Przeglądaj źródła

fix ocr

release_toaliyun_real
zhengfangyuan 5 lat temu
rodzic
commit
d5e66030a2
5 zmienionych plików z 25 dodań i 7 usunięć
  1. +13
    -5
      mallinkOcr/pom.xml
  2. +1
    -1
      mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java
  3. +6
    -0
      mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java
  4. +5
    -1
      mallinkOcr/src/main/resources/Read.txt
  5. BIN
      mallinkOcr/src/main/resources/tessdata/test1.traineddata

+ 13
- 5
mallinkOcr/pom.xml Wyświetl plik

@@ -15,17 +15,25 @@
<dependency>
<groupId>net.java.dev.jna</groupId>
<artifactId>jna</artifactId>
<version>4.1.0</version>
<version>5.3.1</version>
</dependency>
<dependency>
<groupId>net.sourceforge.tess4j</groupId>
<artifactId>tess4j</artifactId>
<version>3.4.0</version>
<version>4.4.0</version>
<exclusions>
<exclusion>
<groupId>com.sun.jna</groupId>
<artifactId>jna</artifactId>
</exclusion>
<artifactId>commons-io</artifactId>
<groupId>commons-io</groupId>
</exclusion>
<exclusion>
<artifactId>commons-logging</artifactId>
<groupId>commons-logging</groupId>
</exclusion>
<exclusion>
<artifactId>jna</artifactId>
<groupId>net.java.dev.jna</groupId>
</exclusion>
</exclusions>
</dependency>


+ 1
- 1
mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java Wyświetl plik

@@ -138,7 +138,7 @@ public class FormallTess4j {
logger.info("doOCR on a jpg image");
//set language
instance.setDatapath(testResourcesLanguagePath);
instance.setLanguage("chi_sim");
instance.setLanguage("test1");
String result = instance.doOCR(imageFile);
return result;
}


+ 6
- 0
mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java Wyświetl plik

@@ -186,25 +186,31 @@ public class FormallTess4jTrain {
/**第一步,用jTessBoxEditor --> Tools --> Merge 多选图片,保存为tif格式*/
System.out.println("第一步,用jTessBoxEditor --> Tools --> Merge 多选图片,保存为tif格式 . 命名格式:lang.fontName.exp0.tif");
System.out.println("》》》》》》》》》");
/**第二部,用tif生成box*/
System.out.println("第二步,用tif生成box");
createBoxFile("mylang.test1.exp0.tif", "mylang", "test1");
System.out.println("》》》》》》》》》");
/**第三步,用jTessBoxEditor 打开.box文件进行矫正。*/
System.out.println("第三步,用jTessBoxEditor 打开.box文件进行矫");
System.out.println("》》》》》》》》》");
/**第四步,新建font_properties,内容 [fontName] 0 0 0 0 0*/
System.out.println("第四步:新建font_properties,内容 [fontName] 0 0 0 0 0");
createFontPorperties("test1", 0, 0, 0, 0, 0);
System.out.println("》》》》》》》》》");
/** 第五步:执行以下命令*/
System.out.println("第五步:执行以下命令");
createTrainFiles("mylang", "test1");
System.out.println("》》》》》》》》》");
/**第六步,执行完成后生成以下几个文件加前缀*/
System.out.println("第六步,执行完成后生成以下几个文件加前缀");
renameTrainFiles("test1");
System.out.println("》》》》》》》》》");
/**第七步:合并5个文件*/
System.out.println("第七步:合并5个文件");


+ 5
- 1
mallinkOcr/src/main/resources/Read.txt Wyświetl plik

@@ -7,4 +7,8 @@ https://digi.bib.uni-mannheim.de/tesseract/

https://blog.csdn.net/qq_40147863/article/details/82290015

https://blog.csdn.net/boonya/article/details/81325997
https://blog.csdn.net/boonya/article/details/81325997


合并字库 https://www.cnblogs.com/c2soft/articles/10415236.html
完整教程 https://www.cnblogs.com/wpcnblog/p/12850590.html

BIN
mallinkOcr/src/main/resources/tessdata/test1.traineddata Wyświetl plik


Ładowanie…
Anuluj
Zapisz