeImage) + else: + lines = findLines(edgeImage) + + if lines is None: + return [[0, 1, 5, 21], [8, 1, 5, 3], [4, 12, 0, 8], [41, 11, 20, 15]] + + lines_vertical = filter(lambda line: True if abs(line[0][1] - line[0][3]) > edgeImage.shape[0] * 0.5 else False, lines) + lines_horizontal = filter(lambda line: True if abs(line[0][0] - line[0][2]) > edgeImage.shape[1] * 0.5 else False, lines) + + # lines_vertical = filter(isVerticalLine, lines_vertical) + # lines_horizontal = filter(isHorizontalLine, lines_horizontal) + + lines_vertical = sorted(lines_vertical, key=lambda line: line[0][0]) + lines_horizontal = sorted(lines_horizontal , key=lambda line: line[0][1]) + + if len(lines_vertical) < 2 or len(lines_horizontal) < 2: + return [[0, 1, 5, 21], [8, 1, 5, 3], [4, 12, 0, 8], [41, 11, 20, 15]] + return [lines_vertical[0][0], lines_horizontal [0][0], lines_vertical[-1][0], lines_horizontal [-1][0]] + +def writeHoughEdge(edgeImage, title): + lines = findHoughEdge(edgeImage, False) + houghEdgeImage = image.copy() + for line in lines: + x1,y1,x2,y2 = line + cv2.line(houghEdgeImage,(x1,y1),(x2,y2),(0,0,255),2) + + cv2.imshow('houghEdgeImage' + title, houghEdgeImage) + +def writeHoughEdgeP(edgeImage, title): + lines = findHoughEdge(edgeImage, True) + writeHoughEdgeP = image.copy() + for line in lines: + x1,y1,x2,y2 = line + cv2.line(writeHoughEdgeP,(x1,y1),(x2,y2),(255,0,0),2) + + cv2.imshow('writeHoughEdgeP' + title, writeHoughEdgeP) + +def findLines(edgeImage): + lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) + ok_lines = [] + for line in lines: + rho,theta = line[0] + + if (theta < (np.pi/4. )) or (theta > (3.*np.pi/4.0)): #垂直直线 + pt1 = (int(rho/np.cos(theta)),0) #该直线与第一行的交点 + #该直线与最后一行的焦点 + pt2 = (int((rho-edgeImage.shape[0]*np.sin(theta))/np.cos(theta)),edgeImage.shape[0]) + else: #水平直线 + pt1 = (0,int(rho/np.sin(theta))) # 该直线与第一列的交点 + #该直线与最后一列的交点 + pt2 = (edgeImage.shape[1], int((rho-edgeImage.shape[1]*np.cos(theta))/np.sin(theta))) + + x1, y1 = pt1 + x2, y2 = pt2 + + if (x2-x1) == 0 : + x_angle = 90 + else: + xielv = (y2-y1)/(x2-x1) + x_angle = xielv * (180 / math.pi) + x_angle = x_angle % 180 + + if (x_angle < 22.5 or x_angle > 157.5) or (x_angle > 67.5 and x_angle < 112.5) : + ok_lines.append([[x1,y1,x2,y2]]) + return ok_lines + +def findLinesP(edgeImage): + thresh_min = min(edgeImage.shape) + lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) + ok_lines = [] + for line in lines: + x1,y1,x2,y2 = line[0] + + if (x2-x1) == 0 : + x_angle = 90 + else: + xielv = (y2-y1)/(x2-x1) + x_angle = xielv * (180 / math.pi) + x_angle = x_angle % 180 + + if (x_angle < 22.5 or x_angle > 157.5) or (x_angle > 67.5 and x_angle < 112.5) : + ok_lines.append([[x1,y1,x2,y2]]) + return ok_lines + +def writeLines(edgeImage, title): + lines = findLines(edgeImage) + houghEdgeImage = image.copy() + for line in lines: + x1,y1,x2,y2 = line[0] + cv2.line(houghEdgeImage,(x1,y1),(x2,y2),(0,0,255),2) + cv2.imshow('findLines' + title, houghEdgeImage) + +def writeLinesP(edgeImage, title): + lines = findLinesP(edgeImage) + houghEdgeImage = image.copy() + for line in lines: + x1,y1,x2,y2 = line[0] + cv2.line(houghEdgeImage,(x1,y1),(x2,y2),(255,0,0),2) + cv2.imshow('findLinesP' + title, houghEdgeImage) + +def __clac_intersection(line_a, line_b): + x1_a, y1_a, x2_a, y2_a = line_a + x1_b, y1_b, x2_b, y2_b = line_b + A_a = y2_a - y1_a + B_a = x1_a - x2_a + C_a = x2_a * y1_a - x1_a * y2_a + A_b = y2_b - y1_b + B_b = x1_b - x2_b + C_b = x2_b * y1_b - x1_b * y2_b + m = A_a * B_b - A_b * B_a + output_x = (C_b * B_a - C_a * B_b) / m + output_y = (C_a * A_b - C_b * A_a) / m + return (int(output_x), int(output_y)) + +# writeLines(lineXImage, 'X') +# writeLines(lineYImage, 'Y') +# writeLinesP(lineXImage, 'X') +# writeLinesP(lineYImage, 'Y') + +# writeHoughEdge(lineXImage, 'X') +# writeHoughEdge(lineYImage, 'Y') +# writeHoughEdgeP(lineXImage, 'X') +# writeHoughEdgeP(lineYImage, 'Y') + +linesX = findHoughEdge(lineXImage, False) +linesY = findHoughEdge(lineYImage, False) + +houghEdgeImage = image.copy() +cv2.line(houghEdgeImage,(linesX[0][0],linesX[0][1]),(linesX[0][2],linesX[0][3]),(255,0,0),2) +cv2.line(houghEdgeImage,(linesX[2][0],linesX[2][1]),(linesX[2][2],linesX[2][3]),(0,255,0),2) +cv2.line(houghEdgeImage,(linesY[1][0],linesY[1][1]),(linesY[1][2],linesY[1][3]),(0,0,255),2) +cv2.line(houghEdgeImage,(linesY[3][0],linesY[3][1]),(linesY[3][2],linesY[3][3]),(255,255,0),2) +cv2.imshow('houghEdge', houghEdgeImage) + +p1 = __clac_intersection((linesX[0][0],linesX[0][1], linesX[0][2],linesX[0][3]), (linesY[1][0],linesY[1][1], linesY[1][2],linesY[1][3])) +p2 = __clac_intersection((linesY[1][0],linesY[1][1], linesY[1][2],linesY[1][3]), (linesX[2][0],linesX[2][1], linesX[2][2],linesX[2][3])) +p3 = __clac_intersection((linesX[2][0],linesX[2][1], linesX[2][2],linesX[2][3]), (linesY[3][0],linesY[3][1], linesY[3][2],linesY[3][3])) +p4 = __clac_intersection((linesY[3][0],linesY[3][1], linesY[3][2],linesY[3][3]), (linesX[0][0],linesX[0][1], linesX[0][2],linesX[0][3])) + +print((p1, p2, p3, p4)) + +warpPerspectiveImage = image.copy() +pts1 = np.float32([p1,p2,p4,p3]) +pts2 = np.float32([[0,0],[800,0],[0,800],[800,800]]) +M = cv2.getPerspectiveTransform(pts1,pts2) +dst = cv2.warpPerspective(warpPerspectiveImage,M,(800,800)) +cv2.imshow('warpPerspective', dst) + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +''' +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) +cv2.imshow('show', image) +''' + +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/image_cutting_v1.py b/图像识别CV/pythoncv_learn/image_cutting_v1.py new file mode 100644 index 0000000..622c2e7 --- /dev/null +++ b/图像识别CV/pythoncv_learn/image_cutting_v1.py @@ -0,0 +1,55 @@ +# -*- coding: utf-8 -*- +# @Author : matthew +# @Software: PyCharm + +import cv2 +import matplotlib.pyplot as plt +import numpy as np + + +def seg_kmeans_gray(): + img = cv2.imread('10049.jpg', cv2.IMREAD_GRAYSCALE) + + # 展平 + img_flat = img.reshape((img.shape[0] * img.shape[1], 1)) + img_flat = np.float32(img_flat) + + # 迭代参数 + criteria = (cv2.TERM_CRITERIA_EPS + cv2.TermCriteria_MAX_ITER, 20, 0.5) + flags = cv2.KMEANS_RANDOM_CENTERS + + # 聚类 + compactness, labels, centers = cv2.kmeans(img_flat, 2, None, criteria, 10, flags) + + # 显示结果 + img_output = labels.reshape((img.shape[0], img.shape[1])) + plt.subplot(121), plt.imshow(img, 'gray'), plt.title('input') + plt.subplot(122), plt.imshow(img_output, 'gray'), plt.title('kmeans') + plt.show() + +def seg_kmeans_color(): + img = cv2.imread('10049.jpg', cv2.IMREAD_COLOR) + # 变换一下图像通道bgr->rgb，否则很别扭啊 + b, g, r = cv2.split(img) + img = cv2.merge([r, g, b]) + + # 3个通道展平 + img_flat = img.reshape((img.shape[0] * img.shape[1], 3)) + img_flat = np.float32(img_flat) + + # 迭代参数 + criteria = (cv2.TERM_CRITERIA_EPS + cv2.TermCriteria_MAX_ITER, 20, 0.5) + flags = cv2.KMEANS_RANDOM_CENTERS + + # 聚类 + compactness, labels, centers = cv2.kmeans(img_flat, 2, None, criteria, 10, flags) + + # 显示结果 + img_output = labels.reshape((img.shape[0], img.shape[1])) + plt.subplot(121), plt.imshow(img), plt.title('input') + plt.subplot(122), plt.imshow(img_output, 'gray'), plt.title('kmeans') + plt.show() + +if __name__ == '__main__': + # seg_kmeans_gray() + seg_kmeans_color() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/image_cutting_v2.py b/图像识别CV/pythoncv_learn/image_cutting_v2.py new file mode 100644 index 0000000..da4ef65 --- /dev/null +++ b/图像识别CV/pythoncv_learn/image_cutting_v2.py @@ -0,0 +1,26 @@ +from PIL import Image +from sklearn.cluster import KMeans +import numpy as np + +q = Image.open('10049.jpg') +# q.show() +m, n = q.size +q1 = np.array(q) +#这里有坑，注意q.size和q1.shape的值不一样，横竖跌倒 + +q1 = q1.reshape((m*n, 3)) + +k = 8 +y = KMeans(n_clusters = k).fit_predict(q1) + +centroids = np.zeros((k, 3)) +#计算类心值，之后填充图像 +for cent in range(k): + centroids[cent] = q1[np.where(y == cent)].mean(axis = 0) + +ynew = y.reshape((n, m)) +pic_new = Image.new("RGB", (m, n)) +for i in range(m): + for j in range(n): + pic_new.putpixel((i, j), tuple([int(x) for x in centroids[ynew[j][i]]])) +pic_new.show() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/image_cutting_v3.py b/图像识别CV/pythoncv_learn/image_cutting_v3.py new file mode 100644 index 0000000..95d3551 --- /dev/null +++ b/图像识别CV/pythoncv_learn/image_cutting_v3.py @@ -0,0 +1,33 @@ +import numpy as np +from PIL import Image as image +#加载PIL包，用于加载创建图片 +from sklearn.cluster import KMeans#加载Kmeans算法 + +def loadData(filePath): + f = open(filePath,'rb') #以二进制形式打开文件 + data= [] + img =image.open(f)#以列表形式返回图片像素值 + m,n =img.size #获得图片大小 + for i in range(m): + for j in range(n): + #将每个像素点RGB颜色处理到0-1范围内 + x,y,z =img.getpixel((i,j)) + #将颜色值存入data内 + data.append([x/256.0,y/256.0,z/256.0]) + f.close() + #以矩阵的形式返回data，以及图片大小 + return np.mat(data),m,n +imgData,row,col =loadData('10069.jpg')#加载数据 + +km=KMeans(n_clusters=3) +#聚类获得每个像素所属的类别 +label =km.fit_predict(imgData) +label=label.reshape([row,col]) +#创建一张新的灰度图以保存聚类后的结果 +pic_new = image.new("L",(row,col)) +#根据类别向图片中添加灰度值 +for i in range(row): + for j in range(col): + pic_new.putpixel((i,j),int(256/(label[i][j]+1))) +#以JPEG格式保存图像 +pic_new.show() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/image_cutting_v4.py b/图像识别CV/pythoncv_learn/image_cutting_v4.py new file mode 100644 index 0000000..1e854b4 --- /dev/null +++ b/图像识别CV/pythoncv_learn/image_cutting_v4.py @@ -0,0 +1,133 @@ +import numpy as np +import random +from matplotlib import pyplot as plt +import cv2 +import os + +def loss_function(present_center, pre_center): + ''' + 损失函数，计算上一次与当前聚类中的差异（像素差的平方和） + :param present_center: 当前聚类中心 + :param pre_center: 上一次聚类中心 + :return:　损失值 + ''' + present_center = np.array(present_center) + pre_center = np.array(pre_center) + return np.sum((present_center - pre_center)**2) + + +def classifer(intput_signal, center): + ''' + 分类器（通过当前的聚类中心，给输入图像分类） + :param intput_signal: 输入图像 + :param center: 聚类中心 + :return:　标签矩阵 + ''' + if len(intput_signal.shape) == 2: + input_row, input_col = intput_signal.shape # 输入图像的尺寸 + else: + input_row, input_col, layers = intput_signal.shape # 输入图像的尺寸 + + pixls_labels = np.zeros((input_row, input_col)) # 储存所有像素标签 + + pixl_distance_t = [] # 单个元素与所有聚类中心的距离，临时用 + + for i in range(input_row): + for j in range(input_col): + # 计算每个像素与所有聚类中心的差平方 + for k in range(len(center)): + distance_t = np.sum(abs((intput_signal[i, j]).astype(int) - center[k].astype(int))**2) + pixl_distance_t.append(distance_t) + # 差异最小则为该类 + pixls_labels[i, j] = int(pixl_distance_t.index(min(pixl_distance_t))) + # 清空该list，为下一个像素点做准备 + pixl_distance_t = [] + return pixls_labels + + +def k_means(input_signal, center_num, threshold): + ''' + 基于k-means算法的图像分割（适用于灰度图） + :param input_signal:　输入图像 + :param center_num:　聚类中心数目 + :param