They look alike.
http://www.fonts2u.com/dejavu-sans-extralight.font
http://www.fontsaddict.com/font/dejavu-sans-extralight.html
On Friday, July 18, 2014 6:34:15 AM UTC-5, Mustak M wrote:
>
> I am using Java wrapper Tess4J. Using following code to retrieve the font
> type and font size from an image. The image contains "Arial" font text and
> font size is 48. The code is returning font type as
> font: DejaVu_Sans_Ultra-Light, size: 13
>
> Code:
>
> * public*
> *static* *void* testResultIterator() *throws* Exception {
>
> String *datapath* =
> "tessdata";
>
> String *language* =
> "eng";
>
> String *expOCRResult* =
> "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 <lazy> #90 dog";
>
> TessAPI1.TessBaseAPI handle;
>
> handle = TessAPI1.*TessBaseAPICreate*();
>
> System.
> *out*.println("TessBaseAPIGetIterator");
>
> String lang =
> "eng";
>
> File tiff =
> *new* File("C:\\1\\CaptureArial.JPG");
>
> 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,
> "tessdata", lang);
>
> TessAPI1.*TessBaseAPISetPageSegMode*(handle, TessAPI1.TessPageSegMode.
> *PSM_AUTO*);
>
> TessAPI1.*TessBaseAPISetImage*(handle, buf, image.getWidth(),
> image.getHeight(), bytespp, bytespl);
>
> TessAPI1.*TessBaseAPIRecognize*(handle,
> *null*);
>
> TessAPI1.TessResultIterator ri = TessAPI1.*TessBaseAPIGetIterator*
> (handle);
>
> TessAPI1.TessPageIterator pi = TessAPI1.
> *TessResultIteratorGetPageIterator*(ri);
>
> TessAPI1.*TessPageIteratorBegin*(pi);
>
> System.
> *out*.println("Bounding boxes:\nchar(s) left top right bottom confidence
> font-attributes");
>
> // *int* height = image.getHeight();
>
> *do* {
>
> Pointer ptr = TessAPI1.*TessResultIteratorGetUTF8Text*(ri,
> TessAPI1.TessPageIteratorLevel.
> *RIL_WORD*);
>
> String word = ptr.getString(0);
>
> TessAPI1.*TessDeleteText*(ptr);
>
> *float* confidence = TessAPI1.*TessResultIteratorConfidence*(ri,
> TessAPI1.TessPageIteratorLevel.*RIL_WORD*);
>
> IntBuffer leftB = IntBuffer.*allocate*(1);
>
> IntBuffer topB = IntBuffer.*allocate*(1);
>
> IntBuffer rightB = IntBuffer.*allocate*(1);
>
> IntBuffer bottomB = IntBuffer.*allocate*(1);
>
> TessAPI1.*TessPageIteratorBoundingBox*(pi, TessAPI1.TessPageIteratorLevel.
> *RIL_WORD*, 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));
>
> // System.out.println(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() == TessAPI1.*TRUE*;
>
> *boolean* italic = italicB.get() == TessAPI1.*TRUE*;
>
> *boolean* underlined = underlinedB.get() == TessAPI1.*TRUE*;
>
> *boolean* monospace = monospaceB.get() == TessAPI1.*TRUE*;
>
> *boolean* serif = serifB.get() == TessAPI1.*TRUE*;
>
> *boolean* smallcaps = smallcapsB.get() == TessAPI1.*TRUE*;
>
> *int* pointSize = pointSizeB.get();
>
> *int* fontId = fontIdB.get();
>
> System.
> *out*.println(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,
> TessAPI1.TessPageIteratorLevel.*RIL_WORD*) == TessAPI1.*TRUE*);
>
> }
>
> ---------
>
> Its the same code refered from
>
>
> *http://sourceforge.net/p/tess4j/code/HEAD/tree/Tess4J_3/trunk/test/net/sourceforge/tess4j/TessAPI1Test.java#l447*
>
> <http://sourceforge.net/p/tess4j/code/HEAD/tree/Tess4J_3/trunk/test/net/sourceforge/tess4j/TessAPI1Test.java#l447>
>
> ----
>
> Any thoughts !
>
> Image file attached for reference.
>
>
>
> Thanks
>
>
>
>
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/e3f43b71-adc3-4e6d-ac98-f39ca72887f6%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
