All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- Reworked CV POM API
- Now you can add properties to OCR in convert_to_cvpom(source, ocr_props=None)
- This properties can be added to the CVPOMDriver in the new kwargs:
kwargs = {'ocr': {'paragraph': True}} # Optional
MyCVPOMDriver(model_path, framework_specific_driver, **kwargs)
For now is only used for ocr and the values are any parameters that EasyOCR allows under self._reader.readtext(**ocr_props_comb) check here