Finessing filter scarcity problem in face recognition via multi-fold filter convolution

The deep convolutional neural networks for face recognition, from DeepFace to the recent FaceNet, demand a sufficiently large volume of filters for feature extraction, in addition to being deep. The shallow filter-bank approaches, e.g., principal component analysis network (PCANet), binarized statistical image features (BSIF), and other analogous variants, endure the filter scarcity problem that not all PCA and ICA filters available are discriminative to abstract noise-free features. This paper extends our previous work on multi-fold filter convolution (ℳ-FFC), where the pre-learned PCA and ICA filter sets are exponentially diversified by ℳ folds to instantiate PCA, ICA, and PCA-ICA offspring. The experimental results unveil that the 2-FFC operation solves the filter scarcity state. The 2-FFC descriptors are also evidenced to be superior to that of PCANet, BSIF, and other face descriptors, in terms of rank-1 identification rate (%).

[1]  Matti Pietikäinen,et al.  Learning Discriminant Face Descriptor , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Matti Pietikäinen,et al.  Face Recognition Using Smoothed High-Dimensional Representation , 2015, SCIA.

[3]  DeLiang Wang,et al.  Texture classification using spectral histograms , 2003, IEEE Trans. Image Process..

[4]  Xiaogang Wang,et al.  DeepID3: Face Recognition with Very Deep Neural Networks , 2015, ArXiv.

[5]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Andrew Beng Jin Teoh,et al.  DCTNet: A simple learning-free approach for face recognition , 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[7]  Cheng-Yaw Low,et al.  Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[10]  Andrew Beng Jin Teoh,et al.  Multi-fold Gabor filter convolution descriptor for face recognition , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Esa Rahtu,et al.  BSIF: Binarized statistical image features , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[12]  Wen Gao,et al.  Local Gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Wen Gao,et al.  Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition , 2007, IEEE Transactions on Image Processing.

[14]  Frédéric Jurie,et al.  Face Recognition using Local Quantized Patterns , 2012, BMVC.

[15]  Xiaoyang Tan,et al.  Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions , 2007, IEEE Transactions on Image Processing.

[16]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

[17]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Jiwen Lu,et al.  Learning Compact Binary Face Descriptor for Face Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.