threshold:　迭代阈值 + :return: + ''' + input_signal_cp = np.copy(input_signal) # 输入信号的副本 + if len(input_signal_cp.shape) == 2: + input_row, input_col = input_signal_cp.shape # 输入图像的尺寸 + is_gray = True + else: + input_row, input_col, layers = input_signal_cp.shape # 输入图像的尺寸 + is_gray = False + pixls_labels = np.zeros((input_row, input_col)) # 储存所有像素标签 + + is_present_center_random = True + if os.path.exists('./present_center.npz'): + present_center_npz = np.load('./present_center.npz', allow_pickle=True) + present_center = present_center_npz['center_arr'] + is_gray_old = present_center_npz['is_gray'] + pixls_labels = present_center_npz['pixls_labels'] + + if is_gray_old == is_gray: + is_present_center_random = False + + if is_present_center_random: + # 随机初始聚类中心行标与列标 + initial_center_row_num = [i for i in range(input_row)] + random.shuffle(initial_center_row_num) + initial_center_row_num = initial_center_row_num[:center_num] + + initial_center_col_num = [i for i in range(input_col)] + random.shuffle(initial_center_col_num) + initial_center_col_num = initial_center_col_num[:center_num] + + # 当前的聚类中心 + present_center = [] + for i in range(center_num): + present_center.append(input_signal_cp[initial_center_row_num[i], initial_center_row_num[i]]) + pixls_labels = classifer(input_signal_cp, present_center) + + + print("Start Train") + num = 0 # 用于记录迭代次数 + while True: + pre_centet = present_center.copy() # 储存前一次的聚类中心 + # 计算当前聚类中心 + for n in range(center_num): + temp = np.where(pixls_labels == n) + present_center[n] = sum(input_signal_cp[temp].astype(int)) / len(input_signal_cp[temp]) + # 根据当前聚类中心分类 + pixls_labels = classifer(input_signal_cp, present_center) + # 计算上一次聚类中心与当前聚类中心的差异 + loss = loss_function(present_center, pre_centet) + num = num + 1 + print("Step:"+ str(num) + " Loss:" + str(loss)) + # 当损失小于迭代阈值时，结束迭代 + if loss <= threshold: + np.savez('./present_center.npz', center_arr=present_center, is_gray=is_gray, pixls_labels=pixls_labels) + break + return pixls_labels + +if __name__ == '__main__': + image = cv2.imread('10008.jpg', cv2.IMREAD_COLOR) + # image = cv2.imread('10008.jpg', cv2.IMREAD_GRAYSCALE) + + #如果本身是彩图 似乎也没什么影响！ + #plt显示按照 rgb次序！因此要转换 + b,g,r = cv2.split(image) + image = cv2.merge([r,g,b]) + + image = cv2.resize(image, (100, 100)) + + k = 3 + threshold = 1 + labels = k_means(image, k, threshold) + + plt.subplot(1, 2, 1) + plt.title("Soucre Image") + plt.imshow(image,cmap="gray") + plt.subplot(1, 2, 2) + plt.title("Segamenting Image with k-means\n" + "k=" + str(k) + " threshold=" + str(threshold)) + plt.imshow(labels/3) + plt.show() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/image_cutting_v5.py b/图像识别CV/pythoncv_learn/image_cutting_v5.py new file mode 100644 index 0000000..4f59a1b --- /dev/null +++ b/图像识别CV/pythoncv_learn/image_cutting_v5.py @@ -0,0 +1,193 @@ +import numpy as np +import random +from matplotlib import pyplot as plt +import cv2 +import os + +def loss_function(present_center, pre_center): + ''' + 损失函数，计算上一次与当前聚类中的差异（像素差的平方和） + :param present_center: 当前聚类中心 + :param pre_center: 上一次聚类中心 + :return:　损失值 + ''' + present_center = np.array(present_center) + pre_center = np.array(pre_center) + return np.sum((present_center - pre_center)**2) + + +def classifer(intput_signal, center): + ''' + 分类器（通过当前的聚类中心，给输入图像分类） + :param intput_signal: 输入图像 + :param center: 聚类中心 + :return:　标签矩阵 + ''' + if len(intput_signal.shape) == 2: + input_row, input_col = intput_signal.shape # 输入图像的尺寸 + else: + input_row, input_col, layers = intput_signal.shape # 输入图像的尺寸 + + pixls_labels = np.zeros((input_row, input_col)) # 储存所有像素标签 + + pixl_distance_t = [] # 单个元素与所有聚类中心的距离，临时用 + + for i in range(input_row): + for j in range(input_col): + # 计算每个像素与所有聚类中心的差平方 + for k in range(len(center)): + distance_t = np.sum(abs((intput_signal[i, j]).astype(int) - center[k].astype(int))**2) + pixl_distance_t.append(distance_t) + # 差异最小则为该类 + pixls_labels[i, j] = int(pixl_distance_t.index(min(pixl_distance_t))) + # 清空该list，为下一个像素点做准备 + pixl_distance_t = [] + return pixls_labels + + +def k_means(input_signal, center_num, threshold): + ''' + 基于k-means算法的图像分割（适用于灰度图） + :param input_signal:　输入图像 + :param center_num:　聚类中心数目 + :param threshold:　迭代阈值 + :return: + ''' + input_signal_cp = np.copy(input_signal) # 输入信号的副本 + if len(input_signal_cp.shape) == 2: + input_row, input_col = input_signal_cp.shape # 输入图像的尺寸 + is_gray = True + else: + input_row, input_col, layers = input_signal_cp.shape # 输入图像的尺寸 + is_gray = False + pixls_labels = np.zeros((input_row, input_col)) # 储存所有像素标签 + + is_present_center_random = True + if os.path.exists('./present_center.npz'): + present_center_npz = np.load('./present_center.npz', allow_pickle=True) + present_center = present_center_npz['center_arr'] + is_gray_old = present_center_npz['is_gray'] + pixls_labels = present_center_npz['pixls_labels'] + + if is_gray_old == is_gray: + is_present_center_random = False + + if is_present_center_random: + # 随机初始聚类中心行标与列标 + initial_center_row_num = [i for i in range(input_row)] + random.shuffle(initial_center_row_num) + initial_center_row_num = initial_center_row_num[:center_num] + + initial_center_col_num = [i for i in range(input_col)] + random.shuffle(initial_center_col_num) + initial_center_col_num = initial_center_col_num[:center_num] + + # 当前的聚类中心 + present_center = [] + for i in