I cannot emphasize this single item (in a long list of stuff one can/must do before feeding any image to an OCR engine) enough: *tesseract has been trained to 'read' books, i.e black text on white background. Consequently, any image preprocessing step(s) that get you there, are strongly advised.*
This, and lots of other "*I don't wanna hear this 🥴*" important details show up in the documents and emails listed below: (I know people like twitter-sized or shorter text, but you've got some reading to do if you want to be successful at OCRing stuff. We all have to, it's not simple.) *- https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html <https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html> 🎯* - https://github.com/tesseract-ocr/tessdoc/blob/main/tess3/FAQ-Old.md#is-there-a-minimum--maximum-text-size-it-wont-read-screen-text - https://groups.google.com/g/tesseract-ocr/c/Wdh_JJwnw94/m/24JHDYQbBQAJ?pli=1 - https://groups.google.com/g/tesseract-ocr/c/B2-EVXPLovQ/m/lP0zQVApAAAJ and then a bunch of messages that are related; I'd rather not repeat myself, so please take your time and read those threads: some of it may sound crazy at first, but you're doing something that's touching on the edge of the original design goals and that means you're bound to meet some "weird behaviour" along the way. Before I let myself out, *the second most important piece of advice I can give everyone: use HOCR (which is HTML content plus coordinates) or TSV output instead of anything else; do not, I repeat: !DO NOT! output txt format, just because every internet wizard out there does it in their blog: txt (text) format is minimal-information and you are way better off with a maximal-information output for when you need to diagnose trouble* -- plus, now you've seen the workflow diagram that's part of the info above, *turning HOCR/TSV into TXT should be part of your postprocessing*, AFAIAC. Other direct or sideways relevant blurbs to be read here (again, consider reading the entire threads; OCR is one of those activities where 'quickly scanning my text books to pass my exam' as you previously learned at school is not going to get you closer to success faster, on the contrary: - https://groups.google.com/g/tesseract-ocr/c/jWdpUF7mTxE - https://groups.google.com/g/tesseract-ocr/c/vrBc1FPeprQ/m/GxTlapF-BwAJ - https://groups.google.com/g/tesseract-ocr/c/c_S7GG5njkw/m/OPQ6q5zBAQAJ - https://groups.google.com/g/tesseract-ocr/c/8BerjYWGGQU/m/KwSz7724AQAJ - https://groups.google.com/g/tesseract-ocr/c/YLOkyuOMsrs/m/wEKTYtfQAAAJ HTH Met vriendelijke groeten / Best regards, Ger Hobbelt -------------------------------------------------- web: http://www.hobbelt.com/ http://www.hebbut.net/ mail: [email protected] mobile: +31-6-11 120 978 -------------------------------------------------- On Thu, Oct 30, 2025 at 6:26 PM Michael Schuh <[email protected]> wrote: > I am trying to extract the date and time from > > [image: time.png] > > I have successfully use tesseract to extract text from other images. > tesseract does not find any text in the above image, > > michael@argon:~/michael/trunk/src/tides$ tesseract time.png out > Estimating resolution as 142 > > michael@argon:~/michael/trunk/src/tides$ cat out.txt > > michael@argon:~/michael/trunk/src/tides$ ls -l out.txt > -rw-r----- 1 michael michael 0 Oct 30 08:58 out.txt > > Any help you can give me would be appreciated. I attached the time.png > file I used above. > > Thanks, > Michael > > -- > 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 visit > https://groups.google.com/d/msgid/tesseract-ocr/77ac0d2b-7796-4f17-8bc6-0e70a9653adan%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/77ac0d2b-7796-4f17-8bc6-0e70a9653adan%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 visit https://groups.google.com/d/msgid/tesseract-ocr/CAFP60fo3H7nEZ%2BMLWE6j9c--hBzmqFWSFUdGAXbDULBb27wnPQ%40mail.gmail.com.
