ai_qback/make_docx_demo/check_test_table/image_preprocess2.py

# -*- coding:utf-8 -*-
"""
20250114 在单词上划线，分别有斜杠、反斜杠、横着划线三种方式；找到它们的位置

"""
import re
import time

from PIL import Image, ImageFilter
import numpy as np
import cv2
import json
from pathlib import Path
from baidu_ocr import high_ocr_location


def test_log(text: str):
    if type(text) == dict:
        text = json.dumps(text, ensure_ascii=False)
    with open("log.txt", "w", encoding="utf-8") as f:
        f.write(str(text))


class PreprocessImage:
    def __init__(self, image_path):
        self.image_path = image_path 
        self.template_image_path = "template.jpg" 

        self.image = cv2.imread(image_path) 
        self.template_image = cv2.imread(self.template_image_path)
        self.temp_h, self.temp_w = self.template_image.shape[:2] 

    def correct_image(self, point_tuple,image_path='sharpen_image.jpg'):
        """图像矫正
        point_tuple:传过来的4个点坐标的元组"""
        sharpen_image = cv2.imread(image_path)

        src_points = np.float32(point_tuple)

       
       
        dst_points = np.float32([[122, 78], [1070, 78], [122, 2730], [1070, 2730]]) 

        M = cv2.getPerspectiveTransform(src_points, dst_points)
       
        transformed_image = cv2.warpPerspective(sharpen_image, M, (self.temp_w, self.temp_h))

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

       
        blurred = cv2.GaussianBlur(gray, (5, 5), 0)

       
       

       
       
       
       
       
       
       
       

       
        image_rgb = cv2.cvtColor(blurred, cv2.COLOR_BGR2RGB)
       
        cv2.imwrite('transformed_image.jpg', image_rgb)

    def sharpen_image(self):
       
        img = Image.open(self.image_path)
        sharpened_img = img.filter(ImageFilter.SHARPEN)
        sharpened_img.save('sharpen_image.jpg') 

    @staticmethod
    def parser_ocr(ocr_data):
        for word_item in ocr_data['words_result']:
           
            for char_item in word_item['chars']:

                pass



    def run(self):
       
        self.sharpen_image() 
        ocr_data = high_ocr_location(self.image_path)
        point_tuple = self.parser_ocr(ocr_data)
        self.correct_image(point_tuple)


class ComparisonAlgorithm:
    """比较算法核心"""

    def __init__(self, transformed_image, ocr_data):
        self.transformed_image = cv2.imread(transformed_image) 
        self.ocr_data = ocr_data 
        self.order_ocr_data = {} 
        self.already_find_index = set() 

        self.image = Image.open(transformed_image) 

    @staticmethod
    def separate_numbers_and_letters(text):
        """正则提取数字和字母"""
        numbers = "".join(re.findall(r'\d+', text)) 
        letters = "".join(re.findall(r'[a-zA-Z]+', text)) 
        return numbers, letters

    def is_line_word(self, x, y):
        """判断点的颜色是否符合标准; cv2取点速度没有pillow快
        指定要查询的点的坐标 (x, y)"""

       
       
       

        rgb_color = self.image.getpixel((x, y))
        r, g, b = rgb_color

        if all([r < 130, g < 130, b < 130]):
            return 1
        return 0

    def __make_order_ocr_data(self):
        for word_item in self.ocr_data['words_result']:
            word = word_item['words']
            if word[0].isdigit() and len(word) >= 2: 
               
                word_text = word_item['words']
                location = word_item['location'] 
                first_char_location = word_item['chars'][0]['location'] 
                end_char_location = word_item['chars'][-1]['location'] 
                chars_location = word_item['chars'] 

                numbers, letters = self.separate_numbers_and_letters(word_text)
                if numbers not in self.order_ocr_data: 
                    self.order_ocr_data[numbers] = {"word": letters, "location": location, "chars_location": chars_location,
                                                    "first_char_location": first_char_location, "end_char_location": end_char_location}

    def color_algorithm_1(self, int_index, word_location, first_char_location, word):
        """
        颜色算法1，正常单词
        int_index:整数序号
        word_location：这个序号的单词的整行位置；对应 self.order_ocr_data[current_index]['location']
        first_char_location： 第一个字母的位置；对应 self.order_ocr_data[current_index]['first_char_location']
        word:具体序号的单词，标识用
        """
        next_index = str(int_index + 1) 
        black_count_1 = 0 

        for x in range(word_location['left'], word_location['left'] + word_location['width']):

