/**
* Test of ChoiceIterator.
*
* @throws Exception
*/
@Test
public void testChoiceIterator() throws Exception {
logger.info("TessResultIteratorGetChoiceIterator");
String filename = String.format("%s/%s", this.testResourcesDataPath, "eurotext.tif");
File tiff = new File(filename);
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.TessBaseAPISetImage(
handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl);
TessAPI1.TessBaseAPISetVariable(handle, "save_blob_choices", "T");
TessAPI1.TessBaseAPISetRectangle(handle, 37, 228, 548, 31);
ETEXT_DESC monitor = new ETEXT_DESC();
ProgressMonitor pmo = new ProgressMonitor(monitor);
pmo.start();
TessAPI1.TessBaseAPIRecognize(handle, monitor);
logger.info("Message: " + pmo.getMessage());
TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle);
int level = TessPageIteratorLevel.RIL_SYMBOL;
if (ri != null) {
do {
Pointer symbol = TessAPI1.TessResultIteratorGetUTF8Text(ri, level);
float conf = TessAPI1.TessResultIteratorConfidence(ri, level);
if (symbol != null) {
logger.info(String.format("symbol %s, conf: %f", symbol.getString(0), conf));
boolean indent = false;
TessChoiceIterator ci = TessAPI1.TessResultIteratorGetChoiceIterator(ri);
do {
if (indent) {
System.out.print("\t");
}
System.out.print("\t- ");
String choice = TessAPI1.TessChoiceIteratorGetUTF8Text(ci);
logger.info(
String.format("%s conf: %f", choice, TessAPI1.TessChoiceIteratorConfidence(ci)));
indent = true;
} while (TessAPI1.TessChoiceIteratorNext(ci) == TessAPI1.TRUE);
TessAPI1.TessChoiceIteratorDelete(ci);
}
logger.info("---------------------------------------------");
TessAPI1.TessDeleteText(symbol);
} while (TessAPI1.TessResultIteratorNext(ri, level) == TessAPI1.TRUE);
}
assertTrue(true);
}
/**
* Test of TessBaseAPIRect method, of class TessDllAPI1.
*
* @throws Exception while processing the image
*/
@Test
public void testTessBaseAPIRect() throws Exception {
logger.info("TessBaseAPIRect");
String expResult = expOCRResult;
File tiff = new File(this.testResourcesDataPath, "eurotext.tif");
BufferedImage image = ImageIO.read(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);
Pointer utf8Text = TessAPI1.TessBaseAPIRect(handle, buf, bytespp, bytespl, 0, 0, 1024, 800);
String result = utf8Text.getString(0);
TessAPI1.TessDeleteText(utf8Text);
logger.info(result);
assertEquals(expResult, result.substring(0, expResult.length()));
}
/**
* Test of TessBaseAPIGetHOCRText method, of class TessAPI1.
*
* @throws Exception while getting ocr text from image.
*/
@Test
public void testTessBaseAPIGetHOCRText() throws Exception {
logger.info("TessBaseAPIGetHOCRText");
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.TessBaseAPISetPageSegMode(handle, TessPageSegMode.PSM_AUTO);
TessAPI1.TessBaseAPIInit3(handle, datapath, language);
TessAPI1.TessBaseAPISetImage(
handle, buf, image.getWidth(), image.getHeight(), bytespp, bytespl);
int page_number = 0;
Pointer utf8Text = TessAPI1.TessBaseAPIGetHOCRText(handle, page_number);
String result = utf8Text.getString(0);
TessAPI1.TessDeleteText(utf8Text);
assertTrue(result.contains("<div class='ocr_page'"));
}
/**
* 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 ResultIterator and PageIterator.
*
* @throws Exception
*/
@Test
public void testResultIterator() throws Exception {
logger.info("TessBaseAPIGetIterator");
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);
ETEXT_DESC monitor = new ETEXT_DESC();
ITessAPI.TimeVal timeout = new ITessAPI.TimeVal();
timeout.tv_sec = new NativeLong(0L); // time > 0 causes blank ouput
monitor.end_time = timeout;
ProgressMonitor pmo = new ProgressMonitor(monitor);
pmo.start();
TessAPI1.TessBaseAPIRecognize(handle, monitor);
logger.error("Message: " + pmo.getMessage());
TessResultIterator ri = TessAPI1.TessBaseAPIGetIterator(handle);
TessPageIterator pi = TessAPI1.TessResultIteratorGetPageIterator(ri);
TessAPI1.TessPageIteratorBegin(pi);
logger.info("Bounding boxes:\nchar(s) left top right bottom confidence font-attributes");
int level = TessPageIteratorLevel.RIL_WORD;
// int height = image.getHeight();
do {
Pointer ptr = TessAPI1.TessResultIteratorGetUTF8Text(ri, level);
String word = ptr.getString(0);
TessAPI1.TessDeleteText(ptr);
float confidence = TessAPI1.TessResultIteratorConfidence(ri, level);
IntBuffer leftB = IntBuffer.allocate(1);
IntBuffer topB = IntBuffer.allocate(1);
IntBuffer rightB = IntBuffer.allocate(1);
IntBuffer bottomB = IntBuffer.allocate(1);
TessAPI1.TessPageIteratorBoundingBox(pi, level, leftB, topB, rightB, bottomB);
int left = leftB.get();
int top = topB.get();
int right = rightB.get();
int bottom = bottomB.get();
System.out.print(
String.format("%s %d %d %d %d %f", word, left, top, right, bottom, confidence));
// logger.info(String.format("%s %d %d %d %d", str, left, height - bottom, right, height -
// top)); //
// training box coordinates
IntBuffer boldB = IntBuffer.allocate(1);
IntBuffer italicB = IntBuffer.allocate(1);
IntBuffer underlinedB = IntBuffer.allocate(1);
IntBuffer monospaceB = IntBuffer.allocate(1);
IntBuffer serifB = IntBuffer.allocate(1);
IntBuffer smallcapsB = IntBuffer.allocate(1);
IntBuffer pointSizeB = IntBuffer.allocate(1);
IntBuffer fontIdB = IntBuffer.allocate(1);
String fontName =
TessAPI1.TessResultIteratorWordFontAttributes(
ri, boldB, italicB, underlinedB, monospaceB, serifB, smallcapsB, pointSizeB, fontIdB);
boolean bold = boldB.get() == TRUE;
boolean italic = italicB.get() == TRUE;
boolean underlined = underlinedB.get() == TRUE;
boolean monospace = monospaceB.get() == TRUE;
boolean serif = serifB.get() == TRUE;
boolean smallcaps = smallcapsB.get() == TRUE;
int pointSize = pointSizeB.get();
int fontId = fontIdB.get();
logger.info(
String.format(
" font: %s, size: %d, font id: %d, bold: %b,"
+ " italic: %b, underlined: %b, monospace: %b, serif: %b, smallcap: %b",
fontName, pointSize, fontId, bold, italic, underlined, monospace, serif, smallcaps));
} while (TessAPI1.TessPageIteratorNext(pi, level) == TRUE);
assertTrue(true);
}