Segment anything: real-time AI model interaction and visualization

This Final Year Project focuses on the design and development of a segmentation AI service that offers users an intuitive interface for real-time mask prediction and selection. This service utilizes the cutting-edge Segment Anything Model(SAM) from the Meta AI research team, finally integrated into...

Full description

Bibliographic Details
Main Author: Wang, Jingwei
Other Authors: Chen Change Loy
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175023
Description
Summary:This Final Year Project focuses on the design and development of a segmentation AI service that offers users an intuitive interface for real-time mask prediction and selection. This service utilizes the cutting-edge Segment Anything Model(SAM) from the Meta AI research team, finally integrated into Image-Pro, a platform developed by research engineers at S-lab. This paper begins with an introduction to SAM, highlighting its applicability in web development. It then progresses through the software development lifecycle, including stages of requirements analysis, system design, and implementation.