首先在Tesseract-OCR官网下载Tesseract-OCR 3.02,以及中文数据包chi_sim.traineddata(简体)
接下来就是新建一个JAVA EE项目,把Tesseract-OCR放在项目WebRoot下。
下面是主要代码:
接受客户端上传过来的图片,使用Tesseract-OCR识别后返回至前台。
package servlet;
import java.io.IOException;
import javax.servlet.ServletConfig;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import util.FileUtil;
import util.OCRUtil;
import com.jspsmart.upload.File;
import com.jspsmart.upload.SmartUpload;
import com.jspsmart.upload.SmartUploadException;
public class OCRServlet extends HttpServlet {
public void doPost(HttpServletRequest request, HttpServletResponse response)
throws ServletException, IOException {
response.setCharacterEncoding("g