range(center_num): + present_center.append(input_signal_cp[initial_center_row_num[i], initial_center_row_num[i]]) + pixls_labels = classifer(input_signal_cp, present_center) + + + print("Start Train") + num = 0 # 用于记录迭代次数 + while True: + pre_centet = present_center.copy() # 储存前一次的聚类中心 + # 计算当前聚类中心 + for n in range(center_num): + temp = np.where(pixls_labels == n) + present_center[n] = sum(input_signal_cp[temp].astype(int)) / len(input_signal_cp[temp]) + # 根据当前聚类中心分类 + pixls_labels = classifer(input_signal_cp, present_center) + # 计算上一次聚类中心与当前聚类中心的差异 + loss = loss_function(present_center, pre_centet) + num = num + 1 + print("Step:"+ str(num) + " Loss:" + str(loss)) + # 当损失小于迭代阈值时，结束迭代 + if loss <= threshold: + np.savez('./present_center.npz', center_arr=present_center, is_gray=is_gray, pixls_labels=pixls_labels) + break + return pixls_labels + +def findLine(edgeImage, title): + houghLinesImage = edgeImage.copy() + ''' + lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) + print(len(lines)) + for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + # if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + # print(xielv) + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) + cv2.imshow('houghLinesImage' + title, houghLinesImage) + ''' + + houghLinesPImage = image.copy() + thresh_min = min(edgeImage.shape) + lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) + print(len(lines)) + for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + ''' + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + ''' + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) + cv2.imshow('HoughLinesP' + title, houghLinesPImage) + +if __name__ == '__main__': + image = cv2.imread('10007.jpg', cv2.IMREAD_COLOR) + # image = cv2.imread('10008.jpg', cv2.IMREAD_GRAYSCALE) + + #如果本身是彩图 似乎也没什么影响！ + #plt显示按照 rgb次序！因此要转换 + b,g,r = cv2.split(image) + image = cv2.merge([r,g,b]) + image = cv2.resize(image, (800, 800)) + + image_s = cv2.resize(image, (100, 100)) + + k = 6 + threshold = 1 + labels = k_means(image_s, k, threshold) + + labels = (labels * (255 / k)).astype(np.uint8) + + labels = cv2.resize(labels, (800, 800)) + + cv2.imshow('labels', labels) + + # 二值化 + h, w = labels.shape[:2] + m = np.reshape(labels, [1, w*h]) + mean = m.sum()/(w*h) + # binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) + ret, binary = cv2.threshold(labels, mean, 255, cv2.THRESH_BINARY) + image_binary = 255 - binary + cv2.imshow('image_binary', image_binary) + + findLine(image_binary, "line") + + plt.subplot(1, 2, 1) + plt.title("Soucre Image") + plt.imshow(image,cmap="gray") + plt.subplot(1, 2, 2) + plt.title("Segamenting Image with k-means\n" + "k=" + str(k) + " threshold=" + str(threshold)) + plt.imshow(labels) + plt.show() + + cv2.waitKey(0) + cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/main.py b/图像识别CV/pythoncv_learn/main.py new file mode 100644 index 0000000..6f00dff --- /dev/null +++ b/图像识别CV/pythoncv_learn/main.py @@ -0,0 +1,111 @@ +import cv2 +import numpy as np + +image=cv2.imread('10076.jpg') +image = cv2.resize(image, (600, 600)) + +''' +imgray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +ret, thresh = cv2.threshold(imgray, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) +''' + +#(3, 3)表示高斯矩阵的长与宽都是3，标准差取1 +InputArray = image.copy() +cv2.GaussianBlur(InputArray, (3, 3), 1, InputArray) +edgeImage = cv2.Canny(InputArray, 20, 80) +cv2.imshow('GaussianBlur', edgeImage) + +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) + +''' +blur = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('blur', blur) +''' + +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', edgeImage) + +''' +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +sobelx = cv2.Sobel(edgeImage,cv2.CV_8U,1,0,ksize=5) +sobely = cv2.Sobel(edgeImage,cv2.CV_8U,0,1,ksize=5) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +# sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +# sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) +cv2.imshow('laplacian', laplacian) +cv2.imshow('sobelx', sobelx) +cv2.imshow('sobely', sobely) +edgeImage = sobely + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 10): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) + +houghLinesImage = image.copy() +lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) +for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + # print(xielv) + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) +cv2.imshow('houghLinesImage', houghLinesImage) + +houghLinesPImage = image.copy() +thresh_min = min(edgeImage.shape) +lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) +print(len(lines)) +for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + # print(xielv) + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) +cv2.imshow('HoughLinesP', houghLinesPImage) + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) + +cv2.imshow('show', image) +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/main_v2.py b/图像识别CV/pythoncv_learn/main_v2.py new file mode 100644 index 0000000..941034a --- /dev/null +++ b/图像识别CV/pythoncv_learn/main_v2.py @@ -0,0 +1,209 @@ +import cv2 +import numpy as np + +image=cv2.imread('10009.jpg') +image = cv2.resize(image, (600, 600)) + +grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +cv2.imshow('grayImage', grayImage) + +edgeImage = grayImage + +# 直方图均衡 +edgeImage = cv2.equalizeHist(edgeImage) +cv2.imshow('equalizeHist', edgeImage) + +''' +# 自适应直方图均衡 +clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) +edgeImage = clahe.apply(edgeImage) +cv2.imshow('createCLAHE', edgeImage) +''' + +# 二值化 +h, w = edgeImage.shape[:2] +m = np.reshape(edgeImage, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, binary = cv2.threshold(edgeImage, mean, 255, cv2.THRESH_BINARY) +image_binary = 255 - binary +cv2.imshow('image_binary', image_binary) + +''' +# 双边滤波 +edgeImage = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('bilateralFilter', edgeImage) +''' + +''' +# 中位模糊 +edgeImage = cv2.medianBlur(edgeImage,5) +cv2.imshow('medianBlur', edgeImage) +''' + +# 高斯模糊 +edgeImage = cv2.GaussianBlur(grayImage, (3, 3), 1) +cv2.imshow('GaussianBlur', edgeImage) + +''' +# 平均 +edgeImage = cv2.blur(edgeImage,(5,5)) +cv2.imshow('blur', edgeImage) +''' + +''' +# 边缘检测 +canny = cv2.Canny(edgeImage, 20, 80) +cv2.imshow('Canny', canny) +''' + +''' +# 轮廓检测 +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 1): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +cv2.imshow('laplacian', laplacian) + +# 二值化 +h, w = laplacian.shape[:2] +m = np.reshape(laplacian, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, laplacian_binary = cv2.threshold(laplacian, mean, 255, cv2.THRESH_BINARY) +cv2.imshow('laplacian_binary', laplacian_binary) + +sobelx = cv2.Sobel(edgeImage,cv2.CV_8U,1,0,ksize=5) +# sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +cv2.imshow('sobelx', sobelx) + +sobely = cv2.Sobel(edgeImage,cv2.CV_8U,0,1,ksize=5) +# sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) +cv2.imshow('sobely', sobely) + +binary_1 = cv2.bitwise_and(image_binary, laplacian_binary) +cv2.imshow('binary_1', binary_1) +edgeImage = binary_1 + +''' +# 侵蚀 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.erode(edgeImage,kernel,iterations = 1) +cv2.imshow('erode', edgeImage) +''' + +''' +# 扩张 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +''' +# 开运算 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_OPEN, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 闭运算 +kernel = np.ones((5,5),np.uint8) +morphologyEx = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', morphologyEx) +''' + +''' +# 形态学梯度 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_GRADIENT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 顶帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_TOPHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 黑帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_BLACKHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 锐化 +cv2.imshow('edgeImage + edgeImage', edgeImage + edgeImage) +''' + +houghLinesImage = image.copy() +lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) +for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) +cv2.imshow('houghLinesImage', houghLinesImage) + +houghLinesPImage = image.copy() +thresh_min = min(edgeImage.shape) +lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) +print(len(lines)) +for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) +cv2.imshow('HoughLinesP', houghLinesPImage) + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +''' +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) +cv2.imshow('show', image) +''' + +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/main_v3.py b/图像识别CV/pythoncv_learn/main_v3.py new file mode 100644 index 0000000..21a0377 --- /dev/null +++ b/图像识别CV/pythoncv_learn/main_v3.py @@ -0,0 +1,220 @@ +import cv2 +import numpy as np + +image=cv2.imread('10076.jpg') +image = cv2.resize(image, (800, 800)) + +grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +cv2.imshow('grayImage', grayImage) + +edgeImage = grayImage + +# 直方图均衡 +edgeImage = cv2.equalizeHist(edgeImage) +cv2.imshow('equalizeHist', edgeImage) + +''' +# 自适应直方图均衡 +clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) +edgeImage = clahe.apply(edgeImage) +cv2.imshow('createCLAHE', edgeImage) +''' + +# 二值化 +h, w = edgeImage.shape[:2] +m = np.reshape(edgeImage, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, binary = cv2.threshold(edgeImage, mean, 255, cv2.THRESH_BINARY) +image_binary = 255 - binary +cv2.imshow('image_binary', image_binary) + +''' +# 双边滤波 +edgeImage = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('bilateralFilter', edgeImage) +''' + +''' +# 中位模糊 +edgeImage = cv2.medianBlur(edgeImage,5) +cv2.imshow('medianBlur', edgeImage) +''' + +# 高斯模糊 +edgeImage = cv2.GaussianBlur(grayImage, (3, 3), 1) +cv2.imshow('GaussianBlur', edgeImage) + +''' +# 平均 +edgeImage = cv2.blur(edgeImage,(5,5)) +cv2.imshow('blur', edgeImage) +''' + +''' +# 边缘检测 +canny = cv2.Canny(edgeImage, 20, 80) +cv2.imshow('Canny', canny) +''' + +''' +# 轮廓检测 +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 1): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +cv2.imshow('laplacian', laplacian) + +# 二值化 +h, w = laplacian.shape[:2] +m = np.reshape(laplacian, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, laplacian_binary = cv2.threshold(laplacian, mean, 255, cv2.THRESH_BINARY) +cv2.imshow('laplacian_binary', laplacian_binary) + +sobelx = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测竖线, 6: HoughLines检测竖线, 8:检测横线) + sobelx = cv2.Sobel(sobelx,cv2.CV_8U,1,0,ksize=5) + # sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +cv2.imshow('sobelx', sobelx) + +sobely = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测横线, 