Tesseract Ocr 引擎识别图形验证码

package com.shanhy.unifiedintegral.common.ocr;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;

import org.jdesktop.swingx.util.OS;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Component;

/**
 * 图形验证码识别
 *
 * @author   单红宇(365384722)
 * @myblog  http://blog.csdn.net/catoop/
 * @create    2016年9月2日
 */
@Component
public class OCRHelper {
	
	private final String LANG_OPTION = "-l";
	private final String EOL = System.getProperty("line.separator");
	/**
	 * tesseract安装目录
	 */
	@Value("${tesseractDirPath:C://Program Files (x86)//Tesseract-OCR}")//默认值C://Program Files (x86)//Tesseract-OCR
	private String tessPath;

	/**
	 * @param imageFile
	 *            传入的图像文件
	 * @param imageFormat
	 *            传入的图像格式
	 * @return 识别后的字符串
	 */
	public String recognizeText(File imageFile) throws Exception {
		/**
		 * 设置输出文件的保存的文件目录
		 */
		File outputFile = new File(imageFile.getParentFile(), "output");

		StringBuffer strB = new StringBuffer();
		List<String> cmd = new ArrayList<String>();
		if (OS.isWindowsXP()) {
			cmd.add(tessPath + "\\tesseract");
		} else if (OS.isLinux()) {
			cmd.add("tesseract");
		} else {
			cmd.add(tessPath + "\\tesseract");
		}
		cmd.add("");
		cmd.add(outputFile.getName());
		cmd.add(LANG_OPTION);
		// 设置语言参数
		// cmd.add("chi_sim");// 中文简体（需要额外安装）
		cmd.add("eng");// 英文（安装默认自带）

		ProcessBuilder pb = new ProcessBuilder();
		/**
		 * Sets this process builder's working directory.
		 */
		pb.directory(imageFile.getParentFile());
		cmd.set(1, imageFile.getName());
		pb.command(cmd);
		pb.redirectErrorStream(true);
		Process process = pb.start();
		// tesseract.exe 1.jpg 1 -l chi_sim
		// Runtime.getRuntime().exec("tesseract.exe 1.jpg 1 -l chi_sim");
		/**
		 * the exit value of the process. By convention, 0 indicates normal
		 * termination.
		 */
		// System.out.println(cmd.toString());
		int w = process.waitFor();
		if (w == 0)// 0代表正常退出
		{
			BufferedReader in = new BufferedReader(
					new InputStreamReader(new FileInputStream(outputFile.getAbsolutePath() + ".txt"), "UTF-8"));
			String str;

			while ((str = in.readLine()) != null) {
				strB.append(str).append(EOL);
			}
			in.close();
		} else {
			String msg;
			switch (w) {
			case 1:// 大部分是权限问题，当前运行的java执行权限不够
				msg = "Errors accessing files. There may be spaces in your image's filename.";
				break;
			case 29:
				msg = "Cannot recognize the image or its selected region.";
				break;
			case 31:
				msg = "Unsupported image format.";
				break;
			default:
				msg = "Errors occurred.";
			}
			throw new RuntimeException(msg);
		}
		new File(outputFile.getAbsolutePath() + ".txt").delete();
		return strB.toString().replaceAll("\\s*", "");
	}
	
	public void setTessPath(String path){
		this.tessPath = path;
	}

//	public static void main(String[] args) {
//		try {
//			OCRHelper ocr = new OCRHelper();
//			ocr.setTessPath("D://Tesseract-OCR");
//			System.out.println(ocr.recognizeText(new File("G://vcode.jpg")));
//		} catch (Exception e) {
//			e.printStackTrace();
//		}
//	}
}