Image Classification with Hybrid Shearlet Scattering Networks
- Resource Type
- Conference
- Authors
- Ren, Qingyun; Zhou, Bingyin; Guo, Wei
- Source
- 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2019 11th International Conference on. 2:304-307 Aug, 2019
- Subject
- Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
scattering transform
shearlets
convolutional neural networks
image classification
- Language
Image classification is a challenging problem since large variabilities like deformations and illumination changes are existed in the images. In this paper, we introduce a shearlet scattering transform which uses the cascade of shearlet transforms and modulus non-linearities to obtain invariant image representations. It improves the sparsity of the previous scattering transform using Morlet. Furthermore, we give a deep hybrid network for image classification. It uses the shearlet scattering transform as the initial layers of a convolutional neural network. Experiments demonstrate that the proposed method can perform better accurate classification results, especially in the limited samples setting.