Amit Dovev

https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00#error-messages-from-training Try running text2inage with this option: `--output_word_boxes`

Was it solved with best/fast?

>Error in boxClipToRectangle: box outside rectangle >Error in pixScanForForeground: invalid box Error in >boxClipToRectangle: box outside rectangle Error in >pixScanForForeground: invalid box This is [a known bug](https://github.com/tesseract-ocr/tesseract/labels/boxClipToRectangle). It is caused...

>Which part is known? This only refers to the message >Error in boxClipToRectangle ...

Fine tuning might help to detect the missing dot in `No.: `. The wrong overlapping bounding boxes is a bug in the layout analysis phase done by Tesseract. Fine tuning...

The word confidence is the lowest confidence among all symbols in a word.

A symbol confidence of 0 looks odd. It should be interpreted as: "It's looks like there is a symbol there. It's hard to recognize, but here is my best guess".

Use [combine_tessdata](https://github.com/tesseract-ocr/tesseract/blob/f0b8c0254b24a3df7751708f67fa567b4aff2e11/doc/combine_tessdata.1.asc) to extract a traineddata file. Compare your ara/fas config file to the official one.

If the official model works well without a config file and your custom model does not, I don't know what's causing this issue and how it can be solved.

>Are the official best files done by Ray? Yes. For your other questions, I don't know.