{"id":23406961,"url":"https://github.com/hs094/instance-segmentation-and-detection","last_synced_at":"2026-05-02T02:39:06.002Z","repository":{"id":265641277,"uuid":"896391961","full_name":"hs094/Instance-Segmentation-and-Detection","owner":"hs094","description":"A sophisticated computer vision application that performs real-time instance segmentation and object detection using a user-friendly Tkinter interface. The project identifies and isolates individual objects within images, providing both bounding box visualization and segmentation masks.","archived":false,"fork":false,"pushed_at":"2025-01-26T10:51:43.000Z","size":3357,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-09T00:07:18.711Z","etag":null,"topics":["matplotlib","opencv","pillow","setuptools","tkinter-gui","torch","torchvision"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hs094.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-11-30T08:33:10.000Z","updated_at":"2025-01-26T10:51:47.000Z","dependencies_parsed_at":"2025-02-14T18:48:00.740Z","dependency_job_id":"6dded11d-33d9-4258-a2f6-b8d600fd91e5","html_url":"https://github.com/hs094/Instance-Segmentation-and-Detection","commit_stats":null,"previous_names":["hs094/instance-segmentation-and-detection"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hs094%2FInstance-Segmentation-and-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hs094%2FInstance-Segmentation-and-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hs094%2FInstance-Segmentation-and-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hs094%2FInstance-Segmentation-and-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hs094","download_url":"https://codeload.github.com/hs094/Instance-Segmentation-and-Detection/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247947859,"owners_count":21023066,"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":["matplotlib","opencv","pillow","setuptools","tkinter-gui","torch","torchvision"],"created_at":"2024-12-22T14:16:29.391Z","updated_at":"2026-05-02T02:39:05.967Z","avatar_url":"https://github.com/hs094.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Instance Segmentation and Detection using a Tkinter-based interface\nThis project is a sophisticated computer vision application that performs real-time instance segmentation and object detection using a user-friendly Tkinter interface. The project identifies and isolates individual objects within images, providing both bounding box visualization and segmentation masks.\n\n## Key Features\n- Interactive GUI built with Tkinter for easy image processing\n- Detects and highlights the top 3 most confident object instances\n- Dual visualization modes:\n  - Bounding box detection with class labels\n  - Precise segmentation masks with custom color overlays\n- Supports multiple image transformations:\n  - Blur\n  - Flip (horizontal/vertical)\n  - Rotate\n  - Crop (center/random)\n  - Rescale\n\n## Technical Highlights\n- Built on PyTorch's powerful deep learning framework\n- Efficient image processing using NumPy and PIL\n- Custom transformation pipeline for image preprocessing\n- Confidence-based filtering for optimal detection results\n- Clean architecture with modular design for easy extensibility\n## Use Cases\n- Object detection in natural scenes\n- Instance segmentation for image analysis\n- Educational tool for computer vision concepts\n- Rapid prototyping of image processing workflows\n\n## Dependencies\n1. PyTorch\n  `pip3 install torch torchvision torchaudio`\n2. Numpy\n  `pip3 install numpy`\n3. Matplotlib\n  `pip3 install matplotlib`\n4. Pillow\n  `pip3 install pillow`\n5. mypackage-hs094\n  `pip3 install ./my_package_hs094-0.0.1-py3-none-any.whl`\n\n### Notes\n1. This software determines only the top 3 entities in the given image based on a confidence score. Other detected entities are not covered by segmentation masks or bounding boxes.\n2. Temporary image files (1 for bounding box and 1 for segmentation mask) are saved to disk in the working directory during the runtime of the script. It is destroyed automatically afterwards.\n\n## Screenshots\n![error](Screenshots/error.png)\n\n![bbox1](Screenshots/bbox1.png)\n\n![mask1](Screenshots/mask1.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhs094%2Finstance-segmentation-and-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhs094%2Finstance-segmentation-and-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhs094%2Finstance-segmentation-and-detection/lists"}