Small-Scale Deep Network for DCT-Based Images Classification
Convolutional neural networks; Deep neural networks; Digital storage; Discrete cosine transforms; Image classification; Image coding; Object recognition; Compressed images; Data redundancy; Discrete Cosine Transform(DCT); Images classification; Information reduction; Neural network model; Raw image...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Tenaga Nasional |
| id |
my.uniten.dspace-24290 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-242902023-05-29T15:22:37Z Small-Scale Deep Network for DCT-Based Images Classification Borhanuddin B. Jamil N. Chen S.D. Baharuddin M.Z. Tan K.S.Z. Ooi T.W.M. 57200577946 36682671900 7410253413 35329255600 57216334027 57193722449 Convolutional neural networks; Deep neural networks; Digital storage; Discrete cosine transforms; Image classification; Image coding; Object recognition; Compressed images; Data redundancy; Discrete Cosine Transform(DCT); Images classification; Information reduction; Neural network model; Raw image data; Research trends; Image compression 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. � 2019 IEEE. Final 2023-05-29T07:22:37Z 2023-05-29T07:22:37Z 2019 Conference Paper 10.1109/ICRAIE47735.2019.9037777 2-s2.0-85083179653 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083179653&doi=10.1109%2fICRAIE47735.2019.9037777&partnerID=40&md5=b7685dd07d0106c3f165c3ea29b11981 https://irepository.uniten.edu.my/handle/123456789/24290 9037777 Institute of Electrical and Electronics Engineers Inc. Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Convolutional neural networks; Deep neural networks; Digital storage; Discrete cosine transforms; Image classification; Image coding; Object recognition; Compressed images; Data redundancy; Discrete Cosine Transform(DCT); Images classification; Information reduction; Neural network model; Raw image data; Research trends; Image compression |
| author2 |
57200577946 |
| author_facet |
57200577946 Borhanuddin B. Jamil N. Chen S.D. Baharuddin M.Z. Tan K.S.Z. Ooi T.W.M. |
| format |
Conference Paper |
| author |
Borhanuddin B. Jamil N. Chen S.D. Baharuddin M.Z. Tan K.S.Z. Ooi T.W.M. |
| spellingShingle |
Borhanuddin B. Jamil N. Chen S.D. Baharuddin M.Z. Tan K.S.Z. Ooi T.W.M. Small-Scale Deep Network for DCT-Based Images Classification |
| author_sort |
Borhanuddin B. |
| title |
Small-Scale Deep Network for DCT-Based Images Classification |
| title_short |
Small-Scale Deep Network for DCT-Based Images Classification |
| title_full |
Small-Scale Deep Network for DCT-Based Images Classification |
| title_fullStr |
Small-Scale Deep Network for DCT-Based Images Classification |
| title_full_unstemmed |
Small-Scale Deep Network for DCT-Based Images Classification |
| title_sort |
small-scale deep network for dct-based images classification |
| publisher |
Institute of Electrical and Electronics Engineers Inc. |
| publishDate |
2023 |
| _version_ |
1806424440165105664 |