Small-Scale Deep Network for DCT-Based Images Classification

B. Borhanuddin, N. Jamil, S. D. Chen, M. Z. Baharuddin, K. S.Z. Tan, T. W.M. Ooi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The need to acquire high performance deep neural network models is a research trend in recent years. Many examples have shown that achieving high validation accuracies require a very large number of parameters in most cases and therefore, the space used to store these models becomes very large. This may be a disadvantage on small storage size and low performance CPU edge devices during image processing that are embedded with neural networks for object recognition tasks. In this paper, we investigate the effect of input images which are partially compressed using the Discrete Cosine Transform (DCT) algorithm on two different Convolutional Neural Network (CNN) performances, known as CNN-C (large model) and CNN-RC3 (small model). DCT is used to reduce some data redundancies but also the risk of losing valuable features for the network to learn efficiently. However, the results show that both CNN architectures with DCT features perform as well as with raw image data, concluding that a properly designed CNN model can still achieve high performance on further compressed images regardless of its information reductions.

Original languageEnglish
Title of host publicationICRAIE 2019 - 4th International Conference and Workshops on Recent Advances and Innovations in Engineering
Subtitle of host publicationThriving Technologies
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728126104
DOIs
Publication statusPublished - Nov 2019
Event4th International Conference and Workshops on Recent Advances and Innovations in Engineering, ICRAIE 2019 - Kedah, Malaysia
Duration: 28 Nov 201929 Nov 2019

Publication series

NameICRAIE 2019 - 4th International Conference and Workshops on Recent Advances and Innovations in Engineering: Thriving Technologies

Conference

Conference4th International Conference and Workshops on Recent Advances and Innovations in Engineering, ICRAIE 2019
CountryMalaysia
CityKedah
Period28/11/1929/11/19

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'Small-Scale Deep Network for DCT-Based Images Classification'. Together they form a unique fingerprint.

  • Cite this

    Borhanuddin, B., Jamil, N., Chen, S. D., Baharuddin, M. Z., Tan, K. S. Z., & Ooi, T. W. M. (2019). Small-Scale Deep Network for DCT-Based Images Classification. In ICRAIE 2019 - 4th International Conference and Workshops on Recent Advances and Innovations in Engineering: Thriving Technologies [9037777] (ICRAIE 2019 - 4th International Conference and Workshops on Recent Advances and Innovations in Engineering: Thriving Technologies). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRAIE47735.2019.9037777