SpringBoot实现识别图片中的身份证号与营业执照信息

<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <dependency>
        <groupId>org.bytedeco</groupId>
        <artifactId>javacv</artifactId>
        <version>1.5.6</version>
    </dependency>
    <dependency>
        <groupId>org.bytedeco</groupId>
        <artifactId>javacpp</artifactId>
        <version>1.5.6</version>
    </dependency>
    <!-- 其他依赖 -->
</dependencies>

import org.bytedeco.javacpp.*;
import org.bytedeco.opencv.opencv_core.*;
import static org.bytedeco.opencv.global.opencv_imgproc.*;
import org.bytedeco.tesseract.TessBaseAPI;

public class OCRService {

    public String doOCR(String imagePath) {
        TessBaseAPI tessBaseAPI = new TessBaseAPI();

        // 初始化Tesseract
        if (tessBaseAPI.Init(".", "ENG") != 0) {
            System.err.println("Could not initialize Tesseract.");
            return null;
        }

        // 读取图像文件
        Mat image = opencv_imgcodecs.imread(imagePath);
        // 图像预处理
        // 如调整大小、转为灰度图等
        cvtColor(image, image, COLOR_BGR2GRAY);

        // 设置图像
        tessBaseAPI.SetImage(image.data(), image.cols(), image.rows(), 1, image.step());

        // 识别文字
        BytePointer outText = tessBaseAPI.GetUTF8Text();
        String result = outText.getString();
        outText.deallocate();

        // 释放资源
        tessBaseAPI.End();

        return result;
    }
}

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class InfoExtractor {

    public String extractIDNumber(String text) {
        Pattern pattern = Pattern.compile("[0-9]{18}|[0-9]{15}");
        Matcher matcher = pattern.matcher(text);

        if (matcher.find()) {
            return matcher.group();
        }

        return null;
    }

    // 可以添加其他方法来提取不同的信息，例如营业执照号等
}

public class DocumentProcessor {

    public String processDocument(String imagePath) {
        OCRService ocrService = new OCRService();
        String text = ocrService.doOCR(imagePath);

        if (text != null && !text.isEmpty()) {
            InfoExtractor extractor = new InfoExtractor();
            String idNumber = extractor.extractIDNumber(text);

            return idNumber; // 返回提取的身份证号
        }

        return null;
    }
}

import org.bytedeco.opencv.opencv_core.Mat;
import static org.bytedeco.opencv.global.opencv_imgcodecs.*;
import static org.bytedeco.opencv.global.opencv_imgproc.*;

public class ImagePreprocessing {

    public Mat preprocessImage(String imagePath) {
        // 读取图像
        Mat image = imread(imagePath);

        // 转换为灰度图像
        Mat gray = new Mat();
        cvtColor(image, gray, COLOR_BGR2GRAY);

        // 应用高斯模糊，减少图像噪声
        Mat blurred = new Mat();
        GaussianBlur(gray, blurred, new Size(3, 3), 0);

        // 边缘检测
        Mat edged = new Mat();
        Canny(blurred, edged, 75, 200);

        // 这里可以根据需要添加其他图像处理步骤

        return edged;
    }
}

public class OCRService {

    public String doOCR(String imagePath) {
        TessBaseAPI tessBaseAPI = new TessBaseAPI();

        // 初始化Tesseract
        if (tessBaseAPI.Init(".", "ENG") != 0) {
            System.err.println("Could not initialize Tesseract.");
            return null;
        }

        ImagePreprocessing preprocessing = new ImagePreprocessing();
        Mat preprocessedImage = preprocessing.preprocessImage(imagePath);

        // 设置图像
        tessBaseAPI.SetImage(preprocessedImage.data(), preprocessedImage.cols(), preprocessedImage.rows(), 1, preprocessedImage.step());

        // 识别文字
        BytePointer outText = tessBaseAPI.GetUTF8Text();
        String result = outText.getString();
        outText.deallocate();

        // 释放资源
        tessBaseAPI.End();

        return result;
    }
}