tesseract

tesseract copied to clipboard

LSTM Engine Diplopia Issue and Inaccurate HOCR Character Level Box Dimensions

22

### Environment: Tesseract Latest Master from GitHub, Ubuntu 20.04.2 User References: @bertsky @stweil ### BackGround The problem named Diplopia (courtesy of @bertsky) consists in there being more than 1 character...

woodjohndavid

Page numbers not detected in various cases

30

### Environment * **Tesseract Version**: Various, `4.1.1`, `5.0.0 v20201231` * **Platform**: Linux, 64 bit ### Current Behavior: In some cases, Tesseract fully automatic page segmentation does not pick up page...

MerlijnWajer

Tesseract seemingly stuck

28

### Environment * **Tesseract Version**: Latest `master` * **Commit Number**: (`23ed59bd7bca777e4e104c4ee540843373aa9869` * **Platform**: `Linux gentoo-x13 5.11.7-gentoo-dist #1 SMP Wed Mar 17 21:03:41 -00 2021 x86_64 AMD Ryzen 7 PRO 4750U...

MerlijnWajer

Repair boundingbox of individual characters of textangle 90 text

7

Solution to issue #3590 (makebox doesn't output horizontal coordinates of textangle 90 content). I followed these lines back to 2010, there has been no-one fiddling with these lines, however they...

rmast

$ ./tesstrain.sh --fonts_dir /home/anupamjain/Documents/workspace/ocr_training/fonts --fontlist 'OCRB' --lang eng --linedata_only --langdata_dir /home/anupamjain/Documents/workspace/ocr_training/langdata_lstm --tessdata_dir /home/anupamjain/Documents/workspace/ocr_training/tesseract/tessdata --save_box_tiff --maxpages 10 --output_dir /home/anupamjain/Documents/workspace/ocr_training/train --exposures "0" === Starting training for language 'eng' [Thursday 28 April 2022...

anupamja-kore

Add option to use demo.processed.tif image to create the demo.pdf

1

Tesseract is doing a fantastic Job at processing the input image! original `demo.jpg` size is `3614 Kb` `tesseract demo.jpg out get.images` gives me `demo.processed.tif` which is only `35 kb` I'd...

codekoriko

LSTM: Non-dictionary words with combination of letters and numbers not recognized.

10

https://groups.google.com/d/msgid/tesseract-ocr/1a3e8773-7151-48f9-92bb-fda888293eab%40googlegroups.com?utm_medium=email&utm_source=footer > While the single "S" is recognized correctly, the text "2S" is recognized as "25". Here is link to the test image: https://03054610326450256607.googlegroups.com/attach/b8b86693ac072/2s.png?part=0.4&view=1

Shreeshrii

Support image width and height larger than 32767

20

Signed-off-by: Stefan Weil

stweil

lstmeval: Improve output by ensuring 'Truth:' text is encoded the same way as OCR output…

5

This ensures that transformations like unicode normalisation are done on the truth output as well as the OCR output, so that you can compare the two properly. Before this a...

nickjwhite

RFC: Remove tessdata directory and replace it by a submodule

6

Signed-off-by: Stefan Weil

stweil