作者:叶庭云
源自:快学python
昨天十行代码实现文字识别,感觉怎样,是不是很爽
今天咋们继续利用pillow和pytesseract来实现验证码的识别
一、环境配置需要 pillow 和 pytesseract 这两个库,pip install 安装就好了。pip install pillow -i http://pypi.douban.com/simple --trusted-host pypi.douban.compip install pytesseract -i http://pypi.douban.com/simple --trusted-host pypi.douban.com安装好Tesseract-OCR.exe
pytesseract 库的配置:搜索找到pytesseract.py,打开该.py文件,找到 tesseract_cmd,改变它的值为刚才安装 tesseract.exe 的路径。
二、验证码识别
识别验证码,需要先对图像进行预处理,去除会影响识别准确度的线条或噪点,提高识别准确度。
实例1import cv2 as cvimport pytesseractfrom PIL import Imagedef recognize_text(image): # 边缘保留滤波 去噪 dst = cv.pyrMeanShiftFiltering(image, sp=10, sr=150) # 灰度图像 gray = cv.cvtColor(dst, cv.COLOR_BGR2GRAY) # 二值化 ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU) # 形态学操作 腐蚀 膨胀 erode = cv.erode(binary, None, iterations=2) dilate = cv.dilate(erode, None, iterations=1) cv.imshow("dilate", dilate) # 逻辑运算 让背景为白色 字体为黑 便于识别 cv.bitwise_not(dilate, dilate) cv.imshow("binary-image", dilate) # 识别 test_message = Image.fromarray(dilate) text = pytesseract.image_to_string(test_message) print(f"识别结果:{text}")src = cv.imread(r"./test/044.png")cv.imshow("input image", src)recognize_text(src)cv.waitKey(0)cv.destroyAllWindows()
运行效果如下:识别结果:3n3DProcess finished with exit code 0
实例2import cv2 as cvimport pytesseractfrom PIL import Imagedef recognize_text(image): # 边缘保留滤波 去噪 blur =cv.pyrMeanShiftFiltering(image, sp=8, sr=60) cv.imshow("dst", blur) # 灰度图像 gray = cv.cvtColor(blur, cv.COLOR_BGR2GRAY) # 二值化 ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU) print(f"二值化自适应阈值:{ret}") cv.imshow("binary", binary) # 形态学操作 获取结构元素 开操作 kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 2)) bin1 = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel) cv.imshow("bin1", bin1) kernel = cv.getStructuringElement(cv.MORPH_OPEN, (2, 3)) bin2 = cv.morphologyEx(bin1, cv.MORPH_OPEN, kernel) cv.imshow("bin2", bin2) # 逻辑运算 让背景为白色 字体为黑 便于识别 cv.bitwise_not(bin2, bin2) cv.imshow("binary-image", bin2) # 识别 test_message = Image.fromarray(bin2) text = pytesseract.image_to_string(test_message) print(f"识别结果:{text}")src = cv.imread(r"./test/045.png")cv.imshow("input image", src)recognize_text(src)cv.waitKey(0)cv.destroyAllWindows()
运行效果如下:二值化自适应阈值:181.0识别结果:8A62N1Process finished with exit code 0
实例3import cv2 as cvimport pytesseractfrom PIL import Imagedef recognize_text(image): # 边缘保留滤波 去噪 blur = cv.pyrMeanShiftFiltering(image, sp=8, sr=60) cv.imshow("dst", blur) # 灰度图像 gray = cv.cvtColor(blur, cv.COLOR_BGR2GRAY) # 二值化 设置阈值 自适应阈值的话 黄色的4会提取不出来 ret, binary = cv.threshold(gray, 185, 255, cv.THRESH_BINARY_INV) print(f"二值化设置的阈值:{ret}") cv.imshow("binary", binary) # 逻辑运算 让背景为白色 字体为黑 便于识别 cv.bitwise_not(binary, binary) cv.imshow("bg_image", binary) # 识别 test_message = Image.fromarray(binary) text = pytesseract.image_to_string(test_message) print(f"识别结果:{text}")src = cv.imread(r"./test/045.jpg")cv.imshow("input image", src)recognize_text(src)cv.waitKey(0)cv.destroyAllWindows()
运行效果如下:二值化设置的阈值:185.0识别结果:7364Process finished with exit code 0
结语
以上就是这篇文章的全部内容了,希望本文的内容对大家的学习或者工作具有一定的参考学习价值,谢谢大家对小编的支持。