python识别图片中是否包含水印(opencv)

最近在写爬虫，但爬下来的很多图片被加了水印，而且水印的位置不是固定的。本来不是搞图形图像处理的我，只好google了一把，看到很多用opencv来解决类似问题。这里记录一下水印识别的代码.

首先，必须安装如下依赖, 用了豆瓣的镜像，速度快些.

pip install matplotlib -i  https://pypi.douban.com/simple pip install numpy pip install opencv-python -i  https://pypi.douban.com/simple

识别水印的代码如下:

import cv2 import numpy as np     # Read the main image img_rgb = cv2.imread('maven-spotbugs-static-code.png')  # Convert it to grayscale img_gray = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)   # Read the template template = cv2.imread('mark.jpg',0)  # Store width and heigth of template in w and h w, h = template.shape[::-1]  # Perform match operations. res = cv2.matchTemplate(img_gray,template,cv2.TM_CCOEFF_NORMED)  # Specify a threshold threshold = 0.8  # Store the coordinates of matched area in a numpy array loc = np.where( res >= threshold) x=loc[0] y=loc[1] # Draw a rectangle around the matched region. if len(x) and len(y):     for pt in zip(*loc[::-1]):         cv2.rectangle(img_rgb, pt, (pt[0] + w, pt[1] + h), (0,255,255), 2)      # Show the final image with the matched area.     #cv2.imshow('Detected',img_rgb)     cv2.imwrite("test_001.png", img_rgb)     print("I found the watermark") else:     print('there is no watermark')

找到水印之后，还会把水印所在位置框选出来，而且还可以得到坐标，这为以后替换水印打下了基础.

From：一号门