Normalized Non-Negative Sparse Encoder for Fast Image Representation

Shizhou Zhang, Jinjun Wang, Weiwei Shi, Yihong Gong, Yong Xia, Yanning Zhang

2019 (modified: 03 Nov 2022)IEEE Trans. Circuits Syst. Video Technol. 2019Readers: Everyone

Abstract: Image representation based on sparse coding generalizes the bag of words model. Although it reduces the reconstruction error for local features to achieve the state-of-the-art image classification performance, the large computational cost hinders the application of sparse coding-based image features. In this paper, we propose approximating a sparse code using the output of a simple neural network. The resulting parameter learning model for the neural network automatically incorporates non-negative and shift-invariant constraints, leading to an efficient normalized non-negative sparse coding (N 3 SC) sparse encoder. Without the use of the traditional iterative process to solve the sparse coding objective, the sparse encoder directly “converts” each local feature into a sparse code. We also introduce a method for training the encoder based on the auto-encoder method. In addition, we formally propose the corresponding sparse coding scheme called N 3 SC, which enforces both the non-negative constraint and the shift-invariant constraint in addition to the traditional sparse coding criteria. As demonstrated by several experiments, the obtained N 3 SC encoder requires only 3%-10% of the processing time for image feature extraction compared with the standard sparse coding scheme. At the same time, the features extracted using the exact solutions of the N 3 SC coding scheme and the N 3 SC encoder offer superior image classification accuracy compared to the accuracy of many existing sparse coding-based representations.

0 Replies