Volume 7, Issue 4
Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition

Shuqin Tu, Yueju Xue, Jinfeng Wang, Xiaolin Huang & Xiao Zhang

Journal of Fiber Bioengineering & Informatics, 7 (2014), pp. 603-613.

Published online: 2014-07

Preview Purchase PDF 2 1792
Export citation
  • 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).

  • Keywords

RGB-D Convolutional Neural Networks Block Group Sparse Coding Classification Recognition Feature Learning Methods

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-7-603, author = {}, 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} }
TY - JOUR T1 - Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition 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).
Shuqin Tu, Yueju Xue, Jinfeng Wang, Xiaolin Huang & Xiao Zhang. (2019). Learning Block Group Spase Representation Combined with Convolutional Neural Networks for RGB-D Object Recognition. Journal of Fiber Bioengineering and Informatics. 7 (4). 603-613. doi:10.3993/jfbi12201413
Copy to clipboard
The citation has been copied to your clipboard