An iOS app for Artwork detection using Apple CoreML and Apple Vision and integrated with Apple VoiceOver and Accessibility Tools, meant to help blind users navigate art museums

ArtSpeakv2 is a SwiftUI-based iOS application designed to explore artworks, listen to their descriptions, capture images, and perform visual lookups using Core ML models.

ArtSpeak utilizes the YOLOv3 model to recognize artworks and generate descriptions. YOLOv3 is an iteration of the famous YOLO models that revolutionized Computer Vision. Here I use it to detect artworks from camera images and then perform a visual lookup.

Read more on YOLOv3: YOLOv3 is an incremental step forward

• Artwork Exploration: Browse artworks categorized into different rooms.
• Audio Descriptions: Listen to detailed descriptions of artworks using text-to-speech.
• Image Capture: Capture images using the integrated camera functionality.
• Visual Lookup: Utilize Core ML models for object detection and description of captured images.

1. Clone the repository:

   git clone https://github.com/your_username/ArtSpeakv2.git
   

2. Open the project in Xcode.

3. Build and run the app on a simulator or iOS device.

• Navigate through different rooms to view artworks.
• Tap on an artwork to view its detailed description.
• Use buttons to listen to audio descriptions or capture images.
• Explore captured images with visual lookup capabilities.

Contributions are welcome! Please feel free to submit issues and pull requests.

• Inspired by the beauty of artworks and the potential of SwiftUI.
• Special thanks to contributors and open-source libraries used in this project.
• This is a project for social good, if you have any similar ideas, please contact.