{"id":21065238,"url":"https://github.com/rostyq/pico-detect","last_synced_at":"2025-05-16T02:33:14.799Z","repository":{"id":47147667,"uuid":"290151025","full_name":"rostyq/pico-detect","owner":"rostyq","description":"Rust library for Pixel Intensity Comparison-based Object (PICO) Detection.","archived":false,"fork":false,"pushed_at":"2024-05-14T13:22:00.000Z","size":1925,"stargazers_count":16,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-10T14:04:22.391Z","etag":null,"topics":["computer-vision","detection"],"latest_commit_sha":null,"homepage":"","language":"Rust","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/rostyq.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}},"created_at":"2020-08-25T07:53:43.000Z","updated_at":"2024-12-24T01:02:00.000Z","dependencies_parsed_at":"2024-11-19T18:04:47.960Z","dependency_job_id":null,"html_url":"https://github.com/rostyq/pico-detect","commit_stats":{"total_commits":94,"total_committers":3,"mean_commits":"31.333333333333332","dds":0.04255319148936165,"last_synced_commit":"0af7b52a383c6f27101ff09959a320907dc1acbf"},"previous_names":["rostyslavb/pico-detect"],"tags_count":7,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rostyq%2Fpico-detect","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rostyq%2Fpico-detect/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rostyq%2Fpico-detect/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rostyq%2Fpico-detect/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rostyq","download_url":"https://codeload.github.com/rostyq/pico-detect/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254456301,"owners_count":22074146,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["computer-vision","detection"],"created_at":"2024-11-19T17:54:30.774Z","updated_at":"2025-05-16T02:33:09.790Z","avatar_url":"https://github.com/rostyq.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![crates-badge]][crates]\n[![docs-badge]][docs]\n![license-badge]\n\n# pico-detect\n\nThis library is a reimplementation of _Pixel Intensity Comparison-based Object_ (PICO) detection algorithms in Rust:\n\n- `Detector`: Cascade of binary classifiers from [pico];\n- `Localizer`: Localization with an ensemble of randomized trees from [picojs](https://github.com/nenadmarkus/picojs) (see `lploc.js`);\n- `Shaper`: Alignment with an ensemble of regression trees from [dlib](https://github.com/davisking/dlib) (see `shape_predictor`).\n\n## Example\n\nTo run CLI example, which takes an image, finds all faces, detects some landmarks and pupils:\n\n\u003e **NOTE**: [Git LFS](https://git-lfs.github.com/) is needed to resolve binary files with `git clone`.\n\u003e\n\u003e If you don't want to use Git LFS you can download models (and test image) direct from this repo\n\u003e (see **model** column in the table below)\n\u003e and put them under [`models/`](./models) directory.\n\n```sh\ncargo run --release --example detect-faces -- --models-dir models -i \"assets/test.png\" --score 35.0 -o result.png\n```\n\nOutput image `result.png` should be like this:\n\n![visualization example](./assets/result.png)\n\n## Models\n\nEach algorithm requires to be loaded with correspondent binary model.\n\n| model                     | algorithm   | source                             | Description               |\n|---------------------------|-------------|------------------------------------|---------------------------|\n| [face.detector.bin]       | `Detector`  | [pico]                             | Human face classifier     |\n| [pupil.localizer.bin]     | `Localizer` | [puploc]                           | Human eye pupil localizer |\n| [face-5.shaper.bin]       | `Shaper`    | [shape_predictor_5_face_landmarks] | Human 5 face landmarks    |\n\n## References\n\n1. [N. Markus, M. Frljak, I. S. Pandzic, J. Ahlberg and R. Forchheimer, \"Object Detection with Pixel Intensity Comparisons Organized in Decision Trees\"](http://arxiv.org/abs/1305.4537)\n\n2. [Eye pupil localization with an ensemble of randomized trees](https://across.fer.hr/_download/repository/PR4885.pdf)\n\n3. [One Millisecond Face Alignment with an Ensemble of Regression Trees](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Kazemi_One_Millisecond_Face_2014_CVPR_paper.pdf)\n\n[crates]: https://crates.io/crates/pico-detect\n[docs]: https://docs.rs/pico-detect\n[docs-badge]: https://docs.rs/pico-detect/badge.svg\n[crates-badge]: https://img.shields.io/crates/v/pico-detect\n[license-badge]: https://img.shields.io/crates/l/pico-detect\n\n[pico]: https://github.com/nenadmarkus/pico\n\n[face.detector.bin]: https://github.com/rostyq/pico-detect/raw/master/models/face.detector.bin\n[pupil.localizer.bin]: https://github.com/rostyq/pico-detect/raw/master/models/pupil.localizer.bin\n[face-5.shaper.bin]: https://github.com/rostyq/pico-detect/raw/master/models/face-5.shaper.bin\n\n[puploc]: https://drone.nenadmarkus.com/data/blog-stuff/puploc.bin\n[shape_predictor_5_face_landmarks]: https://github.com/davisking/dlib-models#shape_predictor_5_face_landmarksdatbz2\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frostyq%2Fpico-detect","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frostyq%2Fpico-detect","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frostyq%2Fpico-detect/lists"}