Interactive Image Segmentation Using Segment Anything Model (SAM) with Vision Transformer (ViT-H) and Web-Based Interface

Satyaki Bhattacharya; Sohalia Sana; Shreya Ranjan; Shruti Sinha; Shreya Gupta; Sakshi Prakash

Interactive Image Segmentation Using Segment Anything Model (SAM) with Vision Transformer (ViT-H) and Web-Based Interface

Author(s)	Mr. Satyaki Bhattacharya, Ms. Sohalia Sana, Ms. Shreya Ranjan, Ms. Shruti Sinha, Ms. Shreya Gupta, Ms. Sakshi Prakash
Country	India
Abstract	Image segmentation plays a crucial role in computer vision applications such as medical imaging, autonomous systems, and object detection. Traditional segmentation techniques often require extensive training and large annotated datasets, making them resource-intensive and less flexible. This study presents an interactive image segmentation system based on the Segment Anything Model (SAM) integrated with a Vision Transformer (ViT-H) backbone. The proposed system allows users to provide point-based prompts to guide segmentation, improving accuracy and usability. A web-based interface is developed using Streamlit to enable real-time interaction and visualization of segmentation results. The model demonstrates strong generalization capability across diverse images without task-specific retraining. Experimental observations indicate that the approach delivers efficient and high-quality segmentation outputs, making it suitable for practical applications. The integration of deep learning with an intuitive interface enhances accessibility for users with minimal technical expertise.
Keywords	Image Segmentation, Segment Anything Model, Vision Transformer, SAM, Deep Learning, Computer Vision, Interactive Segmentation, Streamlit
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-29

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Interactive Image Segmentation Using Segment Anything Model (SAM) with Vision Transformer (ViT-H) and Web-Based Interface

Share this