Enhanced Hand Segmentation Using UNet: A Comparative Study with Classical Approaches

Q: How many days will it take for my paper to be published?

The review time for papers is not fixed. However, if the paper is accepted and the author completes the processing charges formalities, the paper will be published within a few working days.

Q: I would like to receive a hard copy of the journal materials. Are there any additional charges?

You can log in to the author portal and pay 500 INR to receive the hard copy materials.

Remya PK; Rajkumar KK

Enhanced Hand Segmentation Using UNet: A Comparative Study with Classical Approaches

Authors: Remya PK, Rajkumar KK

Unique Paper ID: 182990
Volume: 12
Issue: no
PageNo: 99-105

Keywords: Hand Segmentation Deep Learning UNet Gesture Recognition Mudra Classification

Abstract:
The segmentation of hand gestures from complex backgrounds is essential for accurately classifying classical dance movements, as it enhances feature extraction and recognition performance. This paper presents a robust segmentation framework based on the UNet architecture, a deep learning model well-suited for pixel-wise segmentation. Initially, various traditional segmentation techniques are analyzed and evaluated; among them, UNet demonstrates superior performance in handling the complexity of classical dance gestures. The proposed method consists of two main stages: developing a UNet-based model for hand segmentation and refining it to capture the intricate and expressive movements characteristic of classical dance. The model is trained on a carefully curated dataset featuring diverse hand shapes, skin tones, and poses to ensure strong generalization. Post-segmentation, feature extraction is optimized to focus on the most relevant elements for classification. Robustness and adaptability are further improved using data augmentation and transfer learning techniques. Experimental results show that the proposed system surpasses existing methods in accuracy, real-time performance, and resilience under varying conditions. Applications include real-time gesture recognition in classical dance training, augmented reality, and enhanced human-computer interaction.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 12
Issue: no
PageNo: 99-105

Enhanced Hand Segmentation Using UNet: A Comparative Study with Classical Approaches

Available:https://ijirt.org/article?manuscript=182990

30 Jul, 2025

A Literature Review on Automated Detection of Epileptic Seizures using Machine learning & Deep Learning Techniques

28 Jul, 2025

Enhancing Banana Leaf Disease Diagnosis Using Explainable AI on a Simple Convolutional Neural Network

25 Jul, 2025

Integrated Hydroponics

25 Jul, 2025

CNN-Based Novel Deep Learning Ensemble Model for Kathakali Hand Mudra Recognition and Classification

25 Jul, 2025

Vehicle Event Data Recorder and Driver Review System (VEDRAR) Using Machine Learning

25 Jul, 2025

Memory-Aware Scheduling in Constrained Environments

25 Jul, 2025

Interpretable Deep Learning for Biological Age Prediction: A Counterfactual Approach to Personalized Health Insights

24 Jul, 2025

Colored Chain: A Blockchain Based Supply Chain System

24 Jul, 2025

Contemporaneous Secured Information Transfer by using Extended and Modified RSA Cryptosystem

24 Jul, 2025

Deep Learning-Based Gesture Recognition for Computer Vision Applications

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now