Hand Gesture Recognition Using Deep Learning

EasyChair Preprint 13291

Abstract

A vital component of human-computer interaction, hand gesture recognition has applications in a wide range of industries, including virtual reality, robotics, healthcare, and sign language translation. However, extensively annotated datasets and substantial computational resources are frequently needed for training deep learning models for hand gesture detection from scratch. By using the information that pre-trained models have gained from working with huge datasets and tailoring it to specific tasks using smaller datasets, Deep learning proves to be a potent way to address these issues. This work presents a thorough analysis of Deep  learning methods used in hand gesture detection tasks, emphasizing their effectiveness, drawbacks, and potential applications. The key components of this approach include data acquisition, pre-processing, model selection, and evaluation. The proposed approach was evaluated using various metrics, including accuracy, precision, recall, and F1 score. The results demonstrated that Deep learning significantly enhanced the models' ability to differentiate between healthy and diseased leaves, with high accuracy and reduced false positives. Moreover, the model's ability to generalize across different plant species and disease types was assessed, highlighting its versatility.

Keyphrases: Computer Science, Hand Gesture Recognition, Hand gesture image dataset, Indian Sign Language(ISL), Machine learning for human interaction, ResNet-50, VGG16, deep learning

@booklet{EasyChair:13291,
  author    = {I Hemanth and P Siva Prasad},
  title     = {Hand Gesture Recognition Using Deep Learning},
  howpublished = {EasyChair Preprint 13291},
  year      = {EasyChair, 2024}}