DHGNet: Devatha Hastha Gesture Network with Advanced Graph Enhancement for Gesture Identification and Recognition

Abstract

This study aims to develop an AI-powered system to classify and interpret Devatha Hasthas in Indian classical dance. By combining cultural preservation with modern technology, the system enhances accessibility and supports effective learning and documentation of intricate hand gestures, contributing to the promotion and understanding of traditional art forms. The study utilized a dataset of 16 Devatha Hasthas, MediaPipe hand tracking for segmentation, and feature extraction combining Hu moments and VGG19. Dimensionality reduction was performed using an ExtraTree classifier, followed by gesture classification through a Dense Neural Network. A Neo4j graph database was used for structured visualization and interaction. The system achieved an impressive classification accuracy of 96%, highlighting its effectiveness in accurately identifying Devatha Hasthas. Additionally, the integration of Neo4j graph database provided insightful interpretations of gesture relationships, demonstrating the potential of graph-based modeling to enhance the analysis of gesture interactions and cultural dynamics in classical dance. This study holds significant value for fields such as gesture recognition, AI, cultural heritage preservation, dance education, and digital humanities. By bridging traditional art forms with modern technologies, it empowers researchers, educators, and practitioners to enhance learning, fostering a deeper connection between cultural traditions and innovative technological advancements. This study introduces a novel integration of AI, deep learning, and graph-based modeling to interpret classical dance gestures, providing fresh perspectives on gesture interactions. It enhances current knowledge by bridging traditional art forms with advanced technologies, opening new possibilities for cultural studies, gesture recognition, and innovative approaches to preserving and learning intricate dance traditions.