python opencv ocr_Python+OpenCV:OCR图像分割

通过将前景中所需的文本转换为黑色，同时将不需要的背景转换为白色，对图像进行预处理，有助于提高OCR的精度。此外，删除水平线和垂直线可以提高结果。这是去除不需要的噪声(如水平/垂直线)后的预处理图像。注意删除的边框和表格行

import cv2

# Load in image, convert to grayscale, and threshold

image = cv2.imread('1.jpg')

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

thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Find and remove horizontal lines

horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (35,2))

detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)

cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

cnts = cnts[0] if len(cnts) == 2 else cnts[1]

for c in cnts:

cv2.drawContours(thresh, [c], -1, (0,0,0), 3)

# Find and remove vertical lines

vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,35))

detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)

cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

cnts = cnts[0] if len(cnts) == 2 else cnts[1]

for c in cnts:

cv2.drawContours(thresh, [c], -1, (0,0,0), 3)

# Mask out unwanted areas for result

result = cv2.bitwise_and(image,image,mask=thresh)

result[thresh==0] = (255,255,255)

cv2.imshow('thresh', thresh)

cv2.imshow('result', result)

cv2.waitKey()