java中实现OCR文字提取的几个常用工具(Tesseract、PaddleOCR及RapidOCR)

        <!-- Tesseract OCR 主依赖 -->
        <dependency>
            <groupId>net.sourceforge.tess4j</groupId>
            <artifactId>tess4j</artifactId>
            <version>5.8.0</version> <!-- 使用最新版本 -->
            <exclusions>
                <!-- 排除 tess4j 自带的旧版 JNA -->
                <exclusion>
                    <groupId>net.java.dev.jna</groupId>
                    <artifactId>jna</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.apache.pdfbox</groupId>
                    <artifactId>pdfbox</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <!-- 显式添加最新版 JNA -->
        <dependency>
            <groupId>net.java.dev.jna</groupId>
            <artifactId>jna</artifactId>
            <version>5.13.0</version> <!-- 使用最新稳定版 -->
        </dependency>
        <!-- 用来判断文件实际类型 -->
        <dependency>
            <groupId>org.apache.tika</groupId>
            <artifactId>tika-core</artifactId>
            <version>2.7.0</version>
        </dependency>
         <!-- 如果需要 PDF 支持 -->
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.29</version> <!-- 最新稳定版 -->
        </dependency>

   //对传入的文件进行处理
   public File imageCheck(MultipartFile multipartFile) {
        File tempFile = null;
        File reNameFile = null;
        try {
            // 使用UUID生成唯一字符串
            String uuid = UUID.randomUUID().toString();
            tempFile = new File(SAVE_PATH+multipartFile.getOriginalFilename());
            multipartFile.transferTo(tempFile);
            //获取实际类型；举例传入图片后缀为png但实际图片类型为jpg,此时需要对图片后缀更正，若不进行更正识别时会存在异常
            String mimeType = new Tika().detect(tempFile);

            System.out.println(mimeType);
            String[] type = mimeType.split("/");
            String fileName = SAVE_PATH+uuid+"."+type[1];
            reNameFile = new File(fileName);
            tempFile.renameTo(reNameFile);
            //openVC(fileName); //图片预处理
        } catch (Exception e) {
            if (reNameFile != null) {
                reNameFile.delete();
            }
            throw new RuntimeException("文件生成异常", e);
        } finally {
            if (tempFile != null) {
                tempFile.delete();
            }
        }
        return reNameFile;
    }
    //pdf文字提取
    public  String convertPdfToImage(Tesseract tesseract, File pdfFile, int dpi) {
        try (PDDocument document = PDDocument.load(pdfFile)) {
            List<Word> allWorld = new ArrayList<>();
            for (int page = 0; page < document.getNumberOfPages(); page++) {
                PDFRenderer renderer = new PDFRenderer(document);
                // 渲染指定页面为图像，dpi参数控制图像质量
                BufferedImage bf = renderer.renderImageWithDPI(page, dpi);
                List<Word> words =  tesseract.getWords(bf, ITessAPI.TessPageIteratorLevel.RIL_WORD);
                allWorld.addAll(words);
            }
            return JSONObject.toJSONString(allWorld);
        } catch (Exception e) {
            e.printStackTrace();
            return null;
        }
    }
    //此处为开始，开始传入图片，对图片进行文字识别
    public String ocrCore(MultipartFile multipartFile) {
        Tesseract tesseract = new Tesseract();
        File reNameFile = null;
        String result = "";
        try {
            reNameFile  = imageCheck(multipartFile);

            tesseract.setDatapath(TEST_DATA_PATH); // 设置训练数据路径
            tesseract.setLanguage("chi_sim+chi_tra+eng"); // 同时识别中文和英文
            BufferedImage bf = null;
            if (reNameFile.getAbsolutePath().endsWith(".pdf")) {
                result= convertPdfToImage(tesseract,reNameFile, 300);
            } else {
                bf = ImageIO.read(reNameFile);
                List<Word> words =  tesseract.getWords(bf, ITessAPI.TessPageIteratorLevel.RIL_WORD);
                result = JSONObject.toJSONString(words);
            }
            //result = tesseract.doOCR(reNameFile);
            System.out.println(result);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (reNameFile != null) {
                reNameFile.delete();
            }
        }
        return result;
    }

pip install paddlepaddle paddleocr

##若需要识别pdf文件需要安装以下python组件
pip install pdf2image poppler-utils

from flask import Flask, request, jsonify
from paddleocr import PaddleOCR
from pdf2image import convert_from_path
import numpy as np
import json

app = Flask(__name__)
ocr = PaddleOCR(use_angle_cls=True, lang="ch",use_gpu=True)

