Skip to content

Releases: agfianf/color-correction

v0.0.1-rc6

24 Oct 06:54
125738f

Choose a tag to compare

v0.0.1-rc6 Pre-release
Pre-release
Merge pull request #15 from agfianf/claude/code-quality-review-011CUR…

v0.0.1-rc5

16 Apr 03:25
7ff4b6f

Choose a tag to compare

v0.0.1-rc5 Pre-release
Pre-release

Update Docs

v0.0.1-rc4

12 Apr 07:20
05cb139

Choose a tag to compare

v0.0.1-rc4 Pre-release
Pre-release

Release Candidate with MCCardDetector and Segmentation Support

This release introduces the MCCardDetector for improved color checker card detection, adds segmentation support, and includes minor fixes and dependency updates.

Added

  • Implemented MCCardDetector class in color_correction/core/card_detection/mcc_det.py for detecting color checker cards and patches using OpenCV's mcc module.
  • Added segmentation support to handle quadrilateral regions via SegmentPoint type and updated DetectionResult schema to include segment field.
  • Introduced crop_segment_straighten utility in image_processing.py to straighten and crop quadrilateral regions using perspective transformation.
  • Extended DetectionProcessor to process both bounding box and segmentation-based detection results.
  • Added draw_segmentation function in yolo_utils.py to visualize segmentation polygons on images.
  • Updated ColorCorrection service to support both YOLOv8CardDetector and MCCardDetector based on model name (yolov8 or mcc).

Changed

  • Bumped version to 0.0.1-rc4 in __init__.py and pyproject.toml.
  • Updated DetectionProcessor.extract_color_patches to handle segmentation results alongside bounding boxes.
  • Modified ColorCorrectionAnalyzer to use set_reference_patches instead of set_reference_image for consistency.
  • Adjusted dependency versions in pyproject.toml for compatibility:
    • pydantic>=2.10.6
    • pydantic-settings>=2.8.1
    • shapely>=2.0.7
    • matplotlib>=3.10.1
    • onnx==1.17.0
    • onnxruntime==1.20.1
    • pandas==2.2.3
    • opencv-contrib-python>=4.11.0.86
    • Dev dependencies: pytest==8.3.5, ruff==0.11.2, pre-commit==4.2.0, ultralytics==8.3.96
  • Changed ruff line-length to 120 in pyproject.toml for better code formatting flexibility.

Fixed

  • Ensured DetectionResult schema compatibility with both bounding box and segmentation outputs by making boxes and segment optional.
  • Added debug logging in ColorCorrection to track grid image shapes during color difference calculations.

What's Changed

  • Feat/fixing reference image setting by @agfianf in #12

Full Changelog: v0.0.1-rc3...v0.0.1-rc4

v0.0.1-rc3

11 Feb 15:47
75f5bc7

Choose a tag to compare

v0.0.1-rc3 Pre-release
Pre-release

What's Changed

Full Changelog: v0.0.1-rc2...v0.0.1-rc3

v0.0.1-rc2

09 Feb 16:39
6ebe1cb

Choose a tag to compare

v0.0.1-rc2 Pre-release
Pre-release

What's Changed

Full Changelog: v0.0.1-rc1...v0.0.1-rc2

v0.0.1-rc1

09 Feb 14:56

Choose a tag to compare

v0.0.1-rc1 Pre-release
Pre-release

Release Candidate with Full Feature Set and Documentation

What's Changed

Full Changelog: v0.0.1b3...v0.0.1-rc1

v0.0.1b3

05 Feb 22:59
08b60e2

Choose a tag to compare

v0.0.1b3 Pre-release
Pre-release

Add Analyzer Report and Bug Fixes

🚀 Features

  • Added comprehensive reporting functionality for color correction results
    • New ColorCorrectionAnalyzer class for benchmarking different correction methods
    • HTML report generation with interactive sorting and PDF export
    • Visual comparison of before/after color patches
    • Detailed ΔE metrics for patches and full images
  • Enhanced image processing utilities
    • Added base64 image conversion support
    • Improved color difference calculation with rounded metrics
  • Added HTML report generation templates and styling
    • Responsive design with Plus Jakarta Sans font
    • Interactive table sorting
    • PDF export functionality
    • Detailed column descriptions

📝 Documentation

  • Added new Analyzer section in README
    • Example usage code for ColorCorrectionAnalyzer
    • Sample benchmark output visualization
  • Updated version to 0.0.1b3

🔧 Technical Changes

  • Renamed benchmark class to report for better clarity
  • Added new utility modules:
    • formater.py for value formatting
    • report_generator.py for HTML generation
    • Added new constants and method definitions

Fix Naming Package

05 Feb 00:54
ca64a1d

Choose a tag to compare

Fix Naming Package Pre-release
Pre-release
Merge pull request #6 from agfianf/fix/naming-package

Fix/naming package

v0.0.1b1

04 Feb 17:04
0e121db

Choose a tag to compare

v0.0.1b1 Pre-release
Pre-release

Enhanced Color Correction with Improved Documentation and Evaluation

✨ Features

  • Enhanced color correction with improved patch comparison and metrics
  • Added polynomial correction model with configurable degrees
  • Implemented comprehensive color difference evaluation

📚 Documentation

  • Added "How it works" section with visual explanation
  • Updated README with polynomial correction details
  • Improved section headers for better clarity
  • Added sample debug output visualization
  • Enhanced usage examples with evaluation results

🔧 Technical

  • Added calc_color_diff_patches() method for quality evaluation
  • Implemented CIE 2000 color difference calculation
  • Enhanced debug visualization capabilities
  • Added support for multiple correction models

v0.0.1b0

03 Feb 14:45
778a14d

Choose a tag to compare

v0.0.1b0 Pre-release
Pre-release

Enhance Color Correction with Multiple Models and Improved Visualization

🔧 Improvements

  • Color Correction Core
    • Added new correction models: polynomial, linear regression, and affine regression
    • Improved patch detection and processing pipeline
    • Added support for debug visualization outputs
    • Enhanced color patch extraction with better error handling

🎨 Features

  • Reference Colors
    • Added RGB format reference colors alongside BGR
    • Improved color patch visualization and comparison tools
    • Added support for custom reference images

📝 Documentation

  • README Updates
    • Simplified usage documentation with clearer examples
    • Added visual explanation of color correction workflow
    • Updated installation and usage instructions

🛠️ Development

  • Project Structure
    • Reorganized core modules for better maintainability
    • Added new utility modules for image processing
    • Updated VSCode settings for better development experience

🔨 Build

  • Dependencies
    • Added scikit-learn for advanced correction models
    • Updated ruff to v0.9.4
    • Added pre-commit hooks configuration

🧪 Testing

  • Test Coverage
    • Added new test cases for image processing utilities
    • Improved test organization and structure