tess4j3.2.1 + jdk1.8部署

按照官网文档和国内文章各种实验都不成功,最终成功后把步骤分享出来,以免大家被坑了!

 

1. maven添加

 	<!-- https://mvnrepository.com/artifact/net.sourceforge.tess4j/tess4j -->
	<dependency>
	    <groupId>net.sourceforge.tess4j</groupId>
	    <artifactId>tess4j</artifactId>
	    <version>3.2.1</version>
	</dependency>

 

2. 测试代码

public class TesseractExample {
	 public static void main(String[] args) throws Exception {
	        // File imageFile = new File("C:\\wangl\\eurotext.tif");
		InputStream is = downLoadFromUrl("https://passport.baidu.com//cgi-bin//genimage?njG8b06f54d9425e2bf023b14d95b01078933b5de06810514de");
		BufferedImage bi = ImageIO.read(is);
	        ITesseract instance = new Tesseract();  // JNA Interface Mapping
                //这句非常重要
                instance.setDatapath("C:\\wangl\\soft\\tess4j\\tessdata");  
	        try {
	            String result = instance.doOCR(bi);
	            System.out.println(result);
	        } catch (TesseractException e) {
	            System.err.println(e.getMessage());
	        }
	        if(is != null){
	        	is.close();
	        }
	 }
	 
	 public static InputStream downLoadFromUrl(String urlStr) throws IOException{
	        URL url = new URL(urlStr);  
	        HttpURLConnection conn = (HttpURLConnection)url.openConnection();  
	        //设置超时间为3秒
	        conn.setConnectTimeout(3*1000);
	        //防止屏蔽程序抓取而返回403错误
	        conn.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");
	        //得到输入流
	        InputStream inputStream = conn.getInputStream();  
	        return inputStream;
	}
}

 

3. 总结:根本不需要设置testdata,根本不需要拷贝dll,根本不需要设置环境变量(testdata,dll已经包含在jar中)