This commit introduces a new confidence calibration system that converts DeepFace distance values into actual match probabilities, addressing previous misleading confidence percentages. Key changes include the addition of calibration methods in `FaceProcessor`, updates to the `IdentifyPanel` and `AutoMatchPanel` to utilize calibrated confidence, and new configuration settings in `config.py`. The README has been updated to document these enhancements, ensuring users see more realistic match probabilities throughout the application.
This commit modifies the `AutoMatchPanel` class to enable search entry and buttons when the auto-match process starts. The search controls are disabled when there is only one matched person, and the help label text is updated accordingly. Additionally, the search controls are disabled when clearing the search, improving user experience by providing clear feedback on search functionality status.
This commit introduces a new method `_calculate_face_canvas_size` in the `IdentifyPanel` class to calculate a responsive size for the face canvas based on the available window space. Additionally, the `_update_face_canvas_size` method has been implemented to dynamically adjust the canvas size during window resize events. The dashboard GUI has also been updated to improve layout consistency by fixing the width of the folder input text box. These changes enhance the user experience by ensuring that the face canvas adapts to different screen sizes and resolutions.
This commit modifies the `process_faces` method in both the `PhotoTagger` and `FaceProcessor` classes to accept an optional `limit` parameter. If `None`, all unprocessed photos will be processed, enhancing flexibility in face processing. Additionally, the `get_unprocessed_photos` method in `DatabaseManager` is updated to handle the optional limit, ensuring consistent behavior across the application. Docstrings have been updated to reflect these changes, improving code documentation and clarity.
This commit introduces a comprehensive EXIF orientation handling system to improve face processing accuracy. Key changes include the addition of an `exif_orientation` field in the database schema, updates to the `FaceProcessor` class for applying orientation corrections before face detection, and the implementation of a new `EXIFOrientationHandler` utility for managing image orientation. The README has been updated to document these enhancements, including recent fixes for face orientation issues and improved face extraction logic. Additionally, tests for EXIF orientation handling have been added to ensure functionality and reliability.
This commit refactors the handling of face location data to exclusively use the DeepFace format ({x, y, w, h}) instead of the legacy tuple format (top, right, bottom, left). Key changes include updating method signatures, modifying internal logic for face quality score calculations, and ensuring compatibility in the GUI components. Additionally, configuration settings for face detection have been adjusted to allow for smaller face sizes and lower confidence thresholds, enhancing the system's ability to detect faces in various conditions. All relevant tests have been updated to reflect these changes, ensuring continued functionality and performance.
This commit introduces significant enhancements to the face detection system, addressing false positives by updating configuration settings and validation logic. Key changes include stricter confidence thresholds, increased minimum face size, and improved aspect ratio requirements. A new script for cleaning up existing false positives from the database has also been added, successfully removing 199 false positive faces. Documentation has been updated to reflect these changes and provide usage instructions for the cleanup process.
This commit adds final notes to the migration documentation and quickstart files, confirming readiness for DeepFace implementation across all phases. The updates include completion confirmations in `DEEPFACE_MIGRATION_COMPLETE.md`, `PHASE1_COMPLETE.md`, `PHASE2_COMPLETE.md`, and `PHASE3_COMPLETE.md`, as well as quickstart notes in `.notes/phase1_quickstart.md` and `.notes/phase2_quickstart.md`. These changes ensure clarity on the project's progress and readiness for the next steps in the DeepFace integration.
This commit adds a quality filtering feature to the Identify Panel, allowing users to filter faces based on a quality score (0-100%). The `_get_unidentified_faces()` method has been updated to accept a `min_quality_score` parameter, and the SQL query now includes a WHERE clause for quality filtering. All relevant call sites have been modified to utilize this new feature, improving the user experience during face identification. The unique checkbox default state has also been confirmed to be unchecked, ensuring consistency in the UI behavior.
This commit introduces a quality filtering feature in the Identify Panel, allowing users to filter faces based on a quality score (0-100%). The panel now includes a slider for adjusting the quality threshold and displays the current quality percentage. Additionally, navigation functions have been updated to skip to the next or previous face that meets the quality criteria, improving the user experience during identification. The README has been updated to reflect these new features and enhancements.
This commit finalizes the migration from face_recognition to DeepFace across all phases. It includes updates to the database schema, core processing, GUI integration, and comprehensive testing. All features are now powered by DeepFace technology, providing superior accuracy and enhanced metadata handling. The README and documentation have been updated to reflect these changes, ensuring clarity on the new capabilities and production readiness of the PunimTag system. All tests are passing, confirming the successful integration.
This commit introduces several new files to enhance project organization and developer onboarding. The `.cursorignore` and `.cursorrules` files provide guidelines for Cursor AI, while `CONTRIBUTING.md` outlines contribution procedures. Additionally, `IMPORT_FIX_SUMMARY.md`, `RESTRUCTURE_SUMMARY.md`, and `STATUS.md` summarize recent changes and project status. The `README.md` has been updated to reflect the new project focus and structure, ensuring clarity for contributors and users. These additions aim to improve maintainability and facilitate collaboration within the PunimTag project.
