Java OCR tesseract 图像智能文字字符识别技术实例代码
程序员文章站
2023-12-13 10:30:10
接着上一篇ocr所说的,上一篇给大家介绍了tesseract 在命令行的简单用法,当然了要继承到我们的程序中,还是需要代码实现的,下面给大家分享下java实现的例子。...
接着上一篇ocr所说的,上一篇给大家介绍了tesseract 在命令行的简单用法,当然了要继承到我们的程序中,还是需要代码实现的,下面给大家分享下java实现的例子。
拿代码扫描上面的图片,然后输出结果。主要思想就是利用java调用系统任务。
下面是核心代码:
package com.zhy.test; 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; public class ocrhelper { private final string lang_option = "-l"; private final string eol = system.getproperty("line.separator"); /** * 文件位置我防止在,项目同一路径 */ private string tesspath = new file("tesseract").getabsolutepath(); /** * @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); // cmd.add("chi_sim"); cmd.add("eng"); 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: 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*", ""); } }
代码很简单,中间那部分processbuilder其实就类似runtime.getruntime().exec("tesseract.exe 1.jpg 1 -l chi_sim"),大家不习惯的可以使用runtime。
测试代码:
package com.zhy.test; import java.io.file; public class test { public static void main(string[] args) { try { file testdatadir = new file("testdata"); system.out.println(testdatadir.listfiles().length); int i = 0 ; for(file file :testdatadir.listfiles()) { i++ ; string recognizetext = new ocrhelper().recognizetext(file); system.out.print(recognizetext+"\t"); if( i % 5 == 0 ) { system.out.println(); } } } catch (exception e) { e.printstacktrace(); } } }
输出结果:
对比第一张图片,是不是很完美~哈哈 ,当然了如果你只需要实现验证码的读写,那么上面就足够了。下面继续普及图像处理的知识。
当然了,有时候图片被扭曲或者模糊的很厉害,很不容易识别,所以下面我给大家介绍一个去噪的辅助类,绝对碉堡了,先看下效果图。
来张特写:
一个类,不依赖任何jar,把图像中的干扰线消灭了,是不是很给力,然后再拿这样的图片去识别,会不会效果更好呢,嘿嘿,大家自己实验~
代码:
package com.zhy.test; import java.awt.color; import java.awt.image.bufferedimage; import java.io.file; import java.io.ioexception; import javax.imageio.imageio; public class clearimagehelper { public static void main(string[] args) throws ioexception { file testdatadir = new file("testdata"); final string destdir = testdatadir.getabsolutepath()+"/tmp"; for (file file : testdatadir.listfiles()) { cleanimage(file, destdir); } } /** * * @param sfile * 需要去噪的图像 * @param destdir * 去噪后的图像保存地址 * @throws ioexception */ public static void cleanimage(file sfile, string destdir) throws ioexception { file destf = new file(destdir); if (!destf.exists()) { destf.mkdirs(); } bufferedimage bufferedimage = imageio.read(sfile); int h = bufferedimage.getheight(); int w = bufferedimage.getwidth(); // 灰度化 int[][] gray = new int[w][h]; for (int x = 0; x < w; x++) { for (int y = 0; y < h; y++) { int argb = bufferedimage.getrgb(x, y); // 图像加亮(调整亮度识别率非常高) int r = (int) (((argb >> 16) & 0xff) * 1.1 + 30); int g = (int) (((argb >> 8) & 0xff) * 1.1 + 30); int b = (int) (((argb >> 0) & 0xff) * 1.1 + 30); if (r >= 255) { r = 255; } if (g >= 255) { g = 255; } if (b >= 255) { b = 255; } gray[x][y] = (int) math .pow((math.pow(r, 2.2) * 0.2973 + math.pow(g, 2.2) * 0.6274 + math.pow(b, 2.2) * 0.0753), 1 / 2.2); } } // 二值化 int threshold = ostu(gray, w, h); bufferedimage binarybufferedimage = new bufferedimage(w, h, bufferedimage.type_byte_binary); for (int x = 0; x < w; x++) { for (int y = 0; y < h; y++) { if (gray[x][y] > threshold) { gray[x][y] |= 0x00ffff; } else { gray[x][y] &= 0xff0000; } binarybufferedimage.setrgb(x, y, gray[x][y]); } } // 矩阵打印 for (int y = 0; y < h; y++) { for (int x = 0; x < w; x++) { if (isblack(binarybufferedimage.getrgb(x, y))) { system.out.print("*"); } else { system.out.print(" "); } } system.out.println(); } imageio.write(binarybufferedimage, "jpg", new file(destdir, sfile .getname())); } public static boolean isblack(int colorint) { color color = new color(colorint); if (color.getred() + color.getgreen() + color.getblue() <= 300) { return true; } return false; } public static boolean iswhite(int colorint) { color color = new color(colorint); if (color.getred() + color.getgreen() + color.getblue() > 300) { return true; } return false; } public static int isblackorwhite(int colorint) { if (getcolorbright(colorint) < 30 || getcolorbright(colorint) > 730) { return 1; } return 0; } public static int getcolorbright(int colorint) { color color = new color(colorint); return color.getred() + color.getgreen() + color.getblue(); } public static int ostu(int[][] gray, int w, int h) { int[] histdata = new int[w * h]; // calculate histogram for (int x = 0; x < w; x++) { for (int y = 0; y < h; y++) { int red = 0xff & gray[x][y]; histdata[red]++; } } // total number of pixels int total = w * h; float sum = 0; for (int t = 0; t < 256; t++) sum += t * histdata[t]; float sumb = 0; int wb = 0; int wf = 0; float varmax = 0; int threshold = 0; for (int t = 0; t < 256; t++) { wb += histdata[t]; // weight background if (wb == 0) continue; wf = total - wb; // weight foreground if (wf == 0) break; sumb += (float) (t * histdata[t]); float mb = sumb / wb; // mean background float mf = (sum - sumb) / wf; // mean foreground // calculate between class variance float varbetween = (float) wb * (float) wf * (mb - mf) * (mb - mf); // check if new maximum found if (varbetween > varmax) { varmax = varbetween; threshold = t; } } return threshold; } }
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。