如何使用 tesseract、宽度和背景变量读取验证码

Question

这个验证码可以读吗？我该如何阅读？

---编辑代码：

public static String imgToTxt(String imgFileName) {
  try {
   Process pr = (new ProcessBuilder()).redirectOutput(new File("/tmp/tesseract.log"))
     .redirectError(new File("/tmp/tesseract-error.log"))
     .command("/opt/local/bin/tesseract", imgFileName + ".png", imgFileName).start();
   pr.waitFor();
   Reader input = new FileReader(new File(imgFileName + ".txt"));
   StringWriter output = new StringWriter();
   IOUtils.copy(input, output);
   return output.toString();
  } catch (Exception e) {
   e.printStackTrace();
  }
  return null;
 }

Answer 1

为了将来的帮助。我不得不使用 imagemagick 工具处理图像。去除背景并改进字体文本。

public static String imgToTxt(String imgFileName) {
  try {
   ProcessBuilder pb = new ProcessBuilder("convert", imgFileName + ".png", "-fuzz",       "15%", "-fill", "black",
     "-opaque", "rgb(16,128,176)", "-fuzz", "40%", "-fill", "white", "+opaque", "black",
     imgFileName + ".png");
   pb.redirectErrorStream(true);
   Process pr = pb.start();
   BufferedReader br = new BufferedReader(new InputStreamReader(pr.getInputStream()));
   String line = null;
   while ((line = br.readLine()) != null) {
    System.out.println(line);
   }
   pr.waitFor();

   pr = (new ProcessBuilder()).redirectOutput(new File("/tmp/tesseract.log"))
     .redirectError(new File("/tmp/tesseract-error.log"))
     .command("/opt/local/bin/tesseract", imgFileName + ".png", imgFileName).start();
   pr.waitFor();
   Reader input = new FileReader(new File(imgFileName + ".txt"));
   StringWriter output = new StringWriter();
   IOUtils.copy(input, output);
   return output.toString();
  } catch (Exception e) {
   e.printStackTrace();
  }
  return null;
 }

如何使用 tesseract、宽度和背景变量读取验证码

How to read captcha with tesseract, width and background variables

captcha

tesseract