0%

java+Tesseract实现ocr图片文字识别

发表于 分类于

文章字数：69,阅读全文大约需要1分钟

语言包下载

依赖

1
2
3
4
5
<dependency>
    <groupId>org.bytedeco</groupId>
    <artifactId>tesseract-platform</artifactId>
    <version>4.1.1-1.5.5</version>
</dependency>

代码

  • 只测试了简体中文chi_sim和英文eng
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
package com.colin.tool.img;

import org.bytedeco.javacpp.BytePointer;
import org.bytedeco.leptonica.PIX;
import org.bytedeco.leptonica.global.lept;
import org.bytedeco.tesseract.TessBaseAPI;

/**
 * @author colin.cheng
 * @date 2022-01-17
 * @since 1.0.0
 */
public class ImageUtil {

    public static String ocr(String imagePath, OcrLanguage language) {
        TessBaseAPI api=new TessBaseAPI();
        if (api.Init(language.getPath(), language.getLangName()) != 0) {
            api.End();
            return "";
        }
        PIX image = lept.pixRead(imagePath);
        if (image == null) {
            return "";
        }
        api.SetImage(image);
        BytePointer outText=api.GetUTF8Text();
        String result=outText.getString();
        api.End();
        outText.deallocate();
        lept.pixDestroy(image);
        return result;
    }

    public static void main(String[] args) {
        String text = ocr("F:\\test\\img\\0.jpg", OcrLanguage.ZH_CN);
        System.out.println(text);
    }

    public enum OcrLanguage {
        /** 简体中文 */
        ZH_CN("chi_sim", "F:\\test\\img\\traineddata"),
        /** 英文 */
        EN("eng", "F:\\test\\img\\traineddata");

        /** 文件名 */
        private String langName;
        /** 所在文件夹 */
        private String path;

        OcrLanguage(String langName, String path) {
            this.langName = langName;
            this.path = path;
        }

        public String getLangName() {
            return langName;
        }

        public String getPath() {
            return path;
        }
    }
}