{"id":27278946,"url":"https://github.com/ambrish8/bell-s-palsy","last_synced_at":"2026-04-15T05:32:00.418Z","repository":{"id":287377560,"uuid":"964529933","full_name":"Ambrish8/Bell-s-Palsy","owner":"Ambrish8","description":"BELL’S PALSY SEVERITY DETECTION USING DEEP LEARNING","archived":false,"fork":false,"pushed_at":"2025-04-11T11:14:52.000Z","size":1198,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-11T12:53:24.774Z","etag":null,"topics":["cnn-architecture","imagedatagenerator","keras","numpy","opencv","python","pytorch","resnet-50"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Ambrish8.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,"zenodo":null}},"created_at":"2025-04-11T11:05:18.000Z","updated_at":"2025-04-11T11:23:32.000Z","dependencies_parsed_at":"2025-04-11T12:53:27.480Z","dependency_job_id":"f9744588-4599-4353-8e8e-32c2fb442b7f","html_url":"https://github.com/Ambrish8/Bell-s-Palsy","commit_stats":null,"previous_names":["ambrish8/bell-s-palsy"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ambrish8%2FBell-s-Palsy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ambrish8%2FBell-s-Palsy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ambrish8%2FBell-s-Palsy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ambrish8%2FBell-s-Palsy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ambrish8","download_url":"https://codeload.github.com/Ambrish8/Bell-s-Palsy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248453333,"owners_count":21106239,"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":["cnn-architecture","imagedatagenerator","keras","numpy","opencv","python","pytorch","resnet-50"],"created_at":"2025-04-11T17:46:05.855Z","updated_at":"2026-04-15T05:32:00.365Z","avatar_url":"https://github.com/Ambrish8.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Bell-s-Palsy\nBell’s Palsy is a neurological disorder that causes sudden, temporary weakness\nor paralysis of the facial muscles, impacting one side of the face. Early and\naccurate severity detection of Bell’s Palsy is crucial for effective treatment and\nrecovery. This project aims to develop an automated severity detection system\nfocusing on key facial features—eyebrows, eyes, and mouth—using deep\nlearning techniques.\nWe utilize ResNet, a powerful deep convolutional neural network (CNN), to\nclassify Bell’s Palsy severity into four categories: mild, moderate, moderate\nsevere, and severe. The dataset consists of annotated facial images,\npreprocessed with data augmentation techniques such as rotation, zooming, and\nflipping to improve model robustness. The dataset is split into training,\nvalidation, and testing sets for effective model training and evaluation.\nThe model is fine-tuned using transfer learning, leveraging a pre-trained\nResNet model while modifying its classifier to suit our classification task. The\ntraining process is carried out on Google Colab, using an Adam optimizer and\ncross-entropy loss function. The model’s performance is evaluated using\naccuracy and loss metrics on the test dataset.\nBy automating the severity assessment of Bell’s Palsy, this project offers a fast,\naccurate, and scalable solution to assist medical professionals in early diagnosis\nand treatment planning. The system can potentially be integrated into mobile\napplications or telemedicine platforms, improving healthcare accessibility for\npatients in remote areas.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fambrish8%2Fbell-s-palsy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fambrish8%2Fbell-s-palsy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fambrish8%2Fbell-s-palsy/lists"}