OCR预处理：矫正图片中的文本信息（opencv）

1.首先导入工程所需要的三方包，这里需要opencv、numpy、math

import cv2
import numpy as np
import math

2.读取图片

img = cv2.imread(file_path)

3.图片去噪

img_c = cv2.fastNlMeansDenoisingColored(img, None, 10, 10, 7, 21)

4.处理成灰度图

gray = cv2.cvtColor(img_c, cv2.COLOR_BGR2GRAY)

5.Sobel算子，x方向求梯度,主要用于获得数字图像的一阶梯度，常见的应用和物理意义是边缘检测。（可以根据需求选择算子）

 sobel = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize=3)

6.二值化

ret, binary = cv2.threshold(sobel, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY)

7.霍夫直线

    hufu = binary.astype(np.uint8)
    lines = cv2.HoughLinesP(hufu, 1, np.pi / 180, 30, minLineLength=40, maxLineGap=100)

    # 在图像上展示霍夫直线描出的直线
    # for line in lines:
    #     cv2.line(img, (line[0][0], line[0][1]), (line[0][2], line[0][3]), (0, 0, 255), 2)

8.求出所有直线斜率，求出众数（考虑误差），这一步会产生个bug，因为这些直线是利用霍夫直线找到的，所以说需要根据实际场景来设置霍夫直线的相关参数，不然会对图片中的线性非常敏感，比如条形码

    k_dict = {}
    k = 0

    
    for line in lines:
        if line[0][2] - line[0][0] == 0:
            continue
        print(line[0][3],line[0][1],line[0][2],line[0][0])
        k = (line[0][3] - line[0][1]) / (line[0][2] - line[0][0])
        # α = atan(k) * 180 / PI
        k = math.atan(k) * 180 / np.pi
        if len(k_dict.keys()) == 0 :
            k_dict[k] = 1
        else:
            flag = False
            for item in k_dict.keys():
                if abs(item - k) < 2:
                    flag = True
                    k_dict[item] += 1
                    break
            if not flag:
                k_dict[k] = 1

    must_k_num = 0
    must_key = 0
    for item in k_dict.keys():
        if k_dict[item] > must_k_num:
            must_k_num = k_dict[item]
            must_key = item


    print(must_key)

9.旋转图像，在旋转图像之前需要对图片进行填充防止旋转后边角溢出（这一步可以根据角度和勾股定理来计算精准的填充大小），利用仿射变换来旋转图像

#旋转图像

    h, w = img.shape[:2]
    add_w = int((((w*w + h*h) ** 0.5) - w)/2)
    add_h = int((((w*w + h*h) ** 0.5) - h)/2)
    print(add_w,add_h)

    img = cv2.copyMakeBorder(img,add_h,add_h,add_w,add_w, cv2.BORDER_CONSTANT,value=[0,0,0])

    h, w = img.shape[:2]
    center = (w//2, h//2)


    M = cv2.getRotationMatrix2D(center, must_key, 1.0)
    rotated = cv2.warpAffine(img, M, (w, h), flags=cv2.INTER_CUBIC)

    cv2.imwrite(file_path,rotated)


    cv2.imshow("rotated", rotated)
    cv2.waitKey(0)

 

 

 

全部代码在这！！！！！！

import cv2
import numpy as np
import math

def rotate(file_path):
    img = cv2.imread(file_path)

    #去噪
    img_c = cv2.fastNlMeansDenoisingColored(img, None, 10, 10, 7, 21)

    # 灰度图
    gray = cv2.cvtColor(img_c, cv2.COLOR_BGR2GRAY)
    # cv2.imshow("gray", gray)


    # Sobel算子，x方向求梯度,主要用于获得数字图像的一阶梯度，常见的应用和物理意义是边缘检测。
    sobel = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize=3)

    # 二值化
    ret, binary = cv2.threshold(sobel, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY)


    # 霍夫直线
    hufu = binary.astype(np.uint8)
    lines = cv2.HoughLinesP(hufu, 1, np.pi / 180, 30, minLineLength=40, maxLineGap=100)

    # for line in lines:
    #     cv2.line(img, (line[0][0], line[0][1]), (line[0][2], line[0][3]), (0, 0, 255), 2)


    k_dict = {}
    k = 0

    #求出所有直线斜率，求出众数（考虑误差）
    for line in lines:
        if line[0][2] - line[0][0] == 0:
            continue
        print(line[0][3],line[0][1],line[0][2],line[0][0])
        k = (line[0][3] - line[0][1]) / (line[0][2] - line[0][0])
        # α = atan(k) * 180 / PI
        k = math.atan(k) * 180 / np.pi
        if len(k_dict.keys()) == 0 :
            k_dict[k] = 1
        else:
            flag = False
            for item in k_dict.keys():
                if abs(item - k) < 2:
                    flag = True
                    k_dict[item] += 1
                    break
            if not flag:
                k_dict[k] = 1

    must_k_num = 0
    must_key = 0
    for item in k_dict.keys():
        if k_dict[item] > must_k_num:
            must_k_num = k_dict[item]
            must_key = item


    print(must_key)

    #旋转图像

    h, w = img.shape[:2]
    add_w = int((((w*w + h*h) ** 0.5) - w)/2)
    add_h = int((((w*w + h*h) ** 0.5) - h)/2)
    print(add_w,add_h)

    img = cv2.copyMakeBorder(img,add_h,add_h,add_w,add_w, cv2.BORDER_CONSTANT,value=[0,0,0])

    h, w = img.shape[:2]
    center = (w//2, h//2)


    M = cv2.getRotationMatrix2D(center, must_key, 1.0)
    rotated = cv2.warpAffine(img, M, (w, h), flags=cv2.INTER_CUBIC)

    cv2.imwrite(file_path,rotated)


    cv2.imshow("rotated", rotated)
    cv2.waitKey(0)

 

 

谢谢大家观看！