* Add GetComponentImagesExample for Tesseract (pull #673)

bytedeco · Jan 19, 2019 · 577fe8c · 577fe8c
1 parent fb79284
commit 577fe8c
Show file tree

Hide file tree

Showing 3 changed files with 83 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,5 @@
 
+ * Add `GetComponentImagesExample` for Tesseract ([pull #673](https://github.com/bytedeco/javacpp-presets/pull/673))
  * Add presets for nGraph 0.11.1 ([pull #642](https://github.com/bytedeco/javacpp-presets/pull/642))
  * Upgrade presets for ARPACK-NG 3.7.0
  * Build OpenCV without UI when environment variable `HEADLESS=yes` ([pull #667](https://github.com/bytedeco/javacpp-presets/pull/667))

diff --git a/tesseract/samples/pom.xml b/tesseract/samples/pom.xml
@@ -0,0 +1,24 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>org.bytedeco.javacpp-presets</groupId>
+    <artifactId>tesseract-samples</artifactId>
+    <version>4.0.0-1.4.4</version>
+    <name>JavaCPP Presets Samples for Tesseract</name>
+
+    <properties>
+        <maven.compiler.target>1.7</maven.compiler.target>
+        <maven.compiler.source>1.7</maven.compiler.source>
+    </properties>
+
+    <dependencies>
+        <dependency>
+            <groupId>${project.groupId}</groupId>
+            <artifactId>tesseract-platform</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+    </dependencies>
+
+</project>
diff --git a/...mples/src/main/java/org/bytedeco/javacpp/samples/tesseract/GetComponentImagesExample.java b/...mples/src/main/java/org/bytedeco/javacpp/samples/tesseract/GetComponentImagesExample.java
@@ -0,0 +1,58 @@
+
+package org.bytedeco.javacpp.samples.tesseract;
+
+import java.io.File;
+import java.net.URL;
+import org.bytedeco.javacpp.*;
+import static org.bytedeco.javacpp.lept.*;
+import static org.bytedeco.javacpp.tesseract.*;
+
+/**
+ * To run this program, you need to configure:
+ * <ul>
+ *     <li>An environment variable pointing to the dictionaries installed on the system
+ *     TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00</li>
+ * </ul>
+ *
+ * @author Arnaud Jeansen
+ */
+public class GetComponentImagesExample {
+    public static void main(String[] args) throws Exception {
+        BytePointer outText;
+
+        TessBaseAPI api = new TessBaseAPI();
+        // Initialize tesseract-ocr with English, intializing tessdata path with the standard ENV variable
+        if (api.Init(System.getenv("TESSDATA_PREFIX") + "/tessdata", "eng") != 0) {
+            System.err.println("Could not initialize tesseract.");
+            System.exit(1);
+        }
+
+        // Open input image with leptonica library
+        URL url = new URL("https://upload.wikimedia.org/wikipedia/commons/thumb/7/74/Computer_modern_sample.svg/1920px-Computer_modern_sample.svg.png");
+        File file = Loader.cacheResource(url);
+        PIX image = pixRead(file.getAbsolutePath());
+        api.SetImage(image);
+
+        // Lookup all component images
+        int[] blockIds = {};
+        BOXA boxes = api.GetComponentImages(RIL_TEXTLINE, true, null, blockIds);
+
+        for (int i = 0; i < boxes.n(); i++) {
+            // For each image box, OCR within its area
+            BOX box = boxes.box(i);
+            api.SetRectangle(box.x(), box.y(), box.w(), box.h());
+            outText = api.GetUTF8Text();
+            String ocrResult = outText.getString();
+            int conf = api.MeanTextConf();
+
+            String boxInformation = String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d, confidence: %d, text: %s", i, box.x(), box.y(), box.w(), box.h(), conf, ocrResult);
+            System.out.println(boxInformation);
+
+            outText.deallocate();
+        }
+
+        // Destroy used object and release memory
+        api.End();
+        pixDestroy(image);
+    }
+}