6: HoughLines检测横线, 8:检测竖线) + sobely = cv2.Sobel(sobely,cv2.CV_8U,0,1,ksize=5) + # sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) + cv2.imshow('sobely', sobely) + +binary_1 = cv2.bitwise_and(image_binary, laplacian_binary) +cv2.imshow('binary_1', binary_1) + +sobelx_binary = cv2.bitwise_and(sobelx, binary_1) +cv2.imshow('sobelx_binary', sobelx_binary) + +sobely_binary = cv2.bitwise_and(sobely, binary_1) +cv2.imshow('sobely_binary', sobely_binary) + +edgeImage = sobelx_binary + +''' +# 侵蚀 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.erode(edgeImage,kernel,iterations = 1) +cv2.imshow('erode', edgeImage) +''' + +''' +# 扩张 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +''' +# 开运算 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_OPEN, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 闭运算 +kernel = np.ones((5,5),np.uint8) +morphologyEx = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', morphologyEx) +''' + +''' +# 形态学梯度 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_GRADIENT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 顶帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_TOPHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 黑帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_BLACKHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 锐化 +cv2.imshow('edgeImage + edgeImage', edgeImage + edgeImage) +''' + +houghLinesImage = image.copy() +lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) +for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) +cv2.imshow('houghLinesImage', houghLinesImage) + +houghLinesPImage = image.copy() +thresh_min = min(edgeImage.shape) +lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) +print(len(lines)) +for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) +cv2.imshow('HoughLinesP', houghLinesPImage) + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +''' +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) +cv2.imshow('show', image) +''' + +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/main_v4.py b/图像识别CV/pythoncv_learn/main_v4.py new file mode 100644 index 0000000..db7074b --- /dev/null +++ b/图像识别CV/pythoncv_learn/main_v4.py @@ -0,0 +1,232 @@ +import cv2 +import numpy as np + +image=cv2.imread('10076.jpg') +image = cv2.resize(image, (800, 800)) + +grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +cv2.imshow('grayImage', grayImage) + +edgeImage = grayImage + +# 直方图均衡 +edgeImage = cv2.equalizeHist(edgeImage) +cv2.imshow('equalizeHist', edgeImage) + +''' +# 自适应直方图均衡 +clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) +edgeImage = clahe.apply(edgeImage) +cv2.imshow('createCLAHE', edgeImage) +''' + +# 二值化 +h, w = edgeImage.shape[:2] +m = np.reshape(edgeImage, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, binary = cv2.threshold(edgeImage, mean, 255, cv2.THRESH_BINARY) +image_binary = 255 - binary +cv2.imshow('image_binary', image_binary) + +''' +# 双边滤波 +edgeImage = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('bilateralFilter', edgeImage) +''' + +''' +# 中位模糊 +edgeImage = cv2.medianBlur(edgeImage,5) +cv2.imshow('medianBlur', edgeImage) +''' + +# 高斯模糊 +edgeImage = cv2.GaussianBlur(grayImage, (3, 3), 1) +cv2.imshow('GaussianBlur', edgeImage) + +''' +# 平均 +edgeImage = cv2.blur(edgeImage,(5,5)) +cv2.imshow('blur', edgeImage) +''' + +# 边缘检测 +canny = cv2.Canny(edgeImage, 20, 80) +cv2.imshow('Canny', canny) + +kernel = np.ones((5,5),np.uint8) +dilate = cv2.dilate(canny,kernel,iterations = 1) +cv2.imshow('dilate', dilate) + +''' +# 轮廓检测 +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 1): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +cv2.imshow('laplacian', laplacian) + +# 二值化 +h, w = laplacian.shape[:2] +m = np.reshape(laplacian, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, laplacian_binary = cv2.threshold(laplacian, mean, 255, cv2.THRESH_BINARY) +cv2.imshow('laplacian_binary', laplacian_binary) + +sobelx = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测竖线, 6: HoughLines检测竖线, 8:检测横线) + sobelx = cv2.Sobel(sobelx,cv2.CV_8U,1,0,ksize=5) + # sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +cv2.imshow('sobelx', sobelx) + +sobely = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测横线, 6: HoughLines检测横线, 8:检测竖线) + sobely = cv2.Sobel(sobely,cv2.CV_8U,0,1,ksize=5) + # sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) +cv2.imshow('sobely', sobely) + +binary_1 = cv2.bitwise_and(dilate, laplacian_binary) +cv2.imshow('binary_1', binary_1) + +sobelx_binary = cv2.bitwise_and(sobelx, binary_1) +cv2.imshow('sobelx_binary', sobelx_binary) + +sobely_binary = cv2.bitwise_and(sobely, binary_1) +cv2.imshow('sobely_binary', sobely_binary) + +lineXImage = sobelx_binary +lineYImage = sobely_binary + +''' +# 侵蚀 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.erode(edgeImage,kernel,iterations = 1) +cv2.imshow('erode', edgeImage) +''' + +''' +# 扩张 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +''' +# 开运算 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_OPEN, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 闭运算 +kernel = np.ones((5,5),np.uint8) +morphologyEx = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', morphologyEx) +''' + +''' +# 形态学梯度 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_GRADIENT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 