Aspose.OCR Cloud 22.12.0 - Release Notes
What was changed
This is the major release of Aspose.OCR Cloud which delivers significant new features, enhancements to existing features, performance improvements, and fixes. The list below contains the most important features that are supported in this release:
- Image to speech conversion
Convert almost any picture or photo with readable characters into a natural human voice that can be played in the background or downloaded.
- Advanced image binarization
A specialized neural network for converting images to black and white for better text recognition.
- Automatic skew correction
Detect image skew angle and automatically correct the tilt.
Detect perspective distortions and automatically straighten the image.
Intelligently enhance image resolution without losing the content and quality.
Public API changes and backwards compatibility
This release is based on a completely new architecture (version 5.0) that is not backward compatible with previous (version 3.0) principles and workflows.
To maintain compatibility, please continue to use the previous version of the Aspose.OCR Cloud API.
Added public APIs:
See Aspose OCR Cloud 5.0 API Reference for the full list of new endpoints and request parameters.
Updated public APIs:
This is the first release based on the new (version 5.0) architecture. When updates, renames and improvements are introduced, they will be described in future Release Notes. Keep for updates.
Removed public APIs:
This is the first release based on the new (version 5.0) architecture. When some of the methods become deprecated, this will be announced in future Release Notes.