OCR

C_API.c

@@ -0,0 +1,37 @@
+#include <stdio.h>
+#include <leptonica/allheaders.h>
+#include <tesseract/capi.h>
+
+void die(const char *errstr) {
+	fputs(errstr, stderr);
+	exit(1);
+}
+
+int main(int argc, char *argv[]) {
+	TessBaseAPI *handle;
+	PIX *img;
+	char *text;
+
+	if((img = pixRead("russian-text.png")) == NULL)
+		die("Error reading image\n");
+
+	handle = TessBaseAPICreate();
+	if(TessBaseAPIInit3(handle, NULL, "rus") != 0)
+		die("Error initialising tesseract\n");
+
+	TessBaseAPISetImage2(handle, img);
+	if(TessBaseAPIRecognize(handle, NULL) != 0)
+		die("Error in Tesseract recognition\n");
+
+	if((text = TessBaseAPIGetUTF8Text(handle)) == NULL)
+		die("Error getting text\n");
+
+	fputs(text, stdout);
+
+	TessDeleteText(text);
+	TessBaseAPIEnd(handle);
+	TessBaseAPIDelete(handle);
+	pixDestroy(&img);
+
+	return 0;
+}

OCR.cpp

@@ -0,0 +1,28 @@
+#include <tesseract/baseapi.h>
+#include <leptonica/allheaders.h>
+
+int main()
+{
+    char *outText;
+
+    tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
+    // Initialize tesseract-ocr with English, without specifying tessdata path
+    if (api->Init(NULL, "rus")) {
+        fprintf(stderr, "Could not initialize tesseract.\n");
+        exit(1);
+    }
+
+    // Open input image with leptonica library
+    Pix *image = pixRead("a.jpg");
+    api->SetImage(image);
+    // Get OCR result
+    outText = api->GetUTF8Text();
+    printf("OCR output:\n%s", outText);
+
+    // Destroy used object and release memory
+    api->End();
+    delete [] outText;
+    pixDestroy(&image);
+
+    return 0;
+}