Dear temp name, yes I tried "table without border.png", because you wrote "This image is also not recognized correctly" (and you attached image table without border.png).
With 3.03 you will get better results: e.g.: "0 0121 A" for image "first. PNG". I think solution could be "custom segmentation" (with tesseract API or uzn file in case of tesseract executable) E.g. (tested with 3.03 version and and I renamed your file to first.png ;-) ): - put attached uzn file to the same directory as first.png - run 'tesseract first.png - -psm 7' and you will get result "0| 0121|A|D" - there are information from all table cells separated by |. Of course you can not rely on this (cell border recognized as |), but I think is good demonstration what can be achieved with "custom segmentation" Zdenko On Tue, Mar 18, 2014 at 6:46 AM, temp name <[email protected]> wrote: > > Zdenko, > > you must have tried psm mode with image table_without_border. My query was > regarding the image first.png . The image contains a table with single row > and multiple column. Tesseract doesn't produce correct output for that > image. I have tried all the page segment mode with this image. I have > attached the image. Please suggest any solution for this. > > Thanks. > > On Monday, March 17, 2014 2:34:09 AM UTC+5:30, zdenop wrote: > >> Dear temp name, >> >> You wrote "I tried all the page segment mode, but it didn't solved my >> problem.". I tried correct page segment mode and I got attached output. I >> tried it with tesseract v3.02.02 and v3.03 RC1 on openSUSE 13.1 64bit. >> >> Are you sure that you tried ALL page segment mode? >> >> Zdenko >> >> >> On Sun, Mar 16, 2014 at 8:56 PM, temp name <[email protected]> wrote: >> >>> Zdenko, >>> >>> I tried all the page segment mode, but it didn't solved my problem. >>> >>> I tried outputting the page segment image. This image is also not >>> recognized correctly. >>> >>> Please reply soon. >>> >>> >>> On Thursday, March 13, 2014 2:49:56 AM UTC+5:30, zdenop wrote: >>> >>>> Did you read the wiki[1]? >>>> >>>> [1] https://code.google.com/p/tesseract-ocr/wiki/ImproveQual >>>> ity#Segmentation_method >>>> >>>> Zdenko >>>> >>>> >>>> On Thu, Feb 27, 2014 at 8:35 AM, temp name <[email protected]> wrote: >>>> >>>>> Hello, >>>>> >>>>> I have an image which contains only table. When I used tesseract for >>>>> OCR it doesn't recognize text from first and last column. >>>>> I have attached the image which I have used. >>>>> >>>>> After lot of trial, when I modified the image manually and added some >>>>> text over the table before feeding image to the tesseract. >>>>> I got correct results. I am not able to understand the logic here. why >>>>> tesseract don't recognize first image but it recognized second image. >>>>> I suspect it is because of table border analysis or page border >>>>> analysis in preprocessing phase of tesseract. if this is the case, then >>>>> tesseract should have a parameter which can force tesseract to ignore page >>>>> border analysis. I need some help urgently. Any idea? >>>>> >>>>> P.s.I have attached the two images. >>>>> >>>>> -- >>>>> -- >>>>> You received this message because you are subscribed to the Google >>>>> Groups "tesseract-ocr" group. >>>>> To post to this group, send email to [email protected] >>>>> >>>>> To unsubscribe from this group, send email to >>>>> [email protected] >>>>> >>>>> For more options, visit this group at >>>>> http://groups.google.com/group/tesseract-ocr?hl=en >>>>> >>>>> --- >>>>> 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]. >>>>> >>>>> For more options, visit https://groups.google.com/groups/opt_out. >>>>> >>>> >>>> -- >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "tesseract-ocr" group. >>> To post to this group, send email to [email protected] >>> To unsubscribe from this group, send email to >>> [email protected] >>> For more options, visit this group at >>> http://groups.google.com/group/tesseract-ocr?hl=en >>> >>> --- >>> 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]. >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> -- > -- > You received this message because you are subscribed to the Google > Groups "tesseract-ocr" group. > To post to this group, send email to [email protected] > To unsubscribe from this group, send email to > [email protected] > For more options, visit this group at > http://groups.google.com/group/tesseract-ocr?hl=en > > --- > 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]. > For more options, visit https://groups.google.com/d/optout. > -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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]. For more options, visit https://groups.google.com/d/optout.
first.uzn
Description: Binary data
