{"id":51185951,"url":"https://github.com/vevdokimovm/iris-recognition","last_synced_at":"2026-06-27T10:02:19.144Z","repository":{"id":115799010,"uuid":"319687775","full_name":"vevdokimovm/iris-recognition","owner":"vevdokimovm","description":"Iris-based biometric identification system using classical CV pipeline: localization, normalization, LDA matching","archived":false,"fork":false,"pushed_at":"2026-04-20T20:29:47.000Z","size":11260,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-20T22:32:01.133Z","etag":null,"topics":["biometrics","computer-vision","lda","machine-learning","opencv","python"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vevdokimovm.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-12-08T15:55:14.000Z","updated_at":"2026-04-20T20:43:49.000Z","dependencies_parsed_at":"2023-11-16T22:08:52.731Z","dependency_job_id":null,"html_url":"https://github.com/vevdokimovm/iris-recognition","commit_stats":null,"previous_names":["vevdokimovm/human-identification-by-the-iris","vevdokimovm/iris-recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vevdokimovm/iris-recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vevdokimovm%2Firis-recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vevdokimovm%2Firis-recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vevdokimovm%2Firis-recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vevdokimovm%2Firis-recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vevdokimovm","download_url":"https://codeload.github.com/vevdokimovm/iris-recognition/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vevdokimovm%2Firis-recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34848932,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-27T02:00:06.362Z","response_time":126,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["biometrics","computer-vision","lda","machine-learning","opencv","python"],"created_at":"2026-06-27T10:02:16.874Z","updated_at":"2026-06-27T10:02:19.122Z","avatar_url":"https://github.com/vevdokimovm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Human Identification by the Iris\n\nA Python implementation of an iris-based biometric recognition system using classical computer vision and machine learning (LDA). Built on top of the CASIA iris dataset.\n\n\u003e Based on: [smahesh29/OpenCV-Face-and-Eye-Detection](https://github.com/smahesh29/OpenCV-Face-and-Eye-Detection) and [akshatapatel/Iris-Recognition](https://github.com/akshatapatel/Iris-Recognition), modified for custom tasks.\n\n## Pipeline\n\n1. **Iris Localization** — detect and extract the iris region from eye images\n2. **Iris Normalization** — unwrap iris to a fixed-size rectangular representation\n3. **Image Enhancement** — improve contrast and quality for feature extraction\n4. **Feature Extraction** — extract discriminative features using 1D Log-Gabor filters\n5. **Iris Matching** — compare feature vectors using distance metrics\n6. **Performance Evaluation** — compute recognition accuracy metrics\n\n## Tech Stack\n\n- Python 3.x\n- OpenCV — image processing and face/eye detection\n- NumPy, SciPy — numerical computations\n- scikit-learn (LDA) — dimensionality reduction and matching\n- Matplotlib — visualization\n- Pandas — data handling\n\n## Dataset\n\nThe project uses the [CASIA Iris Database](http://www.cbsr.ia.ac.cn/english/IrisDatabase.asp). Images should be placed in:\n\n```\nEyes/\n├── 001/\n│   ├── 001_1_1.jpg   # training images (*_1_*)\n│   ├── 001_2_1.jpg   # test images (*_2_*)\n│   └── ...\n├── 002/\n└── ...\n```\n\n## Getting Started\n\n### Installation\n\n```bash\ngit clone https://github.com/vevdokimovm/Human-Identification-by-the-Iris.git\ncd Human-Identification-by-the-Iris\npip install -r requirements.txt\n```\n\n### Run\n\n```bash\npython IrisRecognition.py\n```\n\nFor real-time face/eye detection from camera:\n\n```bash\npython face_eye_detection_image.py\n```\n\n## Project Structure\n\n```\nHuman-Identification-by-the-Iris/\n├── IrisLocalization.py       # Iris boundary detection\n├── IrisNormalization.py      # Daugman rubber sheet model\n├── ImageEnhancement.py       # Histogram equalization\n├── FeatureExtraction.py      # Log-Gabor feature extraction\n├── IrisMatching.py           # Feature comparison\n├── PerformanceEvaluation.py  # Accuracy metrics\n├── IrisRecognition.py        # Main pipeline\n├── face_eye_detection_image.py  # Real-time detection\n├── haarcascade_*.xml         # Pre-trained Haar cascades\n├── Eyes/                     # Training/test dataset\n└── New_people/               # New subject images\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvevdokimovm%2Firis-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvevdokimovm%2Firis-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvevdokimovm%2Firis-recognition/lists"}