Image recognition using multi-layer sparse feature extraction with ADMM

Tomoya Hirakawa; Kuntopng Wararatpanya; Yoshimistu Kuroki

doi:10.1117/12.2521348

22 March 2019 Image recognition using multi-layer sparse feature extraction with ADMM

Tomoya Hirakawa, Kuntopng Wararatpanya, Yoshimistu Kuroki

Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019; 110493W (2019) https://doi.org/10.1117/12.2521348
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

Abstract

Being motivated by the Saak (Subspace approximation with augmented kernels) transform, we propose an image recognition scheme using multi-layer sparse feature extraction with a convex solver ADMM (Alternating Direction Method of Multipliers). The Saak transform consists of a multi-layer PCA (Principal Component Analysis) and S/P (Sign-to-Position) conversion to avoid sign confusion. This paper adopts sparse representation instead of PCA and also compares the S/P conversion with the activation function ReLU (Rectified Linear Unit), which is realized by involving the projection mapping onto the non-negative set in convex formulas. The Saak transform uses PCA not only for feature extraction but also for dimension compression of feature vectors. We expect that our method does not need the dimension compression since sparse representation compresses features more than PCA. Experimental results on the MNIST and Fashion-MNIST dataset show that the proposed method is equivalent to the Saak transform in recognition accuracy, and that our method can make features more sparse and extract features that have high discriminant power locally.

Citation Download Citation

Tomoya Hirakawa, Kuntopng Wararatpanya, and Yoshimistu Kuroki "Image recognition using multi-layer sparse feature extraction with ADMM", Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 110493W (22 March 2019); https://doi.org/10.1117/12.2521348

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available