本文共 9614 字,大约阅读时间需要 32 分钟。
具体代码如下:
import cv2global imgglobal point1, point2def on_mouse(event, x, y, flags, param): global img, point1, point2 img2 = img.copy() if event == cv2.EVENT_LBUTTONDOWN: #左键点击 point1 = (x,y) cv2.circle(img2, point1, 10, (0,255,0), 5) cv2.imshow('image', img2) elif event == cv2.EVENT_MOUSEMOVE and (flags & cv2.EVENT_FLAG_LBUTTON): #按住左键拖曳 cv2.rectangle(img2, point1, (x,y), (255,0,0), 5) # 图像,矩形顶点,相对顶点,颜色,粗细 cv2.imshow('image', img2) elif event == cv2.EVENT_LBUTTONUP: #左键释放 point2 = (x,y) cv2.rectangle(img2, point1, point2, (0,0,255), 5) cv2.imshow('image', img2) min_x = min(point1[0], point2[0]) min_y = min(point1[1], point2[1]) width = abs(point1[0] - point2[0]) height = abs(point1[1] -point2[1]) cut_img = img[min_y:min_y+height, min_x:min_x+width] resize_img = cv2.resize(cut_img, (28,28)) # 调整图像尺寸为28*28 ret, thresh_img = cv2.threshold(resize_img,127,255,cv2.THRESH_BINARY) # 二值化 cv2.imshow('result', thresh_img) cv2.imwrite('D:\\deng\\ppp\\888.png', thresh_img) # 预处理后图像保存位置def main(): global img img = cv2.imread('D:\\deng\\ppp\\8.jpg') # 手写数字图像所在位置 img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 转换图像为单通道(灰度图) cv2.namedWindow('image') cv2.setMouseCallback('image', on_mouse) # 调用回调函数 cv2.imshow('image', img) cv2.waitKey(0)if __name__ == '__main__': main()
2.0版本
import cv2global imgglobal point1, point2cap = cv2.VideoCapture(0)def on_mouse(event, x, y, flags, param): global img, point1, point2 img2 = img.copy() if event == cv2.EVENT_LBUTTONDOWN: #左键点击 point1 = (x,y) cv2.circle(img2, point1, 10, (0,255,0), 5) cv2.imshow('image', img2) elif event == cv2.EVENT_MOUSEMOVE and (flags & cv2.EVENT_FLAG_LBUTTON): #按住左键拖曳 cv2.rectangle(img2, point1, (x,y), (255,0,0), 5) # 图像,矩形顶点,相对顶点,颜色,粗细 cv2.imshow('image', img2) elif event == cv2.EVENT_LBUTTONUP: #左键释放 point2 = (x,y) cv2.rectangle(img2, point1, point2, (0,0,255), 5) cv2.imshow('image', img2) min_x = min(point1[0], point2[0]) min_y = min(point1[1], point2[1]) width = abs(point1[0] - point2[0]) height = abs(point1[1] -point2[1]) cut_img = img[min_y:min_y+height, min_x:min_x+width] resize_img = cv2.resize(cut_img, (28,28)) # 调整图像尺寸为28*28 ret, thresh_img = cv2.threshold(resize_img,127,255,cv2.THRESH_BINARY) # 二值化 cv2.imshow('result', thresh_img) cv2.imwrite('D:\\deng\\ppp\\888.png', thresh_img) # 预处理后图像保存位置def main(): global img while True: ret, frame = cap.read() img = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) cv2.namedWindow('image') cv2.setMouseCallback('image', on_mouse) # 调用回调函数 cv2.imshow('image', img) if cv2.waitKey(1) & 0xFF == ord('q'): #cv2.waitKey(0) cv2.destroyAllWindows() break #img = cv2.imread('D:\\deng\\ppp\\8.jpg') # 手写数字图像所在位置 #img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 转换图像为单通道(灰度图)if __name__ == '__main__': main()
3.0版本 顺便调用tensorflow的模型进行数字识别。下述代码中,tensorflow_test是自己写的.py文件,并不是一个库。文件中的代码就是中所展示的代码。可以创建一个python文件,将代码拷贝进去。然后通过这个文件进行import。就可以使用import文件中的函数。
from scipy.spatial import distance as distfrom imutils import perspectivefrom imutils import contoursimport numpy as npimport imutilsimport cv2import tensorflow_testfrom PIL import Imagedef midpoint(ptA, ptB): return ((ptA[0] + ptB[0]) * 0.5, (ptA[1] + ptB[1]) * 0.5)#cap = cv2.VideoCapture("http://192.168.1.1:8080/?action=stream")cap = cv2.VideoCapture(0)#HSV颜色空间的红色区间Redlower=np.array([35, 43, 46])Redupper=np.array([124, 255, 255])while(True): # Capture frame-by-frame ret, frame = cap.read() frame = imutils.resize(frame, width=600) # Our operations on the frame come here blurred = cv2.GaussianBlur(frame, (7, 7), 0) hsv = cv2.cvtColor(blurred, cv2.COLOR_BGR2HSV) #hsv = cv2.GaussianBlur(hsv, (7, 7), 0) # perform edge detection, then perform a dilation + erosion to # close gaps in between object edges #edged = cv2.Canny(hsv, 50, 100) #inRange()函数用于图像颜色分割 edged = cv2.inRange(hsv,Redlower,Redupper) edged = cv2.dilate(edged, None, iterations=2) edged = cv2.erode(edged, None, iterations=2) #在OpenCV中,可以用findContours()函数从二值图像中查找轮廓。 #可以使用compare(),inrange(),threshold(),adaptivethreshold(),canny()等函数由灰度图或色彩图创建二进制图像。 #RETR_EXTERNAL表示只检测最外层轮廓。CHAIN_APPROX_SIMPLE表示压缩水平方向,垂直方向,对角线方向的元素,只保留 #该方向的终点坐标,例如一个矩形轮廓只需4个点来保存轮廓信息。 cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2] #cnts, hierarchy = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) #cnts = imutils.grab_contours(cnts) # sort the contours from left-to-right and initialize the # 'pixels per metric' calibration variable #(cnts, _) = contours.sort_contours(cnts) pixelsPerMetric = None # loop over the contours individually for c in cnts: # if the contour is not sufficiently large, ignore it if cv2.contourArea(c) < 100: continue # compute the rotated bounding box of the contour orig = frame.copy() box = cv2.minAreaRect(c) #box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box) box = cv2.boxPoints(box) box = np.array(box, dtype="int") # order the points in the contour such that they appear # in top-left, top-right, bottom-right, and bottom-left # order, then draw the outline of the rotated bounding # box box = perspective.order_points(box) #绘制轮廓drawContours()函数 #第二个参数表示所有输入轮廓,每一个轮廓存储为一个点向量,即point类型的vector表示 #第三个参数为负数,则绘制所有轮廓 #第四个参数为轮廓颜色 #第五个参数为轮廓线条的粗细度 cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2) # loop over the original points and draw them for (x, y) in box: cv2.circle(orig, (int(x), int(y)), 5, (0, 0, 255), -1) # unpack the ordered bounding box, then compute the midpoint # between the top-left and top-right coordinates, followed by # the midpoint between bottom-left and bottom-right coordinates (tl, tr, br, bl) = box #print(box) (tltrX, tltrY) = midpoint(tl, tr) (blbrX, blbrY) = midpoint(bl, br) # compute the midpoint between the top-left and top-right points, # followed by the midpoint between the top-righ and bottom-right (tlblX, tlblY) = midpoint(tl, bl) (trbrX, trbrY) = midpoint(tr, br) # draw the midpoints on the image cv2.circle(orig, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1) cv2.circle(orig, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1) cv2.circle(orig, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1) cv2.circle(orig, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1) # draw lines between the midpoints cv2.line(orig, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)), (255, 0, 255), 2) cv2.line(orig, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)), (255, 0, 255), 2) # compute the Euclidean distance between the midpoints dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY)) dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY)) # if the pixels per metric has not been initialized, then # compute it as the ratio of pixels to supplied metric # (in this case, inches) if pixelsPerMetric is None: # pixelsPerMetric = dB / args["width"] pixelsPerMetric = dB / 20.5 # compute the size of the object dimA = dA / pixelsPerMetric dimB = dB / pixelsPerMetric D = 921.43 / pixelsPerMetric # draw the object sizes on the image cv2.putText(orig, "{:.1f}mm".format(dimA), (int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2) cv2.putText(orig, "{:.1f}mm".format(dimB), (int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2) cv2.putText(orig, "{:.1f}mm".format(D), (int(trbrX + 20), int(trbrY+20)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2) # show the output image cut_img = orig[int(tl[1]): int(bl[1]), int(tl[0]): int(tr[0])] resize_img = cv2.resize(cut_img, (28, 28)) # 调整图像尺寸为28*28 resize_img = cv2.cvtColor(resize_img, cv2.COLOR_RGB2GRAY) ret, thresh_img = cv2.threshold(resize_img, 127, 255, cv2.THRESH_BINARY) # 二值化 cv2.imwrite('D:\\deng\\ppp\\888.png', thresh_img) im = Image.open('D:\\deng\\ppp\\888.png') #im = cv2.imread('D:\\deng\\ppp\\888.png') #im_gray = cv2.cvtColor(im, cv2.COLOR_RGB2GRAY) data = list(im.getdata()) result = [(255 - x) * 1.0 / 255.0 for x in data] tensorflow_test.prediction_num(result) cv2.imshow('result', thresh_img) cv2.imshow("Image", orig) if cv2.waitKey(1) & 0xFF == ord('q'): cap.release() cv2.destroyAllWindows() break
转载地址:http://esfef.baihongyu.com/