【Python】【OpenCV】定位条形码（一）

关于二维码和条形码的检测和识别，在OpenCV中已经有提供了对应的API，cv2.QRCodeDetector() | cv2.barcode_BarcodeDetector() ，相关的实现极其简单：

只需要上述短短三行代码即可检测二维码和条形码的位置并识别码内信息，相关parameter和retval自行查找。

下述是不借助OpenCV直接实现的API来实现定位

Code：

 1 def barcode(image):
 2     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 3     blur = cv2.GaussianBlur(gray, (5, 5), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
 4     cv2.imshow('GaussianBlur', blur)
 5     kernel_x = numpy.array([
 6         [-1, 0, 1],
 7         [-2, 0, 2],
 8         [-1, 0, 1]
 9     ])
10     kernel_y = numpy.array([
11         [-1, -2, -1],
12         [0, 0, 0],
13         [1, 2, 1]
14     ])
15     x = cv2.filter2D(blur, -1, kernel_x)
16     y = cv2.filter2D(blur, -1, kernel_y)
17     cv2.imshow('Sobel', x)
18     _, threshold = cv2.threshold(x, 127, 255, cv2.THRESH_BINARY)
19     kernel = numpy.ones((3, 3), numpy.uint8)
20     r_e = cv2.erode(threshold, kernel, iterations=1)
21     r_d = cv2.dilate(r_e, kernel, iterations=10)
22     contours, hir = cv2.findContours(r_d, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
23     max_contour = numpy.array(max(contours, key=cv2.contourArea))
24     x, y, w, h = cv2.boundingRect(max_contour)
25     cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)