Aide
An App with Voice Assisted Image Captioning and VQA For Visually Challenged Individuals
Install / Use
/learn @J0SAL/AideREADME
AIDE
The aim of the application is to provide assistance to Visually Challenged Individuals with the power of image captioning and VQA (Visual Question Answering)!
App Can be downloaded from here
Publication IEEE
About
A mobile application built using MVP architecture in Flutter which leverages the power of image processing, and deep learning techniques to identify and describe the current scene through the camera and inform it to the user by audio cues. Added support for gesture controls like tap, double tap and long-press, for navigating through the app. Includes feature that allows the result be converted and read into multiple languages.
Features And Interfaces
-
Home Page with Inputs - takes image and (optional) question from the user.
- <img src="https://user-images.githubusercontent.com/52382282/177548148-c80cad98-e060-48fe-88b3-33448e26f1b9.png" alt="drawing" width="200" />
-
Output page - displays and speaks the answer to the question
- <img src="https://user-images.githubusercontent.com/52382282/177548498-cd873d06-06c0-4220-a378-c8e0f8c975df.png" alt="drawing" width="200" />
-
Output page - with translation
- <img src="https://user-images.githubusercontent.com/52382282/177548763-bf386550-e5cd-41ca-95a2-cd352bed6bf4.png" alt="drawing" width="200" />
Built with 🛠️
<p align="left"> <a href="https://flutter.dev/" target="_blank"> <code><img src="https://user-images.githubusercontent.com/52382282/177539764-0dfa07cf-0520-41c1-b796-3d46791c1c98.png" alt="flask" width="80" height="40"/></code> </a> <a href="https://flask.palletsprojects.com/en/2.1.x/" target="_blank"> <code><img src="https://user-images.githubusercontent.com/52382282/169838948-2289424c-0423-41db-9e42-b4e5a30f1c8e.png" alt="flask" width="80" height="40"/></code> </a> </p>Installation
To clone and run this repository you'll need Git and Flutter installed on your computer. From your command line:
# Clone this repository
git clone https://github.com/J0SAL/Aide.git
# Go into the repository
cd Aide
# Install packages
flutter pub get
# Run the app
flutter run
Developers Contact 📞
Related Skills
node-connect
354.5kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
112.4kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
354.5kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
354.5kQQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
