高精度身份证识别系统

import os
import cv2
import numpy as np
import json
from paddleocr import PaddleOCR
import argparse

def adjust_brightness(image, gamma=1.0):
    """调整图像亮度"""
    inv_gamma = 1.0 / gamma
    table = np.array([((i / 255.0) ** inv_gamma) * 255 
                     for i in np.arange(0, 256)]).astype("uint8")
    return cv2.LUT(image, table)

def denoise_image(image):
    """图像去噪"""
    denoised = cv2.medianBlur(image, 3)
    denoised = cv2.GaussianBlur(denoised, (5, 5), 0)
    return denoised

def binarize_image(image):
    """图像二值化"""
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    binary = cv2.adaptiveThreshold(
        gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
        cv2.THRESH_BINARY, 11, 2
    )
    return binary

def correct_skew(image):
    """校正倾斜的身份证图像"""
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    edges = cv2.Canny(gray, 50, 150, apertureSize=3)
    
    lines = cv2.HoughLinesP(edges, 1, np.pi/180, 100, 
                           minLineLength=100, maxLineGap=10)
    
    if lines is None:
        return image
    
    angles = []
    for line in lines:
        x1, y1, x2, y2 = line[0]
        angle = np.degrees(np.arctan2(y2 - y1, x2 - x1))
        angles.append(angle)
    
    median_angle = np.median(angles)
    
    (h, w) = image.shape[:2]
    center = (w // 2, h // 2)
    M = cv2.getRotationMatrix2D(center, median_angle, 1.0)
    rotated = cv2.warpAffine(image, M, (w, h), 
                            flags=cv2.INTER_CUBIC, 
                            borderMode=cv2.BORDER_REPLICATE)
    
    return rotated

def enhance_image(image):
    """图像增强处理流水线"""
    enhanced = adjust_brightness(image, gamma=1.5)
    enhanced = denoise_image(enhanced)
    binary = binarize_image(enhanced)
    return enhanced, binary

def recognize_id_card(image_path):
    """识别身份证信息"""
    image = cv2.imread(image_path)
    if image is None:
        return {"error": "无法读取图像文件"}
    
    corrected = correct_skew(image)
    enhanced, binary = enhance_image(corrected)
    
    ocr = PaddleOCR(use_angle_cls=True, lang='ch', use_gpu=False)
    result = ocr.ocr(enhanced, cls=True)
    
    all_text = []
    for line in result:
        for word in line:
            all_text.append(word[1][0])
    
    id_info = parse_id_info(all_text)
    return id_info

def parse_id_info(text_list):
    """解析OCR识别的文本为身份证信息"""
    id_info = {
        "姓名": "", "性别": "", "民族": "",
        "出生日期": "", "住址": "", "身份证号": "",
        "签发机关": "", "有效期限": ""
    }
    
    # 信息提取逻辑（简化版）
    for i, text in enumerate(text_list):
        if "姓名" in text:
            id_info["姓名"] = text.split("姓名")[-1].strip()
        elif "性别" in text:
            id_info["性别"] = text.split("性别")[-1].strip()[:1]
        # 其他字段类似处理...
    
    # 清理身份证号
    id_num = ''.join(filter(lambda x: x.isdigit() or x.upper() == 'X', 
                          id_info["身份证号"]))
    if len(id_num) == 18:
        id_info["身份证号"] = id_num
    
    return id_info

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='身份证识别系统')
    parser.add_argument('image_path', type=str, help='身份证图像路径')
    parser.add_argument('--output', type=str, default='id_card_info.json', 
                        help='输出JSON文件路径')
    args = parser.parse_args()
    
    result = recognize_id_card(args.image_path)
    
    print("\n身份证识别结果:")
    for key, value in result.items():
        print(f"{key}: {value}")
    
    with open(args.output, 'w', encoding='utf-8') as f:
        json.dump(result, f, ensure_ascii=False, indent=2)
    
    print(f"\n结果已保存至: {args.output}")