Skip to content
CAI
Software that uses CAICheck a score

JaidedAI/EasyOCR

50.3

Adequate · 15 November 2026

12k

lines of production code

Python

with C++

5

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Add CRAFT text detection training code and configuration

The \trainer\ directory now includes the complete training infrastructure for the CRAFT (Character Region Awareness for Text Detection) model. This addition provides Python scripts for training on synthetic (SynthText) and custom datasets, along with evaluation utilities and metrics. It also introduces YAML configuration files to manage training hyperparameters, data augmentation settings, and model architecture options, enabling users to train and fine-tune the CRAFT detection model.

trainer · high confidence

Add DBNet text detection module with CPU-compatible Deformable Convolution

This change introduces the DBNet text detection module to EasyOCR, providing an alternative to the default CRAFT detector. The module includes a new \DBNet\ class for model initialization and inference, along with ResNet and MobileNetV3 backbone implementations. A key feature is the integration of Deformable Convolution (DCN) operators that support Just-in-Time (JiT) compilation, allowing the module to run on CPU hardware in addition to CUDA-enabled GPUs. The implementation also includes updated pretrained weight naming conventions and configuration files to support this inference-only, cross-platform deployment.

easyocr/DBNet · high confidence

Added Japanese dictionary and punctuation generation script

A new Ruby script (scripts/generate-ja.rb) has been added to download and process the JMdict and JMnedict XML resources, generating updated Japanese character lists, a word dictionary, and a punctuation set for the EasyOCR library. A corresponding .gitignore file has been added to exclude the downloaded XML archives from version control.

scripts · high confidence

DBNet detection now supports CPU inference

The DBNet text detection module now runs on CPUs by adding C++ and CUDA implementations for deformable convolution and deformable PSROI pooling operators. This allows users to perform text detection with DBNet on systems without a GPU or when GPU acceleration is unavailable, whereas previously these operations were likely restricted to CUDA-enabled hardware.

easyocr · high confidence

EasyOCR v1.7.2 release with Docker support and CLI entry point

This update introduces EasyOCR version 1.7.2, which includes a new Dockerfile for containerized deployment, a MANIFEST.in file to ensure model and script assets are included in package distributions, and a console script entry point (\easyocr\) for command-line usage. The project has been rebranded from 'JaidedRead' to 'EasyOCR' in the README, and a \custom\_model.md\ guide has been added to document how to train and use custom recognition models.

(repo-wide) · high confidence

Behavioural changes

Refactored model architecture for TorchScript compatibility and torchvision updates

The model implementation in easyocr/model has been refactored to support TorchScript serialization and maintain compatibility with newer versions of torchvision. The VGG backbone now uses a standard class instead of a named tuple for outputs, resolving serialization issues. Additionally, the code handles deprecated pretrained parameter usage in torchvision (version 0.13+) and includes a workaround for AdaptiveAvgPool2d with None target size to ensure TorchScript compatibility. The BidirectionalLSTM module also includes a try-except block for flatten\_parameters to support multi-GPU environments.

easyocr/model · high confidence

Test coverage

Added EasyOCR unit testing framework and documentation

Introduced a new \unit\_test\ module that provides a comprehensive framework for validating EasyOCR functionality. This includes a \UnitTest\ class for executing tests against specific EasyOCR modules (such as detection, recognition, and text extraction), a Python script (\run\_unit\_test.py\) and an IPython notebook (\demo.ipynb\) for running these tests with configurable verbosity, and a utility script (\make\_test\_solution.py\) for generating test data packages. The addition is accompanied by a \README.md\ detailing usage instructions and argument options.

_unit\test · high confidence

Dependencies

Add dependency manifests for CRAFT training and base project

Added requirements.txt files for the base project and the CRAFT trainer component. The base requirements.txt specifies dependencies including torch, torchvision, opencv-python-headless, scipy, numpy, Pillow, scikit-image, python-bidi, PyYAML, Shapely, pyclipper, and ninja. The trainer/craft/requirements.txt pins specific versions for conda, opencv-python, Pillow, Polygon3, PyYAML, scikit-image, Shapely, torch, torchvision, and wandb to ensure reproducible training environments.

