Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition
Year: 2014
Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 4 : pp. 603–613
Abstract
RGB-D (Red, Green and Blue-Depth) cameras are novel sensing systems that can improve image recognition by providing high quality color and depth information in computer vision. In this paper we propose a model to study feature representation of combined Convolutional Neural Networks (CNN) and Block Group Sparse Coding (BGSC). Firstly, CNN is used to extract low-level features from raw RGB- D images directly by applying unsupervised algorithm. Then, BGSC is used to obtain higher feature representation for classification by incorporating both the group structure for low-level features and the block structure for the dictionary in subsequent learning processes. Experimental results show that the CNN-BGSC approach has higher accuracy on a household RGB-D object dataset by linear predictive classifier than using Convolutional and Recursive Neural Networks (CNN-RNN), Group Sparse Coding (GSC), and Sparse Representation base Classification (SRC).
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.3993/jfbi12201413
Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 4 : pp. 603–613
Published online: 2014-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 11
Keywords: RGB-D