>There is the same version of tesseract on the two systems as i mentioned before.
OK. But is there any difference in specs of the 2 systems in terms of AVX etc. Hence tesseract -v would be useful. Also, just check the results via CLI. I get different results when using eng.traineddata from tessdata_best and tessdata_fast ubuntu@tesseract-ocr:~/TEST$ tesseract unnamed.png - --tessdata-dir ~/tessdata_fast Warning: Invalid resolution 0 dpi. Using 70 instead. Estimating resolution as 195 OFW ID CARD Republe of the Pieippings * Department of Labor and Employment ae Phiipploe Overseas Employment Admieistration, MARIA SANTOS DELA CRUZ 29911483 ‘enh x Sess) GIDE ubuntu@tesseract-ocr:~/TEST$ tesseract unnamed.png - --tessdata-dir ~/tessdata_best Warning: Invalid resolution 0 dpi. Using 70 instead. Estimating resolution as 195 OFW ID CARD Ropubkc of he Pisppines Department of Labor and Employment "a Phiipplaa Overseas Employment Admieistration MARIA SANTOS DELA CRUZ 29911483 rn ve hI [Op410) [EI On Tue, Dec 17, 2019 at 1:08 PM adesh gautam <[email protected]> wrote: > The file size of eng.traineddata is same - 3.92MB. > > On Tuesday, December 17, 2019 at 12:47:28 PM UTC+5:30, shree wrote: >> >> Please check file sizes for eng.traineddata - they maybe different >> versions even though they are called the same. >> >> On Mon, Dec 16, 2019 at 9:06 PM adesh gautam <[email protected]> wrote: >> >>> >>> There is the same version of tesseract on the two systems as i mentioned >>> before. >>> >>> The trained data is also same, eng.traineddata >>> >>> >>> These are the two images. >>> >>> [image: a.png] >>> >>> a.jpg >>> >>> >>> [image: b.png] >>> >>> b.jpg >>> >>> >>> And these are the outputs for the same images on different systems. >>> *System 1* >>> >>> *a.jpg* >>> >>> ['(A', '1, oy OFW ID CARD 2', 'Repubic of the Plasppines', 'o WJ, >>> Department of Laor and Empioyment )', '(SSRee) Philippine Oversans >>> Employment Admievstraticn,', 'ee ——', 'MARIA SANTOS DELA CRUZ', 'rn', >>> '20911483', 'orion, 10', 'inde [0p {0)]', 'os', 'isle =', 'TUTTI ARG >>> COMPANY [EI', 'dune 20, 2010'] >>> >>> *b.jpg* >>> >>> ['INTERNATIONAL STUDENT TY', 'EE', 'Ng ome'] >>> >>> *System 2* >>> >>> *a.jpg* >>> >>> ['(~~', '% oy OFW ID CARD L', 'Nepubse of the Preappinas', '4 wi. >>> Department of Labor and Employment »', 'Soe ac Pruippine Oversaas >>> Employment Adminvstraion,', 'fp', 'MARIA SANTOS DELA CRUZ', 'si00an', >>> '29911483', 'emt, 84', 'ine 1} 4 10)', 'mt', 'Mein Drbitue Bcd', '“werraci >>> —ABo coMPany Oat', 'Si vue 90, 2010'] >>> >>> *b.jpg* >>> >>> ['DCL ae Pcl', 'R) arc orn', 'PN secret'] >>> >>> >>> The output is different. >>> >>> Is it normal for tesseract ? >>> >>> >>> >>> On Monday, December 16, 2019 at 6:46:26 PM UTC+5:30, shree wrote: >>>> >>>> Run tesseract --version on the different systems. >>>> >>>> Are thetraineddata files being used on the different systems the same? >>>> >>>> Share an image and the different output received in each case. >>>> >>>> On Mon, Dec 16, 2019, 17:58 adesh gautam <[email protected]> wrote: >>>> >>>>> Hi, >>>>> >>>>> I am using tesseract-ocr on my images, and i am getting different >>>>> results by running tesseract on different systems for same image. >>>>> I am using *pytesseract *library. >>>>> I am setting the following parameters: >>>>> *--psm 6 -c classify_enable_learning=0 -c >>>>> classify_enable_adaptive_matcher=0* >>>>> >>>>> Images have* dpi=300*. >>>>> Tesseract version: >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> *tesseract v5.0.0-alpha.20191030 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 >>>>> FMA >>>>> Found SSE Found libarchive 3.3.2 zlib/1.2.11 liblzma/5.2.3 bz2lib/1.0.6 >>>>> liblz4/1.7.5* >>>>> >>>>> OS: >>>>> *Windows 10* >>>>> >>>>> Are there any system specific optimizations/dependencies by tesseract >>>>> ? >>>>> >>>>> >>>>> -- >>>>> 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 view this discussion on the web visit >>>>> https://groups.google.com/d/msgid/tesseract-ocr/414947ab-b10a-40b8-8196-65a5bbbb3e1c%40googlegroups.com >>>>> <https://groups.google.com/d/msgid/tesseract-ocr/414947ab-b10a-40b8-8196-65a5bbbb3e1c%40googlegroups.com?utm_medium=email&utm_source=footer> >>>>> . >>>>> >>>> -- >>> 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 view this discussion on the web visit >>> https://groups.google.com/d/msgid/tesseract-ocr/e2cf0580-e096-4b5f-80d8-5d609051f203%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/e2cf0580-e096-4b5f-80d8-5d609051f203%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> >> >> >> -- >> >> ____________________________________________________________ >> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >> > -- > 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 view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/e0946afd-dbbe-41ea-9741-1bfadeff97f3%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/e0946afd-dbbe-41ea-9741-1bfadeff97f3%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduXg%3D5ox9Z_SS5j7L7cnwK_xkheyfP523sa2q-FfZLja7Q%40mail.gmail.com.