顶帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_TOPHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 黑帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_BLACKHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 锐化 +cv2.imshow('edgeImage + edgeImage', edgeImage + edgeImage) +''' + +def findLine(edgeImage, title): + houghLinesImage = image.copy() + lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) + print(len(lines)) + for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + ''' + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + ''' + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) + cv2.imshow('houghLinesImage' + title, houghLinesImage) + + houghLinesPImage = image.copy() + thresh_min = min(edgeImage.shape) + lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) + print(len(lines)) + for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + ''' + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + ''' + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) + cv2.imshow('HoughLinesP' + title, houghLinesPImage) + +findLine(lineXImage, 'X') +findLine(lineYImage, 'Y') + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +''' +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) +cv2.imshow('show', image) +''' + +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/main_v5.py b/图像识别CV/pythoncv_learn/main_v5.py new file mode 100644 index 0000000..e25f48b --- /dev/null +++ b/图像识别CV/pythoncv_learn/main_v5.py @@ -0,0 +1,232 @@ +import cv2 +import numpy as np + +image=cv2.imread('10008.jpg') +image = cv2.resize(image, (800, 800)) + +grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) +cv2.imshow('grayImage', grayImage) + +edgeImage = grayImage + +# 直方图均衡 +edgeImage = cv2.equalizeHist(edgeImage) +cv2.imshow('equalizeHist', edgeImage) + +''' +# 自适应直方图均衡 +clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8)) +edgeImage = clahe.apply(edgeImage) +cv2.imshow('createCLAHE', edgeImage) +''' + +# 二值化 +h, w = edgeImage.shape[:2] +m = np.reshape(edgeImage, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, binary = cv2.threshold(edgeImage, mean, 255, cv2.THRESH_BINARY) +image_binary = 255 - binary +cv2.imshow('image_binary', image_binary) + +''' +# 双边滤波 +edgeImage = cv2.bilateralFilter(edgeImage,9,75,75) +cv2.imshow('bilateralFilter', edgeImage) +''' + +''' +# 中位模糊 +edgeImage = cv2.medianBlur(edgeImage,5) +cv2.imshow('medianBlur', edgeImage) +''' + +# 高斯模糊 +edgeImage = cv2.GaussianBlur(grayImage, (3, 3), 1) +cv2.imshow('GaussianBlur', edgeImage) + +''' +# 平均 +edgeImage = cv2.blur(edgeImage,(5,5)) +cv2.imshow('blur', edgeImage) +''' + +# 边缘检测 +canny = cv2.Canny(edgeImage, 20, 80) +cv2.imshow('Canny', canny) + +kernel = np.ones((5,5),np.uint8) +dilate = cv2.dilate(canny,kernel,iterations = 1) +cv2.imshow('dilate', dilate) + +''' +# 轮廓检测 +ret, thresh = cv2.threshold(edgeImage, 127, 255, 0) +contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE) + +def cnt_area(cnt): + area = cv2.contourArea(cnt) + return area +contours.sort(key = cnt_area, reverse=True) +print(len(contours)) +for i in range(0, 1): + cnt = contours[i] + img = image.copy() + cv2.drawContours(img, [cnt], 0, (0,255,0), 3) + cv2.imshow('drawContours_' + str(i), img) +cv2.drawContours(image, contours, -1, (0,255,0), 1) +cv2.imshow('drawContours', image) +''' + +laplacian = cv2.Laplacian(edgeImage,cv2.CV_8U) +# laplacian = cv2.Laplacian(edgeImage,cv2.CV_64F) +cv2.imshow('laplacian', laplacian) + +# 二值化 +h, w = laplacian.shape[:2] +m = np.reshape(laplacian, [1, w*h]) +mean = m.sum()/(w*h) +# binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,25,10) +ret, laplacian_binary = cv2.threshold(laplacian, mean, 255, cv2.THRESH_BINARY) +cv2.imshow('laplacian_binary', laplacian_binary) + +sobelx = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测竖线, 6: HoughLines检测竖线, 8:检测横线) + sobelx = cv2.Sobel(sobelx,cv2.CV_8U,1,0,ksize=5) + # sobelx = cv2.Sobel(edgeImage,cv2.CV_64F,1,0,ksize=5) +cv2.imshow('sobelx', sobelx) + +sobely = edgeImage +for i in range(0, 6): # 3,6,8有奇效(3: HoughLinesP检测横线, 6: HoughLines检测横线, 8:检测竖线) + sobely = cv2.Sobel(sobely,cv2.CV_8U,0,1,ksize=5) + # sobely = cv2.Sobel(edgeImage,cv2.CV_64F,0,1,ksize=5) +cv2.imshow('sobely', sobely) + +binary_1 = cv2.bitwise_and(dilate, laplacian_binary) +cv2.imshow('binary_1', binary_1) + +sobelx_binary = cv2.bitwise_and(sobelx, binary_1) +cv2.imshow('sobelx_binary', sobelx_binary) + +sobely_binary = cv2.bitwise_and(sobely, binary_1) +cv2.imshow('sobely_binary', sobely_binary) + +lineXImage = sobelx_binary +lineYImage = sobely_binary + +''' +# 侵蚀 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.erode(edgeImage,kernel,iterations = 1) +cv2.imshow('erode', edgeImage) +''' + +''' +# 扩张 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.dilate(edgeImage,kernel,iterations = 1) +cv2.imshow('dilate', edgeImage) +''' + +''' +# 开运算 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_OPEN, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 闭运算 +kernel = np.ones((5,5),np.uint8) +morphologyEx = cv2.morphologyEx(edgeImage, cv2.MORPH_CLOSE, kernel) +cv2.imshow('morphologyEx', morphologyEx) +''' + +''' +# 形态学梯度 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_GRADIENT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 顶帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_TOPHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 