Meanwhile I found some PHP functions to crop the image and change the contrast and brightness. The code is as follows:
// Resize $thumb = imagecrop($source, ['x' => 830, 'y' => 330, 'width' => 115, 'height' => 30]); // Filter imagefilter($thumb, IMG_FILTER_GRAYSCALE); imagefilter($thumb, IMG_FILTER_BRIGHTNESS, +50); imagefilter($thumb, IMG_FILTER_CONTRAST, -50); As a result I got at least a result: 39984 Its still not correct, but better than no identification of any letter... How can I improve? Martina Ilgon schrieb am Montag, 25. Dezember 2023 um 18:09:12 UTC+1: > I'm totally new with Tesseract and its usage and I tried several hours to > get a suitable result for the attached web-cam picture of my gas meter. I > do use tesseract with the PHP wrapper from here > https://github.com/thiagoalessio/tesseract-ocr-for-php and installation > and recognition with the given examples work fine. Can anybody give me an > advice? Thanks... > > > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/853740b8-a34e-416d-a7ba-7f3a5e263c38n%40googlegroups.com.
