Yandex Vision OCR release notes

Current versionCurrent version

Release on 06/02/2024Release on 06/02/2024

1. Improved table recognition quality. Now the service should recognize all tables as tables.
2. Added Turkish language support for table recognition.

Previous versionsPrevious versions

Release on 11/01/2024Release on 11/01/2024

Updated the table recognition model.

Release on 07/04/2023Release on 07/04/2023

1. To enable document recognition, we added the vehicle-registration-front and vehicle-registration-back models that extract data from vehicle registration certificates.
2. Improved recognition accuracy for all models.
3. Significantly improved PDF file processing quality.