(dependencies) · high confidence

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 46 → 50 (+4.6)
  • Rubric changed (rubric-2026.11.1 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 58 → 67 (+9.4)
  • Architecture 92 → 92 (-0.0)
  • Maturity 40 → 51 (+11.6)
  • Readiness 34 → 35 (+0.3)
  • Security 86 → 87 (+1.0)

Resolved (60)

  • Dormant codebase
  • Duplicated block (10 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (15 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (22 lines × 2) (easyocr/model/modules.py)
  • Duplicated block (29 lines × 2) (easyocr/cli.py)
  • Duplicated block (5 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (5 lines × 2) (easyocr/model/modules.py)
  • Duplicated block (5 lines × 2) (easyocr/scripts/compile_dbnet_dcn.py)
  • Duplicated block (6 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (6 lines × 3) (easyocr/craft.py)
  • Duplicated block (7 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (7 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (7 lines × 2) (trainer/craft/utils/util.py)
  • Duplicated block (8 lines × 2) (easyocr/craft_utils.py)
  • Duplicated block (8 lines × 2) (easyocr/model/modules.py)
  • Duplicated block (8 lines × 2) (trainer/craft/trainSynth.py)
  • Duplicated block (9 lines × 2) (easyocr/craft.py)
  • Edited copy of a member (38 corresponding lines) (easyocr/model/modules.py)
  • Medium IaC: DS-0013 (Dockerfile)
  • Most significant orphaned file (easyocr/config.py)
  • …and 40 more

New (38)

  • Edited copies of one member (3 members, 17+ corresponding lines) (easyocr/DBNet/decoders/simple_detection.py)
  • Edited copy of a member (11 corresponding lines) (easyocr/DBNet/assets/ops/dcn/modules/deform_conv.py)
  • Edited copy of a member (11 corresponding lines) (easyocr/model/modules.py)
  • Edited copy of a member (13 corresponding lines) (easyocr/DBNet/backbones/resnet.py)
  • Edited copy of a member (14 corresponding lines) (easyocr/model/model.py)
  • Edited copy of a member (18 corresponding lines) (easyocr/utils.py)
  • Edited copy of a member (18 corresponding lines) (trainer/craft/loss/mseloss.py)
  • Edited copy of a member (2 corresponding lines) (easyocr/craft_utils.py)
  • Edited copy of a member (2 corresponding lines) (easyocr/model/modules.py)
  • Edited copy of a member (20 corresponding lines) (easyocr/DBNet/assets/ops/dcn/modules/deform_pool.py)
  • Edited copy of a member (23 corresponding lines) (trainer/craft/trainSynth.py)
  • Edited copy of a member (26 corresponding lines) (easyocr/DBNet/backbones/resnet.py)
  • Edited copy of a member (27 corresponding lines) (easyocr/recognition.py)
  • Edited copy of a member (28 corresponding lines) (easyocr/imgproc.py)
  • Edited copy of a member (29 corresponding lines) (easyocr/utils.py)
  • Edited copy of a member (3 corresponding lines) (easyocr/imgproc.py)
  • Edited copy of a member (3 corresponding lines) (easyocr/model/modules.py)
  • Edited copy of a member (3 corresponding lines) (easyocr/recognition.py)
  • Edited copy of a member (32 corresponding lines) (easyocr/DBNet/decoders/seg_detector.py)
  • Edited copy of a member (39 corresponding lines) (easyocr/DBNet/backbones/resnet.py)
  • …and 18 more

Changes since last survey

  • 2 commits — 1 feature/other, 1 fixes

By area

  • (repo) — 2 commits

Notable commits

  • fix: Merge pull request #1464 from Sainath-Reddy7/fix/readme-dead-link
  • change: Merge pull request #1468 from PetrDlouhy/optional-ninja-dbnet-extra

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

JaidedAI/EasyOCR was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 15 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 2f77e2e8125d666af859a57d49014731ecbf40c6 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.73+preprod-52de90b74216.