ocrs

ocrs copied to clipboard

ocrs crashes one of my computers but runs fine on a weaker but more modern CPU

2

This is my code ```rust use std::{collections::VecDeque, path::PathBuf}; use image; use ocrs::{OcrEngine, OcrEngineParams}; use rten; use rten_imageio::read_image; use rten_tensor::AsView; const SAMPLE_CONTENTS_DIR: &str = "testing_images"; const MODELS_DIR: &str = "models"; mod...

Raj2032

Automatically downscale large input images

8

Input images from cameras etc. often have a much higher resolution than is needed to read the text. Downscaling the image can often produce the same output in much less...

robertknight

Bumps [wasm-bindgen](https://github.com/rustwasm/wasm-bindgen) from 0.2.89 to 0.2.92. Changelog Sourced from wasm-bindgen's changelog. 0.2.92 Released 2024-03-04 Added Add bindings for RTCPeerConnectionIceErrorEvent. #3835 Add bindings for CanvasState.reset(), affecting CanvasRenderingContext2D and OffscreenCanvasRenderingContext2D. #3844 Add...

dependabot[bot]

Is PDF / DOCX support on the roadmap?

3

I know this is not trivial since I've been unsuccessful in finding any PDF->image Rust library, but is this something you plan on supporting in the future? If help is...

wdoppenberg

Add script to evaluate perfomance on SROIE dataset

1

Related to the discussion in https://github.com/robertknight/ocrs/issues/43 this adds a script to evaluate on the SROIE 2019 dataset (scanned recipes). I wanted to do end-to-end eval, and needed the executable, so...

rth

Add evaluation benchmarks

5

Thanks for creating this package! As discussed in https://github.com/robertknight/ocrs/issues/14 it would be nice to add some evaluation benchmarks. And maybe optionally compare with tesseract or some other reference open source...

rth

Support table

1

support table-ocr to csv will be nice

attila-lin

Roadmap for 2024

4

This issue exists to document what I think are the highest priorities in the short-medium term. **Models and training:** - [x] Document how to repeat the model training process (https://github.com/robertknight/ocrs-models/issues/6)....

robertknight

Rectify text lines before recognition

2

Ocrs does not currently apply any perspective correction to extracted text lines before applying recognition. The recognition model is trained to handle skewed and rotated inputs, but this only works...

robertknight

Make it easy to update models to latest version

1

ocrs-cli will automatically download models on first run. It would be useful if it could automatically download updated models when they become available. Some considerations and constraints: - There should...

robertknight