TY - GEN
T1 - Hand Gesture Recognition with Deep Convolutional Neural Networks: A Comparative Study
AU - Chong, You Li
AU - Lee, Chin Poo
AU - Lim, Kian Ming
AU - Lim, Jit Yan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Hand gesture recognition is a growing field with applications in human-computer interaction, sign language interpretation, and virtual/augmented reality. The use of convolutional neural networks (CNNs) has become prevalent in this field as they possess the capability to autonomously extract relevant features from image data, facilitating precise and effective hand gesture recognition. This paper presents a comparison of popular pretrained CNN models for hand gesture recognition, evaluating their performance on three widely used datasets: the American Sign Language (ASL) dataset, ASL with Digits dataset, and NUS Hand Posture dataset. The models were fine-tuned and tested, and the analysis included accuracy, training epoch, and training time. The pretrained CNN models compared include VGG16, ResNet50, InceptionV3, DenseNet201, MobileNetV2, Inception ResNetV2, Xception, and ResNet50V2. The findings of this research can provide valuable insights into choosing an appropriate pretrained CNN model for applications involving hand gesture recognition.
AB - Hand gesture recognition is a growing field with applications in human-computer interaction, sign language interpretation, and virtual/augmented reality. The use of convolutional neural networks (CNNs) has become prevalent in this field as they possess the capability to autonomously extract relevant features from image data, facilitating precise and effective hand gesture recognition. This paper presents a comparison of popular pretrained CNN models for hand gesture recognition, evaluating their performance on three widely used datasets: the American Sign Language (ASL) dataset, ASL with Digits dataset, and NUS Hand Posture dataset. The models were fine-tuned and tested, and the analysis included accuracy, training epoch, and training time. The pretrained CNN models compared include VGG16, ResNet50, InceptionV3, DenseNet201, MobileNetV2, Inception ResNetV2, Xception, and ResNet50V2. The findings of this research can provide valuable insights into choosing an appropriate pretrained CNN model for applications involving hand gesture recognition.
KW - Convolution Neural Network (CNN)
KW - Sign Language Recognition
KW - Static Hand Gesture Recognition
KW - Transfer Learning
UR - http://www.scopus.com/inward/record.url?scp=85186664657&partnerID=8YFLogxK
U2 - 10.1109/ICSPC59664.2023.10419918
DO - 10.1109/ICSPC59664.2023.10419918
M3 - Conference Proceeding
AN - SCOPUS:85186664657
T3 - 2023 IEEE 11th Conference on Systems, Process and Control, ICSPC 2023 - Proceedings
SP - 60
EP - 65
BT - 2023 IEEE 11th Conference on Systems, Process and Control, ICSPC 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th IEEE Conference on Systems, Process and Control, ICSPC 2023
Y2 - 16 December 2023
ER -