code-labs/lab-tesseract/clear.py

import os
from PIL import Image

def clear_save_image(image_path):
	image = Image.open(image_path)
	image = clear_image(image)
	image = image.convert('L') #灰度处理
	file_name = os.path.splitext(os.path.basename(image_path))[0]
	save_path = os.path.join(os.path.dirname(image_path), '../clear_image', file_name + '.jpg')
	image.save(save_path) #图片转换成tif保存到clear_image文件夹中

def clear_image(image):
	image = image.convert('RGB')
	width = image.size[0]
	height = image.size[1]
	noise_color = get_noise_color(image)
	for x in range(width):
		for y in  range(height):
			#清除边框和干扰色
			if (x == 0 or y == 0 or x == width - 1 or y == height - 1 
				or image.getpixel((x, y)) == noise_color):
				image.putpixel((x, y), (255, 255, 255))
			#背景调整为白色	
			if (image.getpixel((x, y))[0] > 180 and image.getpixel((x, y))[1] > 180 and image.getpixel((x, y))[2] > 180):
				image.putpixel((x, y), (255, 255, 255))
	return image

def get_noise_color(image):
	for y in range(1, image.size[1] - 1):
		# 获取第2列非白的颜色
		(r, g, b) = image.getpixel((2, y))
		if r < 255 and g < 255 and b < 255:
			return (r, g, b)

if __name__ == '__main__':
	os.makedirs('./clear_image/', exist_ok=True)
	for file_path in os.listdir('image'):
		file_path = os.path.join('image', file_path)
		if os.path.isfile(file_path):
			clear_save_image(file_path)
	print("clear end.")