Merge pull request #8831 from SmartyAnsh/BAEL-3874-OCR-with-Tesseract

BAEL-3874-ocr_with_tesseract

image-processing/pom.xml

@@ -50,12 +50,24 @@
             <artifactId>imageio-bmp</artifactId>
             <version>${imageio.version}</version>
         </dependency>
+        <dependency>
+            <groupId>net.sourceforge.tess4j</groupId>
+            <artifactId>tess4j</artifactId>
+            <version>${tess4j.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.bytedeco</groupId>
+            <artifactId>tesseract-platform</artifactId>
+            <version>${tesseract-platform.version}</version>
+        </dependency>
     </dependencies>
-
+    
     <properties>
         <core-image.version>1.3.5</core-image.version>
         <ij.version>1.51h</ij.version>
         <imageio.version>3.3.2</imageio.version>
+        <tess4j.version>4.5.1</tess4j.version>
+        <tesseract-platform.version>4.1.0-1.5.2</tesseract-platform.version>
     </properties>
 
 </project>

image-processing/src/main/java/com/baeldung/tesseract/Tess4JExample.java

@@ -0,0 +1,28 @@
+package com.baeldung.tesseract;
+
+import java.awt.Rectangle;
+import java.io.File;
+
+import net.sourceforge.tess4j.Tesseract;
+import net.sourceforge.tess4j.TesseractException;
+
+public class Tess4JExample {
+
+    public static void main(String[] args) {
+        String result = null;
+        try {
+            File image = new File("src/main/resources/images/baeldung.png");
+            Tesseract tesseract = new Tesseract();
+            tesseract.setLanguage("spa");
+            tesseract.setPageSegMode(1);
+            tesseract.setOcrEngineMode(1);
+            tesseract.setHocr(true);
+            tesseract.setDatapath("src/main/resources/tessdata");
+            result = tesseract.doOCR(image, new Rectangle(1200, 200));
+        } catch (TesseractException e) {
+            e.printStackTrace();
+        }
+        System.out.println(result);
+    }
+
+}

image-processing/src/main/java/com/baeldung/tesseract/TesseractPlatformExample.java

@@ -0,0 +1,26 @@
+package com.baeldung.tesseract;
+
+import org.bytedeco.javacpp.BytePointer;
+import org.bytedeco.leptonica.PIX;
+import org.bytedeco.tesseract.TessBaseAPI;
+
+public class TesseractPlatformExample {
+
+    @SuppressWarnings("resource")
+    public static void main(String[] args) {
+        try {
+            TessBaseAPI tessApi = new TessBaseAPI();
+            tessApi.Init("src/main/resources/tessdata", "eng", 3);
+            tessApi.SetPageSegMode(1);
+            PIX image = org.bytedeco.leptonica.global.lept.pixRead("src/main/resources/images/baeldung.png");
+            tessApi.SetImage(image);
+
+            BytePointer outText = tessApi.GetUTF8Text();
+            System.out.println(outText.getString());
+            tessApi.End();
+        } catch(Exception e) {
+           e.printStackTrace();
+        }
+    }
+
+}

image-processing/src/main/resources/images/output.txt

@@ -0,0 +1,9 @@
+Der ,.schnelle” braune Fuchs springt
+iiber den faulen Hund. Le renard brun
+«rapide» saute par-dessus le chien
+paresseux. La volpe marrone rapida
+salta sopra il cane pigro. El zorro
+marron rapido salta sobre el perro
+perezoso. A raposa marrom rapida
+salta sobre 0 cao preguicoso.
+