Skip to content

misread seven or five depending on --psm value #4397

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
psurmont opened this issue Mar 9, 2025 · 0 comments
Open

misread seven or five depending on --psm value #4397

psurmont opened this issue Mar 9, 2025 · 0 comments

Comments

@psurmont
Copy link

psurmont commented Mar 9, 2025

Current Behavior

i m using tesseract 5.3.0 on a docker environement (Debian/php/mysql)
i use png images processed with a 600 DPI resolution.
when i use -l fra option on tesseract, 7 are very often misread as / or /7 or 7/
there are less misread if i don't use -l fra option.
But if i use --psm 4 then the misread 7 on / are also frequent. If i use --psm 6 option it's the 5 that are misread in 9 frequently. I looked at my png and there are no ways for those 7 to be misread in / or those 5 to be misread on 9.
I tried to use --dpi 600 or --dpi 300 and there are no improvement.
Thank you in advance.

Pierre

Expected Behavior

i expect all the digits of my documents to be read in a good way

Suggested Fix

i d k

tesseract -v

tesseract 5.3.0
leptonica-1.82.0
libgif 5.2.1 : libjpeg 6b (libjpeg-turbo 2.1.2) : libpng 1.6.39 : libtiff 4.5.0 : zlib 1.2.13 : libwebp
1.2.4 : libopenjp2 2.5.0
Found AVX
Found SSE4.1
Found OpenMP 201511
Found libarchive 3.6.2 zlib/1.2.13 liblzma/5.4.1 bz2lib/1.0.8 liblz4/1.9.4 libzstd/1.5.4
Found libcurl/7.88.1 OpenSSL/3.0.15 zlib/1.2.13 brotli/1.0.9 zstd/1.5.4 libidn2/2.3.3 libpsl/0.21.2 (+li
bidn2/2.3.3) libssh2/1.10.0 nghttp2/1.52.0 librtmp/2.3 OpenLDAP/2.5.13

Operating System

debian 12 / docker

Other Operating System

developpment platform is MACOS

uname -a

No response

Compiler

no compiler

CPU

No response

Virtualization / Containers

docker

Other Information

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant