@Article{JFBI-7-603,
author = {Shuqin Tu, Yueju Xue, Jinfeng Wang, Xiaolin Huang and Xiao Zhang},
title = {Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition},
journal = {Journal of Fiber Bioengineering and Informatics},
year = {2014},
volume = {7},
number = {4},
pages = {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).},
issn = {2617-8699},
doi = {https://doi.org/10.3993/jfbi12201413},
url = {http://global-sci.org/intro/article_detail/jfbi/4814.html}
}