- Title
- Distortion robust image classification using deep convolutional neural network with discrete cosine transform
- Creator
- Hossain, Md Tahmid; Teng, Shyh Wei; Zhang, Dengsheng; Lim, Suryani; Lu, Guojun
- Date
- 2019
- Type
- Text; Conference proceedings
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/180831
- Identifier
- vital:15814
- Identifier
-
https://doi.org/10.1109/ICIP.2019.8803787
- Identifier
- ISBN:978-3-030-34878-6
- Abstract
- Convolutional Neural Networks are highly effective for image classification. However, it is still vulnerable to image distortion. Even a small amount of noise or blur can severely hamper the performance of these CNNs. Most work in the literature strives to mitigate this problem simply by fine-tuning a pre-trained CNN on mutually exclusive or a union set of distorted training data. This iterative fine-tuning process with all known types of distortion is exhaustive and the network struggles to handle unseen distortions. In this work, we propose distortion robust DCT-Net, a Discrete Cosine Transform based module integrated into a deep network which is built on top of VGG16 [1]. Unlike other works in the literature, DCT-Net is "blind" to the distortion type and level in an image both during training and testing. The DCT-Net is trained only once and applied in a more generic situation without further retraining. We also extend the idea of dropout and present a training adaptive version of the same. We evaluate our proposed DCT-Net on a number of benchmark datasets. Our experimental results show that once trained, DCT-Net not only generalizes well to a variety of unseen distortions but also outperforms other comparable networks in the literature.
- Publisher
- IEEE
- Relation
- 2019 IEEE International Conference on Image Processing (ICIP);Taipei, Taiwan; 22-25 Sept, 2019 p. 659-663
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright IEEE
- Subject
- CNN; Computer Science - Computer Vision and Pattern Recognition; DCT; Discrete cosine transforms; Distortion; Dropout; Gaussian noise; Speckle; Training; Training data; VGG16; Visualization
- Reviewed
- Hits: 1768
- Visitors: 1704
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|