tess4j3.2.1识别中英文

tess4j3.2.1识别中英文1 测试代码 public class TesseractExa public static void main String args throws Exception 1 本地 File imageFile new File C wangl eurotext tif InputStream is new

1. 测试代码

public class TesseractExample {
public static void main(String[] args) throws Exception {
//1.本地
//File imageFile = new File("C:\\wangl\\eurotext.tif");
//InputStream is = new FileInputStream(imageFile);;
//2.url http
//InputStream is = downLoadFromUrl("http://s1.sinaimg.cn/mw690/003bsgbmgy6R6ekxkl2e0");
//3.url https
InputStream is = downLoadFromUrl("https://login.10333.com/dotoyo//captchacode");

BufferedImage bi = ImageIO.read(is);
ITesseract instance = new Tesseract(); // JNA Interface Mapping
//设置datapath
instance.setDatapath("C:\\wangl\\soft\\tess4j\\tessdata");
//设置语言包
instance.setLanguage("eng+chi_sim");
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 Exception{
//指定证书文件
System.setProperty("javax.net.ssl.trustStore","C:\\wangl\\soft\\Java\\jdk1.7.0_79\\jre\\lib\\security\\jssecacerts");
URL url = new URL(urlStr);
HttpURLConnection conn = (HttpURLConnection)url.openConnection();
//信任所有的https证书
trustAllHttpsCertificates();
HttpsURLConnection.setDefaultHostnameVerifier(hv);
//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;
}

public static HostnameVerifier hv = new HostnameVerifier() {
public boolean verify(String urlHostName, SSLSession session) {
System.out.println("Warning: URL Host: " + urlHostName + " vs. "
+ session.getPeerHost());
return true;
}
};

private static void trustAllHttpsCertificates() throws Exception {
javax.net.ssl.TrustManager[] trustAllCerts = new javax.net.ssl.TrustManager[1];
javax.net.ssl.TrustManager tm = new miTM();
trustAllCerts[0] = tm;
javax.net.ssl.SSLContext sc = javax.net.ssl.SSLContext
.getInstance("SSL");
sc.init(null, trustAllCerts, null);
javax.net.ssl.HttpsURLConnection.setDefaultSSLSocketFactory(sc
.getSocketFactory());
}

static class miTM implements javax.net.ssl.TrustManager,
javax.net.ssl.X509TrustManager {
public java.security.cert.X509Certificate[] getAcceptedIssuers() {
return null;
}

public boolean isServerTrusted(
java.security.cert.X509Certificate[] certs) {
return true;
}

public boolean isClientTrusted(
java.security.cert.X509Certificate[] certs) {
return true;
}

public void checkServerTrusted(
java.security.cert.X509Certificate[] certs, String authType)
throws java.security.cert.CertificateException {
return;
}

public void checkClientTrusted(
java.security.cert.X509Certificate[] certs, String authType)
throws java.security.cert.CertificateException {
return;
}
}
}

2. 设置datapath,设置语言包中英文

3. 注意如果https证书不被信任,那么需要导出证书(填写host port 路径,运行InstallCert

导出证书)

public class InstallCert {

public static void main(String[] args) throws Exception {
//
// int port;
// char[] passphrase;
// if ((args.length == 1) || (args.length == 2)) {
// String[] c = args[0].split(":");
// host = c[0];
// port = (c.length == 1) ? 443 : Integer.parseInt(c[1]);
// String p = (args.length == 1) ? "changeit" : args[1];
// passphrase = p.toCharArray();
// } else {
// System.out
// .println("Usage: java InstallCert [:port] [passphrase]");
// return;
// }
String host = "14.17.69.168";
int port = 443;
String p = "changeit" ;
char[] passphrase = p.toCharArray();


File file = new File("jssecacerts");
if (file.isFile() == false) {
char SEP = File.separatorChar;
File dir = new File(System.getProperty("java.home") + SEP + "lib"
+ SEP + "security");
file = new File(dir, "jssecacerts");
if (file.isFile() == false) {
file = new File(dir, "cacerts");
}
}
System.out.println("Loading KeyStore " + file + "...");
InputStream in = new FileInputStream(file);
KeyStore ks = KeyStore.getInstance(KeyStore.getDefaultType());
ks.load(in, passphrase);
in.close();

