All Versions
16
Latest Version
Avg Release Cycle
103 days
Latest Release
628 days ago

Changelog History
Page 1

  • v1.7.2 Changes

    September 24, 2024
    • 24 September 2024 - Version 1.7.2
      • Fix several compatibilities

  • v1.7.1 Changes

    September 04, 2023
    • 4 September 2023 - Version 1.7.1
      • Fix several compatibilities

  • v1.7.0 Changes

    May 25, 2023

  • v1.6.2 Changes

    September 15, 2022
    • 15 September 2022 - Version 1.6.2
      • Add CPU support for DBnet detector
      • DBnet will only be compiled when users initialize EasyOCR with DBnet detector.

  • v1.6.1 Changes

    September 01, 2022
    • 1 September 2022 - Version 1.6.1
      • Fix DBNET path bug for Windows
      • Add new built-in model cyrillic_g2. This model is a new default for Cyrillic script.

  • v1.6.0 Changes

    August 24, 2022

    v1.6.0

    • 24 August 2022 - Version 1.6.0
      • Restructure code to support alternative text detectors.
      • Add detector DBNET, see paper. It can be used by initializing like this reader = easyocr.Reader(['en'], detect_network = 'dbnet18').

  • v1.5.0 Changes

    June 02, 2022

    v1.5.0

    • 2 June 2022 - Version 1.5.0
      • Add trainer for CRAFT detection model (thanks@gmuffiness, see PR)

  • v1.4.2 Changes

    April 09, 2022
    • 9 April 2022 - Version 1.4.2
      • Update dependencies (opencv and pillow issues)

  • v1.4.1 Changes

    September 11, 2021
    • 11 September 2021 - Version 1.4.1
      • Add trainer folder
      • Add readtextlang method (thanks@arkya-art, see PR)
      • Extend rotation_info argument to support all possible angle (thanksabde0103, see PR)

  • v1.4 Changes

    June 29, 2021
    • 29 June 2021 - Version 1.4
      • Instruction on training/using custom recognition model
      • Example dataset
      • Batched image inference for GPU (thanks @SamSamhuns, see PR)
      • Vertical text support (thanks @interactivetech). This is for rotated text, not to be confused with vertical Chinese or Japanese text. (see PR)
      • Output in dictionary format (thanks @A2va, see PR)