黑帽 +kernel = np.ones((5,5),np.uint8) +edgeImage = cv2.morphologyEx(edgeImage, cv2.MORPH_BLACKHAT, kernel) +cv2.imshow('morphologyEx', edgeImage) +''' + +''' +# 锐化 +cv2.imshow('edgeImage + edgeImage', edgeImage + edgeImage) +''' + +def findLine(edgeImage, title): + houghLinesImage = image.copy() + lines = cv2.HoughLines(edgeImage,1,np.pi/180,200) + print(len(lines)) + for line in lines: + rho,theta = line[0] + a = np.cos(theta) + b = np.sin(theta) + x0 = a*rho + y0 = b*rho + x1 = int(x0 + 1000*(-b)) + y1 = int(y0 + 1000*(a)) + x2 = int(x0 - 1000*(-b)) + y2 = int(y0 - 1000*(a)) + if (x2-x1) == 0 : + xielv = (y2-y1)/0.00000001 + else: + xielv = (y2-y1)/(x2-x1) + ''' + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + ''' + cv2.line(houghLinesImage,(x1,y1),(x2,y2),(0,0,255),2) + cv2.imshow('houghLinesImage' + title, houghLinesImage) + + houghLinesPImage = image.copy() + thresh_min = min(edgeImage.shape) + lines = cv2.HoughLinesP(edgeImage, 1.2, np.pi / 180, 160, minLineLength=int(edgeImage.shape[0] * 0.7),maxLineGap=int(thresh_min * 0.5)) + print(len(lines)) + for line in lines: + x1,y1,x2,y2 = line[0] + xielv = (y2-y1)/(x2-x1) + ''' + if (xielv > -0.08 and xielv < 0.08) or xielv > 8.0 or xielv < -8.0 : + print(xielv) + ''' + cv2.line(houghLinesPImage,(x1,y1),(x2,y2),(255,0,0),2) + cv2.imshow('HoughLinesP' + title, houghLinesPImage) + +findLine(lineXImage, 'X') +findLine(lineYImage, 'Y') + +''' +circles = cv2.HoughCircles(edgeImage,cv2.HOUGH_GRADIENT,1,20,param1=50,param2=30,minRadius=0,maxRadius=0) +circles = np.uint16(np.around(circles)) +for i in circles[0,:]: + # 绘制外圆 + cv2.circle(image,(i[0],i[1]),i[2],(0,255,0),2) + # 绘制圆心 + cv2.circle(image,(i[0],i[1]),2,(0,0,255),3) +''' + +''' +pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]]) +pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]]) +M = cv2.getPerspectiveTransform(pts1, pts2) +image = cv2.warpPerspective(image, M, (600, 600)) +cv2.imshow('show', image) +''' + +cv2.waitKey(0) +cv2.destroyAllWindows() \ No newline at end of file diff --git a/图像识别CV/pythoncv_learn/present_center.npz b/图像识别CV/pythoncv_learn/present_center.npz new file mode 100644 index 0000000..f190937 Binary files /dev/null and b/图像识别CV/pythoncv_learn/present_center.npz differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/01.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/01.gif new file mode 100644 index 0000000..6c73c67 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/01.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/02.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/02.gif new file mode 100644 index 0000000..87006ec Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/02.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/03.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/03.gif new file mode 100644 index 0000000..3050bb1 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/03.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/04.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/04.gif new file mode 100644 index 0000000..cabb8bb Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/04.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/05.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/05.gif new file mode 100644 index 0000000..5d62983 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/05.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/06.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/06.gif new file mode 100644 index 0000000..8912236 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/06.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/07.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/07.gif new file mode 100644 index 0000000..8fe3c1e Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/07.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/08.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/08.gif new file mode 100644 index 0000000..ad6fc7a Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/08.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/09.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/09.gif new file mode 100644 index 0000000..64a2114 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/09.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/10.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/10.gif new file mode 100644 index 0000000..6abf38f Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/10.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/11.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/11.gif new file mode 100644 index 0000000..9b961c2 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/11.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/12.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/12.gif new file mode 100644 index 0000000..2e8174f Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/12.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/13.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/13.gif new file mode 100644 index 0000000..ced59a9 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/13.gif differ diff --git a/图像识别CV/pythoncv_learn/围棋识别过程参考/围棋识别过程参考.gif b/图像识别CV/pythoncv_learn/围棋识别过程参考/围棋识别过程参考.gif new file mode 100644 index 0000000..af72a00 Binary files /dev/null and b/图像识别CV/pythoncv_learn/围棋识别过程参考/围棋识别过程参考.gif differ