           
            b_top, b_height = first_char_location['top'], int(first_char_location['height'])
            bottom_location_y = b_top + b_height 

            if int_index == 50 or int_index == 100:
                next_word_top_location = bottom_location_y + b_height * 2
           
            elif next_index in self.order_ocr_data and (
                    self.order_ocr_data[next_index]['first_char_location']['top'] - bottom_location_y) < b_height:
                next_word_location = self.order_ocr_data[next_index]['first_char_location']
                next_word_top_location = next_word_location['top'] + int(next_word_location['height'] / 8)
            else:
               
               
                next_word_top_location = bottom_location_y + int(b_height * 0.5)

            for y in range(bottom_location_y, next_word_top_location):
                result = self.is_line_word(x, y)
                if result:
                    black_count_1 += 1
                    break

        black_count_per = black_count_1 / (word_location['width'])
        if black_count_per > 0.8: 
            print(f"{int_index}正常划线{black_count_per:.2f}", word)
            self.already_find_index.add(int_index)
            return int_index 
       
       

    def color_algorithm_2(self, int_index, word_location, word):
        """颜色算法2，单词自身中间的黑点率
        int_index:整数序号
        word_location：这个序号的单词的整行位置；对应 self.order_ocr_data[current_index]['location']
        word:具体序号的单词，标识用
        """
        black_count_2 = 0 
        for x in range(word_location['left'], word_location['left'] + word_location['width']):

            mid = word_location['top'] + int(word_location['height'] / 2)
            bottom = word_location['top'] + int(word_location['height']) + 5 

            for y in range(mid, bottom):
                result = self.is_line_word(x, y)
                if result:
                    black_count_2 += 1
                    break

        black_count_per = black_count_2 / (word_location['width'])
        if black_count_per > 0.92: 
            print(f"{int_index}中间划线{black_count_per:.2f}", word)
            self.already_find_index.add(int_index)
            return int_index 
       
       

    def color_algorithm_3(self, int_index, word_location, end_char_location, word):
        """
        颜色算法3，正常单词的左右各推20个像素点，判断下黑点率
        int_index:整数序号
        word_location：这个序号的单词的整行位置；对应 self.order_ocr_data[current_index]['location']
        end_char_location： 最后一个字母的位置；对应 self.order_ocr_data[current_index]['end_char_location']
        word:具体序号的单词，标识用
        """
        next_index = str(int_index + 1) 
        black_count_1 = 0 
        moving_distance = 20

        """这是在获取所有需要的横向左右x坐标"""
        all_x = [] 
        for i in range(word_location['left'] - moving_distance, word_location['left']):
            all_x.append(i)
        word_right_loca = word_location['left'] + word_location['width'] + 2 
        for i in range(word_right_loca, word_right_loca + moving_distance):
            all_x.append(i)

        b_top, b_height = word_location['top'], int(word_location['height'])
        bottom_location_y = b_top + b_height 
       
        bottom_location_y_half = end_char_location['top'] + int(end_char_location['height'] * 0.8) 

        for x in all_x:
            if int_index == 50 or int_index == 100:
                next_word_top_location = bottom_location_y + b_height * 2
           
            elif next_index in self.order_ocr_data and (
                    self.order_ocr_data[next_index]['first_char_location']['top'] - bottom_location_y) < b_height:
                next_word_location = self.order_ocr_data[next_index]['first_char_location']
                next_word_top_location = next_word_location['top'] + 3 
            else:
               
