验证码识别

1.图片二值化：先将RGB图像转为灰度图再转为二值图

2.图片去噪

3.使用pytesseract（OCR）将识别并“读取”嵌入图像中的文本

import pytesseract
from PIL import Image


def get_bin_table(threshold=170):
    """
    :param: threshold
    :return:
    """
    table = []
    for i in range(256):
        table.append(0) if i < threshold else table.append(1)
    return table


def type_trans(path):
    img = Image.open(path)
    img = img.convert('L')                      # 转换为灰度图像
    img = img.point(get_bin_table(), '1')       # 转换为二值图   1代表二值图， L代表灰度图
    return img


def cut_noise(img):
    width, height = img.size
    for i in range(1, width-1):       
        for j in range(1, height-1):   
            pixel_set = []           
            for m in range(i-1, i+2):
                for n in range(j-1, j+2):
                    if img.getpixel((m, n)) != 1:
                        pixel_set.append(img.getpixel((m, n)))
            if len(pixel_set) <= 2:
                print(pixel_set)
                img.putpixel((i, j), 1)
    return img


img = type_trans('image.jpg')
img = cut_noise(img)
text = pytesseract.image_to_string(img)
exclude_char_list = ' .:\\|\'\"?![],()~@#$%^&*_+-={};<>/¥'
text = ''.join([x for x in text if x not in exclude_char_list])