通过轮廓法校正数字串图像，然后使用垂直投影法分割数字串

倾斜的字符串数字因为垂直投影后的直方图存在区域连接的问题，直接对数字进行分割较为困难，因此在数字串分割前对数字串进行倾斜校正，校正后分割数字明显可以提高分割的准确度。

import numpy as np
import os
import cv2
import random
import string
import glob
import os.path
import time
from PIL import Image


def rotate(image, angle, center=None, scale=1.0):
    (w, h) = image.shape[0:2]
    if center is None:
        center = (w // 2, h // 2)
    wrapMat = cv2.getRotationMatrix2D(center, angle, scale)
    return cv2.warpAffine(image, wrapMat, (h, w))

# 使用矩形框
def getCorrect():
    # 读取图片，灰度化
    path = 'D:\\picture\\test1\\test\\num\\'       ##原图存放地址
    save_correct = 'D:\\picture\\test1\\test\\correct\\'   ##倾斜矫正后的图片存放地址
    paths = glob.glob(os.path.join(path, '*.jpg'))
    for filename in paths:
        img = cv2.imread(filename)
        print(filename)
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)  # 转换了灰度化
        # 图像取非
        grayNot = cv2.bitwise_not(gray)
        # OTSU二值化
        threImg = cv2.threshold(grayNot, 0, 255, cv2.THRESH_OTSU, )[1]
        # 获得有文本区域的点集,求点集的最小外接矩形框，并返回旋转角度
        coords = np.column_stack(np.where(threImg > 0))
        angle = cv2.minAreaRect(coords)[-1]
        if angle < -45:
            angle = -(angle + 90)
        else:
            angle = -angle

        # 仿射变换，将原图校正
        dst = rotate(threImg, angle)         #threImg校正二值化图片，src校正原图
        #cv2.imshow("dst", dst)
        salt = ''.join(random.sample(string.digits, 8))  # 随机输出8位由数字组成的字符串
        cv2.imwrite(save_correct + salt + '.jpg', dst)  # 存储裁剪得到的图像
        #cv2.waitKey()
        #print(angle)

    ###############分割字符#####################

        # 1、读取图像，并把图像转换为灰度图像并显示
       ## img = cv2.imread("D:/picture/test1/1.png")  # 读取图片
       #img_gray = cv2.cvtColor(dst, cv2.COLOR_BGR2GRAY)  # 转换了灰度化
       # cv2.imshow('gray', img_gray)  # 显示图片
        # 2、将灰度图像二值化，设定阈值是100
        #img_thre = img_gray
        #cv2.threshold(img_gray, 0, 255, cv2.THRESH_OTSU, img_thre)
        #cv2.imshow('threshold', img_thre)
        # 3、保存黑白图片
       # cv2.imwrite('thre_res.png', img_thre)


        # 4、分割字符
        white = []  # 记录每一列的白色像素总和
        black = []  # ..........黑色.......
        height = dst.shape[0]
        width = dst.shape[1]
        white_max = 0
        black_max = 0
        # 计算每一列的黑白色像素总和
        for i in range(width):
            s = 0  # 这一列白色总数
            t = 0  # 这一列黑色总数
            for j in range(height):
                if dst[j][i] == 255:
                    s += 1
                if dst[j][i] == 0:
                    t += 1
            white_max = max(white_max, s)
            black_max = max(black_max, t)
            white.append(s)
            black.append(t)
           # print(s)
           # print(t)
        arg = False  # False表示白底黑字；True表示黑底白字
        if black_max > white_max:
            arg = True


        # 分割图像
        def find_end(start_):
            end_ = start_ + 1
            for m in range(start_ + 1, width - 1):
                if (black[m] if arg else white[m]) > (
                        0.85 * black_max if arg else 0.85 * white_max):  # 0.95这个参数请多调整，对应下面的0.05,这个参数控制分割的阈值
                    end_ = m
                    break
            return end_

        n = 1
        start = 1
        end = 2
        while n < width - 2:
            n += 1
            if (white[n] if arg else black[n]) > (0.15 * white_max if arg else 0.15 * black_max):
                # 上面这些判断用来辨别是白底黑字还是黑底白字
                # 0.05这个参数请多调整，对应上面的0.95
                start = n
                end = find_end(start)
                n = end
                if end - start > 5:
                    cj = dst[1:height, start:end]
                    #cv2.imshow('caijian', cj)
                    salt = ''.join(random.sample(string.digits, 8))  # 随机输出8位由数字组成的字符串
                    cv2.imwrite(r"D:\\picture\\test1\\test\\seg\\" + salt + '.jpg',cj)  # 存储裁剪得到的图像
                    #cv2.waitKey(0)


if __name__ == "__main__":
    start = time.time()
    getCorrect()
    end = time.time()
    print("Execution Time:", end - start)