SSLContext context = SSLContext.getInstance("TLS");
TrustManagerFactory tmf = TrustManagerFactory
.getInstance(TrustManagerFactory.getDefaultAlgorithm());
tmf.init(ks);
X509TrustManager defaultTrustManager = (X509TrustManager) tmf
.getTrustManagers()[0];
SavingTrustManager tm = new SavingTrustManager(defaultTrustManager);
context.init(null, new TrustManager[] { tm }, null);
SSLSocketFactory factory = context.getSocketFactory();

System.out
.println("Opening connection to " + host + ":" + port + "...");
SSLSocket socket = (SSLSocket) factory.createSocket(host, port);
socket.setSoTimeout(10000);
try {
System.out.println("Starting SSL handshake...");
socket.startHandshake();
socket.close();
System.out.println();
System.out.println("No errors, certificate is already trusted");
} catch (SSLException e) {
System.out.println();
e.printStackTrace(System.out);
}

X509Certificate[] chain = tm.chain;
if (chain == null) {
System.out.println("Could not obtain server certificate chain");
return;
}

System.out.println();
System.out.println("Server sent " + chain.length + " certificate(s):");
System.out.println();
MessageDigest sha1 = MessageDigest.getInstance("SHA1");
MessageDigest md5 = MessageDigest.getInstance("MD5");
for (int i = 0; i < chain.length; i++) {
X509Certificate cert = chain[i];
System.out.println(" " + (i + 1) + " Subject "
+ cert.getSubjectDN());
System.out.println(" Issuer " + cert.getIssuerDN());
sha1.update(cert.getEncoded());
System.out.println(" sha1 " + toHexString(sha1.digest()));
md5.update(cert.getEncoded());
System.out.println(" md5 " + toHexString(md5.digest()));
System.out.println();
}

System.out
.println("Enter certificate to add to trusted keystore or 'q' to quit: [1]");
String line = "1";
int k;
try {
k = (line.length() == 0) ? 0 : Integer.parseInt(line) - 1;
} catch (NumberFormatException e) {
System.out.println("KeyStore not changed");
return;
}

X509Certificate cert = chain[k];
String alias = host + "-" + (k + 1);
ks.setCertificateEntry(alias, cert);

OutputStream out = new FileOutputStream("c://wangl//https//jssecacerts");
ks.store(out, passphrase);
out.close();

System.out.println();
System.out.println(cert);
System.out.println();
System.out
.println("Added certificate to keystore 'jssecacerts' using alias '"
+ alias + "'");
}

private static final char[] HEXDIGITS = "0123456789abcdef".toCharArray();

private static String toHexString(byte[] bytes) {
StringBuilder sb = new StringBuilder(bytes.length * 3);
for (int b : bytes) {
b &= 0xff;
sb.append(HEXDIGITS[b >> 4]);
sb.append(HEXDIGITS[b & 15]);
sb.append(' ');
}
return sb.toString();
}

private static class SavingTrustManager implements X509TrustManager {

private final X509TrustManager tm;
private X509Certificate[] chain;

SavingTrustManager(X509TrustManager tm) {
this.tm = tm;
}

public X509Certificate[] getAcceptedIssuers() {
throw new UnsupportedOperationException();
}

public void checkClientTrusted(X509Certificate[] chain, String authType)
throws CertificateException {
throw new UnsupportedOperationException();
}

public void checkServerTrusted(X509Certificate[] chain, String authType)
throws CertificateException {
this.chain = chain;
tm.checkServerTrusted(chain, authType);
}
}

}

4.https需要在代码1中指定证书文件.

5.图片信息为: 汉字验证码–demo分享

最终结果显示: 汉字验证码汴demo分享

OK,识别率还可以,但存在提升的空间!

6.如果追求高识别率,可以考虑付费的国外泰比和国内的汉王.

编程小号
上一篇 2025-01-25 18:40
下一篇 2025-03-13 15:11

相关推荐

版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 举报,一经查实,本站将立刻删除。
如需转载请保留出处:https://bianchenghao.cn/hz/117778.html