Comparison of Transfer Learning Algorithm Performance in Hand Sign Language Digits Image Classification

A. Muh. Amil Siddik

doi:10.20956/j.v20i1.26503

Authors

A. Muh. Amil Siddik Hasanuddin University https://orcid.org/0000-0002-5435-0642

DOI:

https://doi.org/10.20956/j.v20i1.26503

Keywords:

Transfer Learning, VGG-16, ResNet-50

Abstract

Image hand sign classification has become an interesting topic in image processing and machine learning. However, to achieve optimal performance in hand sign image classification tasks, a large and diverse dataset as well as powerful learning algorithms are required. One popular technique for improving the performance of classification models is transfer learning, which allows the use of knowledge learned from previous models and applies it to new tasks. In this study, the performance of two different transfer learning algorithms, ResNet-50 and VGG-16, was compared on the Sign Language Digits Dataset, which consists of 10 different types of handwriting images. The results of the experiment showed that both tested transfer learning algorithms had good performance. However, VGG-16 provided the best results with an accuracy of 97,29%, precision of 97,38%, recall of 97,45%, and an F1 score of 97,36%, while ResNet-50 achieved an accuracy of 94,57%, precision of 94,75%, recall of 94,96%, and an F1 score of 94,78%. In conclusion, transfer learning algorithms are effective techniques for improving the performance of hand sign image classification models. Choosing the appropriate transfer learning algorithm and dataset can help generate more accurate classification models.

Downloads

Download data is not yet available.

References

Guan, Q. Wang, Y., Ping, B., Li, D., Du, J., Qin, Yu, Lu, H., Wan, X. & J. Xiang. 2019. Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study. Journal of Cancer, Vol 10, No. 20, 4876-4882.

He, K., Zhang, X., Ren, S. & Sun, J., 2016. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Thn 2016, 770-778, Las Vegas, NV, USA.

Hijazi, S. L., Kumar, R. & Rowen, C., 2015. Using Convolutional Neural Networks for Image Recognition. Cadance, San Jose, CA, USA.

Kensert, A., Harrison, P. J. & Spjuth, O., 2019. Transfer Learning with Deep Convolutional Neural Networks for Classifying Cellular Morphological Changes. SLAS Discov., Vol 24, No. 4, 466-475.

Mascarenhas, S. & Agarwal, M., 2021. A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification. 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON). Thn 2021. 96-99. Bengaluru, India.

Mavi, A., 2011. A New Dataset and Proposed Convolutional Neural Network Architecture for Classification of American Sign Language Digits. ArXiv, abs/2011.08927.

Miranda, N., Novamizanti, L. & Rizal, S., 2020. CONVOLUTIONAL NEURAL NETWORK PADA KLASIFIKASI SIDIK JARI MENGGUNAKAN RESNET-50. Jurnal Teknik Informatika (Jutif), Vol 1, 61-68 .

Mustapha, A., Mohamed, L., Hamid, H. & Ali, K., 2021. Diabetic Retinopathy Classification Using ResNet50 and VGG-16 Pretrained Networks. International Journal of Computer Engineering and Data Science, Vol 1, No. 1, 1-7.

Perdana, I. P. I., Putra, I. K. G. D. & Dharmaadi, I. P. A., 2021. Classification of Sign Language Numbers Using the CNN Method. JITTER- Jurnal Ilmiah Teknologi dan Komputer, Vol 2, No.3, 485-493.

Rathi, P., Gupta, R., Agarwal, S. & Shukla, A., 2020. Sign Language Recognition Using ResNet50 Deep Neural Network Architecture. 5th International Conference on Next Generation Computing Technologies (NGCT-2019), 1-7. Uttarakhand, India.

Simonyan, K. & Zisserman, A., 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. 3rd International Conference on Learning Representations (ICLR 2015), Thn 2015, 1–14. California, US.

Stern, H., Shmueli, M. & Berman, S., 2010. Hand Gesture Classification. The 3rd Israeli Conference on Robotics. Thn 2010. Herzelia, Israel.

Suartika, I. W., Wijaya, A. Y. & Soelaiman, R., 2016. Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) pada Caltech 101. JURNAL TEKNIK ITS, Vol 5, No. 1, A65-A69.

Vatathanavaro, S., Tungjitnob, S. & Pasupa, K., 2018. White Blood Cell Classification: A Comparison between VGG-16 and ResNet-50 Models. The 6th Joint Symposium on Computational Intelligence (JSCI6). Thn 2018, 1-2. Bangkok, Thailand.

Wonohadidjojo, D. M., 2021. Perbandingan Convolutional Neural Network pada Transfer Learning Method untuk Mengklasifikasikan Sel Darah Putih. Jurnal Teknik Informatika, Vol 13, No. 1, 51-57.