{"id":15159387,"url":"https://github.com/neural-nuts/cam2caption","last_synced_at":"2025-09-30T09:31:01.873Z","repository":{"id":215186804,"uuid":"108535294","full_name":"neural-nuts/Cam2Caption","owner":"neural-nuts","description":"[DEPRECATED] An Android application which converts camera feed to captions in real time","archived":true,"fork":false,"pushed_at":"2018-02-02T14:33:08.000Z","size":31832,"stargazers_count":53,"open_issues_count":5,"forks_count":18,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-09-27T21:20:59.292Z","etag":null,"topics":["android-application","convolutional-neural-networks","image-captioning","recurrent-neural-networks","tensorflow-android","tensorflow-models"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/neural-nuts.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}},"created_at":"2017-10-27T10:58:38.000Z","updated_at":"2024-05-14T07:16:11.000Z","dependencies_parsed_at":"2024-01-03T03:28:11.998Z","dependency_job_id":null,"html_url":"https://github.com/neural-nuts/Cam2Caption","commit_stats":null,"previous_names":["neural-nuts/cam2caption"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neural-nuts%2FCam2Caption","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neural-nuts%2FCam2Caption/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neural-nuts%2FCam2Caption/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neural-nuts%2FCam2Caption/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/neural-nuts","download_url":"https://codeload.github.com/neural-nuts/Cam2Caption/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234722055,"owners_count":18876896,"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":["android-application","convolutional-neural-networks","image-captioning","recurrent-neural-networks","tensorflow-android","tensorflow-models"],"created_at":"2024-09-26T21:20:36.780Z","updated_at":"2025-09-30T09:30:52.910Z","avatar_url":"https://github.com/neural-nuts.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cam2Caption\nAn Android application which converts camera feed to natural language captions in real time.\nThe app uses our customized pre-trained model generated through [image-caption-generator](https://github.com/neural-nuts/image-caption-generator). \nUsing this model the app takes **1-2 second(s)** to caption a live camera frame on Huawei Honor 6x.\n\nThe trained model to run this app can be obtained [here](https://drive.google.com/open?id=0ByhzM2YklhADNmk4cEN2MTA5U0E).\n\n## Software Pre-Requisites\n1. Android-Sdk for \u003e Kitkat\n2. Android-Studio\n3. Tensorflow Java Library\n    - Already provided build #44 in this repository. Latest nightly builds can be obtained frome [here](https://ci.tensorflow.org/view/Nightly/job/nightly-android/)\n    - **Warning**: Did not test this app with builds other that #44\n\n## Data Pre-Requisites\n1. Trained model from [image-caption-generator](https://github.com/neural-nuts/image-caption-generator)\n2. Word IDs to Word map pickle from [image-caption-generator](https://github.com/neural-nuts/image-caption-generator) currently provided in `Application/src/main/assets`\n\n## Instructions\nTo build this app for your android phone-\n1. Clone this repository\n2. Download the trained model from [here](https://drive.google.com/open?id=0ByhzM2YklhADNmk4cEN2MTA5U0E).\n3. Add the downloaded pre-trained model to `Application/src/main/assets` folder in the repository.\n4. Open the repository in Android Studio\n5. Build the app on your device using Android Studio\n\n## Working\nThe app is just a prototype, which uses our optimized and skimmed-down model from [image-caption-generator](https://github.com/neural-nuts/image-caption-generator), we also use a faster encoder CNN- Google's Inception v4.and finally use an end-to-end pre-trained model as balackbox in this app for quickly generating captions in real time.\n\nNote: Due to lack of computation power our model is not very well trained.\n\n## Preview\nHere is a quick preview of the app which was made by pointing the device camera towards a slideshow running on a screen and some real-life scenes. \n#TO-DO: Create a real preview by testing the app on streets.\n\n\u003ca href=\"url\"\u003e\u003cimg src=\"https://github.com/neural-nuts/Cam2Caption/blob/master/preview.gif\" align=\"left\" height=\"600\" width=\"350\" \u003e\u003c/a\u003e\n\n## Notes\n1. To create a tensorflow android app from scratch please follow this brilliant [tutorial](https://omid.al/posts/2017-02-20-Tutorial-Build-Your-First-Tensorflow-Android-App.html) by Omid Alemi.\n2. Currently the app is tested for Huawei Honor 6x only.\n\n## Citation\n\nIf you use our model or code in your research, please cite the paper:\n\n```\n@article{Mathur2017,\n  title={Camera2Caption: A Real-time Image Caption Generator},\n  author={Pranay Mathur and Aman Gill and Aayush Yadav and Anurag Mishra and Nand Kumar Bansode},\n  journal={IEEE Conference Publication},\n  year={2017}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneural-nuts%2Fcam2caption","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fneural-nuts%2Fcam2caption","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneural-nuts%2Fcam2caption/lists"}