               
                next_word_top_location = bottom_location_y + int(b_height * 0.3)

            for y in range(bottom_location_y_half, next_word_top_location):
                result = self.is_line_word(x, y)
                if result:
                    black_count_1 += 1
                    break

        black_count_per = black_count_1 / len(all_x)
        if black_count_per > 0.4: 
            print(f"{int_index}前后双边划线{black_count_per:.2f}", word)
            self.already_find_index.add(int_index)
            return int_index 
       
       

    def color_algorithm_4(self, int_index, word_location, chars_location, word):
        """灰度图极差算法"""
       
       

        for char_index, char_dict in enumerate(chars_location):
            if char_dict['char'] == '.' or char_dict['char'] == ',':
                point_location, point_char_index = char_dict['location'], char_index
                break
        else: 
            char_index = 2
            point_location, point_char_index = chars_location[char_index]['location'], char_index

        white_block = 0
        point_location_half = point_location['top'] + point_location['height']//2
        y1, y2 = point_location_half, point_location_half + point_location['height']
        for x in range(point_location['left'], point_location['left'] + point_location['width']):
            roi_image = self.transformed_image[y1:y2, x:x + 1]
            min_val = np.min(roi_image)
            max_val = np.max(roi_image)
            range_value = max_val - min_val
            if min_val>110 or range_value < 90:
                white_block +=1

        if white_block/point_location['width'] < 0.1:
            print(f"{int_index}极差算法 {word},左{point_location['left']},宽{point_location['width']},高{point_location['height']},{y1},{y2}")
            self.already_find_index.add(int_index)
            return int_index

       
        white_block = 0
        end_char_location = chars_location[-2]['location']
        bottom = end_char_location['top'] + end_char_location['height']
        y1, y2 = bottom+2, bottom + end_char_location['height']-10
        for x in range(end_char_location['left'], end_char_location['left'] + point_location['width']):
            roi_image = self.transformed_image[y1:y2, x:x + 1]
            min_val = np.min(roi_image)
            max_val = np.max(roi_image)
            range_value = max_val - min_val
            if min_val>110 or range_value < 90:
                white_block +=1

        if white_block/point_location['width'] < 0.1:
            print(f"{int_index}极差算法二 {word},左{point_location['left']},宽{point_location['width']},高{point_location['height']},{y1},{y2}")
            self.already_find_index.add(int_index)
            return int_index



   
    def core_algorithm(self):
        self.__make_order_ocr_data()

        for int_index in range(1, 101):
            current_index = str(int_index)
            if current_index not in self.order_ocr_data:
                continue

            current_dict = self.order_ocr_data[current_index]
            word = current_dict['word'] 
            word_location = current_dict['location'] 
            first_char_location = current_dict['first_char_location'] 
            end_char_location = current_dict['end_char_location'] 
            chars_location = current_dict['chars_location']

            if self.color_algorithm_1(int_index=int_index, word_location=word_location, first_char_location=first_char_location, word=word):
                continue

            if self.color_algorithm_2(int_index=int_index, word_location=word_location, word=word):
                continue

            if self.color_algorithm_3(int_index=int_index, word_location=word_location, end_char_location=end_char_location, word=word):
                continue

            if self.color_algorithm_4(int_index=int_index, word_location=word_location, chars_location=chars_location, word=word):
                continue


if __name__ == '__main__':
   
    image_path = r"C:\Users\86131\Desktop\4.jpg"

   
    script_path = Path(__file__).resolve()
   
    script_directory = script_path.parent
   
    transformed_image_path = str(Path(script_directory, r"transformed_image.jpg"))

   
    pi = PreprocessImage(image_path)
    pi.run()

    transformed_image_ocr_data = high_ocr_location(transformed_image_path) 
    test_log(transformed_image_ocr_data) 

    ca = ComparisonAlgorithm(transformed_image=transformed_image_path, ocr_data=transformed_image_ocr_data)
    ca.core_algorithm()