I cleared the background of the image to the extent that I can possibly do but tesseract only detects the last column here and ignores the rest.
Why is this happening its showing very inconsistent resul
In this image it detects the 1st 2nd and third row
Can some one please explain to me why this is happening ?
I clean maually your image
and results are (leptonica1.74.4 and tesseract matser "4.00.00alpha"):
TEXT ETRACTION
langue :fra
moteur : Default, based on what is available.
analyse : Assume a single uniform block of text.
niveau : ligne
image : a.png
Image too small to scale!! (2x48 vs min width of 3)
Line cannot be recognized!!
Image too small to scale!! (2x48 vs min width of 3)
Line cannot be recognized!!
Text:
8212 15 1 4 40
l 7198 7 3 6 40
6307 6 1 5 60
5640 2 3 6 80
4884 1 1 5 80
proba = 94.9853->[2418 x 49 from (34, 47)] : 8212 15 1 4 40
proba = 84.1706->[2452 x 111 from (0, 150)] : l 7198 7 3 6 40
proba = 94.5019->[2417 x 49 from (35, 377)] : 6307 6 1 5 60
proba = 96.1703->[2416 x 49 from (36, 542)] : 5640 2 3 6 80
proba = 94.8845->[2419 x 49 from (33, 707)] : 4884 1 1 5 80
I don't know python.
In first image you can sum rows and it will give you region with low value and high value. You can crop image using region. @sturkmen got a code for this in a post.
For second image may be you use the same method to decide when inverse image
Asked: 2017-09-13 14:02:52 -0600
Seen: 1,763 times
Last updated: Sep 14 '17
