Mobile-SAM in everyday object recognition application

• Main Author: Chen, Xiangyu
• Other Authors: Lin Guosheng
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science
• Online Access: https://hdl.handle.net/10356/175953
• Institution: Nanyang Technological University

The digital transformation of educational tools has opened avenues to enhance cognitive development in children, particularly in recognizing and naming everyday objects. The development of the application aims to utilise the advancements of Computer Vision (CV) and Segment Anything Model (SAM) to create a more interactive and technologically enriching experience for children. This project will integrate SAM, specifically MobileSAM variant that is optimized for mobile platforms, and GroundingDino framework to deliver an engaging user interface. The project is also backed by extensive research and testing to select the most suitable CV model, ensuring a seamless interaction with real time image processing capabilities.