TY - JOUR
T1 - Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition
AU - Shuqin Tu, Yueju Xue, Jinfeng Wang, Xiaolin Huang & Xiao Zhang
JO - Journal of Fiber Bioengineering and Informatics
VL - 4
SP - 603
EP - 613
PY - 2014
DA - 2014/07
SN - 7
DO - http://doi.org/10.3993/jfbi12201413
UR - https://global-sci.org/intro/article_detail/jfbi/4814.html
KW - RGB-D
KW - Convolutional Neural Networks
KW - Block Group Sparse Coding
KW - Classification Recognition
KW - Feature Learning Methods
AB - 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).