从pdf文件中提取文本和包含文本的图像

Question

我正在从pdf文件中提取文本，该文件具有行文本和一些具有文本的图像报告。我应该使用哪种OCR技术来提取行文本和图像中的文本。我已经尝试了一些OCR技术，要么是做OCR，要么是从pdf中读取文本。我需要一次完成这两个任务。谢谢。

Answer 1

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.BodyContentHandler;
import org.xml.sax.SAXException;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

public class ContentsExtraction {
    private static void extractFromFile(final Parser parser, final String fileName)throws IOException,SAXException,TikaException {
        long start =System.currentTimeMillis();
        BodyContentHandler handler=new BodyContentHandler(10000000);
        Metadata metaData=new Metadata();
        FileInputStream content=new FileInputStream(fileName);
        parser.parse(content,handler,metaData,new ParseContext());
        System.out.println("\n\n File content : "+handler.toString());
    }

    private static void extract(final String fileName,final String writePath)throws IOException{
        File image=new File(fileName);
        Tesseract tessInst=new Tesseract();
        try{
            tessInst.setDatapath("./tessdata");
            String result = tessInst.doOCR(image);
            System.out.println(result);

        }catch (TesseractException e){
            System.err.println(e.getMessage());
        }
    }
    public static void main(String[] args)throws IOException,SAXException,TikaException {
        String path="input.pdf";
        String writePathImage=null;
        String[] ext=path.split("\\.");
        Parser parser=new AutoDetectParser();
        if(ext[1].equalsIgnoreCase("png")||ext[1].equalsIgnoreCase("jpg")||ext[1].equalsIgnoreCase("pdf"))
        {
            writePathImage="output.txt";
            extractFromFile(parser,path);
            extractPdfImage(path,writePathImage);


        }else
        {
            extractFromFile(parser,path);

        }
        System.out.println("Processing Completed");
    }

}