I am trying to get character level details of a file using
hocr_char_boxes=1 option.
But the output it generates seems to be overlapping between the characters.
<div class='ocr_page' id='page_1' title='image "file-0.png"; bbox 0 0
1653 2336; ppageno 0'>
<div class='ocr_carea' id='block_1_1' title="bbox 111 203 930 219">
<p class='ocr_par' id='par_1_1' lang='eng' title="bbox 111 203 930 219">
<span class='ocr_line' id='line_1_1' title="bbox 111 203 930 219;
baseline -0.001 -3; x_size 20; x_descenders 5; x_ascenders 5">
<span class='ocrx_word' id='word_1_1' title='bbox 111 204 135 216;
x_wconf 96'>
<span class='ocrx_cinfo' title='x_bboxes 111 204 117 216;
x_conf 99.56546'>S</span>
<span class='ocrx_cinfo' title='x_bboxes 111 204 119 216;
x_conf 99.574463'>e</span>
<span class='ocrx_cinfo' title='x_bboxes 120 207 135 216;
x_conf 99.543205'>e</span></span>
How can two characters have the same starting point(For S: 'x_bboxes 111
204 117 216 and for e: x_bboxes 111 204 119 216 )
Tesseract details:
tesseract v4.1.0-elag2019
leptonica-1.78.0
libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.3) : libpng 1.6.34 : libtiff
4.0.9 : zlib 1.2.11 : libwebp 0.6.1 : libopenjp2 2.3.0
Found AVX2
Found AVX
Found SSE
Attached the image file.
--
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 tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/3e290dc6-ef6e-4f2a-acf2-d32d864fabcan%40googlegroups.com.
