Cropping the images to reduce the border size and rescaling so that max x was about 25 (between the recommended 20 and 30) fixed this.
On Thursday, September 25, 2025 at 10:55:01 AM UTC-4 Kevin wrote: > Not sure why the images didn't come through. I'll try again... > [image: crop_20250912_073819.jpg][image: crop_20250912_112602.jpg][image: > crop_20250913_000121.jpg][image: crop_20250913_090348.jpg] > On Thursday, September 25, 2025 at 10:52:27 AM UTC-4 Kevin wrote: > >> I have the following images that I'm trying to extract the text from, but >> tesseract keeps recognizing CAM08 and CAM09 as CAM03. I've tried many >> settings in tesseract as well as fffmpeg to modify the images, but nothing >> seems to help. I'm currently using the following version: >> >> tesseract 5.5.1-16-g17b4 >> >> with the following command: >> >> tesseract image.jpg -l eng --dpi 72 --psm 7 >> >> Are there better options to use in tesseract or can the images be cleaned >> up more with ffmpeg? >> >> Thanks, >> Kevin >> > -- 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/ddcfb998-2582-47b6-a800-e0c5f6b3e80cn%40googlegroups.com.
