PCANet was proposed as a lightweight deep learning network that mainly leverages Principal Component Analysis (PCA) to learn multistage filter banks followed by binarization and block-wise histograming. PCANet was shown worked surprisingly well in various image classification tasks. However, PCANet is data-dependence hence inflexible. In this paper, we proposed a data-independence network, dubbed DCTNet for face recognition in which we adopt Discrete Cosine Transform (DCT) as filter banks in place of PCA. This is motivated by the fact that 2D DCT basis is indeed a good approximation for high ranked eigenvectors of PCA. Both 2D DCT and PCA resemble a kind of modulated sine-wave patterns, which can be perceived as a bandpass filter bank. DCTNet is free from learning as 2D DCT bases can be computed in advance. Besides that, we also proposed an effective method to regulate the block-wise histogram feature vector of DCTNet for robustness. It is shown to provide surprising performance boost when the probe image is considerably different in appearance from the gallery image. We evaluate the performance of DCTNet extensively on a number of benchmark face databases and being able to achieve on par with or often better accuracy performance than PCANet.
|Title of host publication||2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||8|
|Publication status||Published - 2016 Feb 19|
|Event||2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong|
Duration: 2015 Dec 16 → 2015 Dec 19
|Name||2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015|
|Other||2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015|
|Period||15/12/16 → 15/12/19|
Bibliographical notePublisher Copyright:
© 2015 Asia-Pacific Signal and Information Processing Association.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Modelling and Simulation
- Signal Processing