@app.route('/ocr', methods=['POST'])
def ocr_api():
    img_path = request.json['image_path']
    if is_pdf(img_path) :
        # 将 PDF 转换为图像列表（每页一张图）
        images = convert_from_path(img_path, dpi=300)  # dpi 越高越清晰，但速度越慢
        resp = []
        # 遍历所有页面识别文字
        for i, image in enumerate(images):
            # 将 PIL.Image 转为 numpy 数组
            img_np = np.array(image)
            result = ocr.ocr(img_np)
            resp.append(result)
        return json.dumps(resp, ensure_ascii=False)
    else:
        result = ocr.ocr(img_path, cls=True)
        return json.dumps(result, ensure_ascii=False)



def is_pdf(file_path):
    return file_path.lower().endswith('.pdf')

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000, threaded=False)


###多线程情况下 连续解析同一张图片可能会存在 OpenCV/Pillow 的图像解码冲突，可能导致间歇性失败

# pps 会对复杂文本进行布局分析，支持识别分栏样式文档的识别
        table_engine = PPStructure(recovery=True, use_pdf2docx_api=True)

        # 处理图片或PDF
        result = table_engine(img_path)
        #result = ocr.ocr(img_path, cls=True)
        texts = []
        for region in result:
            if region['type'] in ('text', 'equation','title', 'header','figure','figure_caption'):  # 只保留文本类型区域
                texts.append(one_row(region['res']))
            if region['type'] == 'table':
                texts.append(region['res']['html'])
        return json.dumps(texts, ensure_ascii=False)

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\r\n    \"image_path\":\"D:/Users/Administrator/Document/personal/ocr/结构化文档样式/记录纸.pdf\"\r\n}\r\n");
Request request = new Request.Builder()
  .url("http://localhost:5000/ocr")
  .method("POST", body)
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();

 <!-- ocr图片识别 -->
        <dependency>
            <groupId>io.github.mymonstercat</groupId>
            <artifactId>rapidocr</artifactId>
            <version>0.0.7</version>
        </dependency>

        <dependency>
            <groupId>io.github.mymonstercat</groupId>
            <artifactId>rapidocr-onnx-platform</artifactId>
            <version>0.0.7</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.29</version> <!-- 最新稳定版 -->
        </dependency>
        <!-- Linux 需要配置 -->
        <dependency>
            <groupId>io.github.mymonstercat</groupId>
            <artifactId>rapidocr-onnx-linux-x86_64</artifactId>
            <version>1.2.2</version>
        </dependency>

//这里开始
public String rapidocrORC(MultipartFile multipartFile) {
        File reNameFile = null;
        String result = "";
        try {
            reNameFile  = imageCheck(multipartFile);//见Tesseract 部分

            InferenceEngine engine = InferenceEngine.getInstance(Model.ONNX_PPOCR_V3);
            if (reNameFile.getAbsolutePath().endsWith(".pdf")) {
                result = convertPdfToImage(engine, reNameFile, 300);
            } else {
                OcrResult ocrResult = engine.runOcr(reNameFile.getAbsolutePath());
                result = JSONObject.toJSONString(ocrResult);
            }

            System.out.println(result);
        } catch (Exception e) {
            e.printStackTrace();
        }  finally {
            if (reNameFile != null) {
                reNameFile.delete();
            }
        }
        return result;


    }

    //pdf 文字提取
    public  String convertPdfToImage(InferenceEngine engine, File pdfFile, int dpi) {
        try (PDDocument document = PDDocument.load(pdfFile)) {
            List<OcrResult> allWorld = new ArrayList<>();
            for (int page = 0; page < document.getNumberOfPages(); page++) {
                PDFRenderer renderer = new PDFRenderer(document);
                // 渲染指定页面为图像，dpi参数控制图像质量
                BufferedImage bf = renderer.renderImageWithDPI(page, dpi);
                String fileName = pdfFile.getAbsolutePath().replace(".pdf","_"+page+".png");
                File image = new File(fileName);
                try {
                    ImageIO.write(bf, "png", image);
                    OcrResult ocrResult = engine.runOcr(fileName);
                    allWorld.add(ocrResult);
                } catch (Exception e) {
                    throw new RuntimeException(e);
                } finally {
                    if (image != null) {
                        image.delete();
                    }
                }

            }
            return JSONObject.toJSONString(allWorld);
        } catch (Exception e) {
            e.printStackTrace();
            return null;
        }
    }