/**
* Test of TessBaseAPIGetUTF8Text method, of class TessAPI1.
*
* @throws java.lang.Exception
*/
@Test
public void testTessBaseAPIGetUTF8Text_Pix() throws Exception {
logger.info("TessBaseAPIGetUTF8Text_Pix");
String expResult = expOCRResult;
File tiff = new File(this.testResourcesDataPath, "eurotext.tif");
Leptonica leptInstance = Leptonica.INSTANCE;
Pix pix = leptInstance.pixRead(tiff.getPath());
TessAPI1.TessBaseAPIInit3(handle, datapath, language);
TessAPI1.TessBaseAPISetImage2(handle, pix);
Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle);
String result = utf8Text.getString(0);
TessAPI1.TessDeleteText(utf8Text);
logger.info(result);
// release Pix resource
PointerByReference pRef = new PointerByReference();
pRef.setValue(pix.getPointer());
leptInstance.pixDestroy(pRef);
assertEquals(expResult, result.substring(0, expResult.length()));
}
/**
* Test of TessBaseAPIGetComponentImages method, of class TessAPI1.
*
* @throws java.lang.Exception
*/
@Test
public void testTessBaseAPIGetComponentImages() throws Exception {
logger.info("TessBaseAPIGetComponentImages");
File image = new File(this.testResourcesDataPath, "eurotext.png");
int expResult = 12; // number of lines in the test image
Pix pix = Leptonica1.pixRead(image.getPath());
TessAPI1.TessBaseAPIInit3(handle, datapath, language);
TessAPI1.TessBaseAPISetImage2(handle, pix);
PointerByReference pixa = null;
PointerByReference blockids = null;
Boxa boxes =
TessAPI1.TessBaseAPIGetComponentImages(
handle, TessPageIteratorLevel.RIL_TEXTLINE, TRUE, pixa, blockids);
// boxes = TessAPI1.TessBaseAPIGetRegions(handle, pixa); // equivalent to
// TessPageIteratorLevel.RIL_BLOCK
int boxCount = Leptonica1.boxaGetCount(boxes);
for (int i = 0; i < boxCount; i++) {
Box box = Leptonica1.boxaGetBox(boxes, i, L_CLONE);
if (box == null) {
continue;
}
TessAPI1.TessBaseAPISetRectangle(handle, box.x, box.y, box.w, box.h);
Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle);
String ocrResult = utf8Text.getString(0);
TessAPI1.TessDeleteText(utf8Text);
int conf = TessAPI1.TessBaseAPIMeanTextConf(handle);
System.out.print(
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));
}
// release Pix resource
PointerByReference pRef = new PointerByReference();
pRef.setValue(pix.getPointer());
Leptonica1.pixDestroy(pRef);
assertEquals(expResult, boxCount);
}
/**
* Test of TessBaseAPIGetUTF8Text method, of class TessDllAPI1.
*
* @throws Exception while processing the image
*/
@Test
public void testTessBaseAPIGetUTF8Text() throws Exception {
logger.info("TessBaseAPIGetUTF8Text");
String expResult = expOCRResult;
File tiff = new File(this.testResourcesDataPath, "eurotext.tif");
BufferedImage image =
ImageIO.read(new FileInputStream(tiff)); // require jai-imageio lib to read TIFF
ByteBuffer buf = ImageIOHelper.convertImageData(image);
int bpp = image.getColorModel().getPixelSize();
int bytespp = bpp / 8;
int bytespl = (int) Math.ceil(image.getWidth() * bpp / 8.0);
TessAPI1.TessBaseAPIInit3(handle, datapath, language);
TessAPI1.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO);
TessAPI1.TessBaseAPISetImage(
handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl);
TessAPI1.TessBaseAPISetRectangle(handle, 0, 0, 1024, 800);
Pointer utf8Text = TessAPI1.TessBaseAPIGetUTF8Text(handle);
String result = utf8Text.getString(0);
TessAPI1.TessDeleteText(utf8Text);
logger.info(result);
assertEquals(expResult, result.substring(0, expResult.length()));
}