diff --git a/mallinkOcr/pom.xml b/mallinkOcr/pom.xml index b43f32111..110fefed4 100644 --- a/mallinkOcr/pom.xml +++ b/mallinkOcr/pom.xml @@ -15,17 +15,25 @@ net.java.dev.jna jna - 4.1.0 + 5.3.1 net.sourceforge.tess4j tess4j - 3.4.0 + 4.4.0 - com.sun.jna - jna - + commons-io + commons-io + + + commons-logging + commons-logging + + + jna + net.java.dev.jna + diff --git a/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java b/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java index 68ee0cd27..522ca71f2 100644 --- a/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java +++ b/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4j.java @@ -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; } diff --git a/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java b/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java index d9741751f..953cef31d 100644 --- a/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java +++ b/mallinkOcr/src/main/java/com/iformall/ocr/FormallTess4jTrain.java @@ -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"); diff --git a/mallinkOcr/src/main/resources/Read.txt b/mallinkOcr/src/main/resources/Read.txt index a99b2cd8b..9a470fa25 100644 --- a/mallinkOcr/src/main/resources/Read.txt +++ b/mallinkOcr/src/main/resources/Read.txt @@ -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 \ No newline at end of file +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 diff --git a/mallinkOcr/src/main/resources/tessdata/test1.traineddata b/mallinkOcr/src/main/resources/tessdata/test1.traineddata index 26a156faf..a07542f43 100644 Binary files a/mallinkOcr/src/main/resources/tessdata/test1.traineddata and b/mallinkOcr/src/main/resources/tessdata/test1.traineddata differ