arrow
Volume 8, Issue 4
Part Recognition Method Based on Visual Selective Attention Mechanism and Deep Learning

Dan Zhou & NanfengXiao

Journal of Fiber Bioengineering & Informatics, 8 (2015), pp. 791-800.

Published online: 2015-08

Export citation
  • Abstract
In order to enable the industrial robots to recognize the specific targets quickly and accurately on the assembly line, an object recognition method driven by visual selective attention mechanism is proposed. With mass training data and a machine learning model containing a number of hidden layers, deep learning can learn more useful features, and thus ultimately improve the classification or the prediction accuracy. The main idea of this method is as follows: for all part images, the visual attention mechanism is used to choose salient regions in an image, achieving the goal of target segmentation. Then an image recognition method based on deep learning is applied to recognize the chosen salient regions. Experimental results show the effectiveness of the proposed method and the cognitive rationality.
  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-8-791, author = {Dan Zhou and NanfengXiao}, title = {Part Recognition Method Based on Visual Selective Attention Mechanism and Deep Learning}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2015}, volume = {8}, number = {4}, pages = {791--800}, abstract = {In order to enable the industrial robots to recognize the specific targets quickly and accurately on the assembly line, an object recognition method driven by visual selective attention mechanism is proposed. With mass training data and a machine learning model containing a number of hidden layers, deep learning can learn more useful features, and thus ultimately improve the classification or the prediction accuracy. The main idea of this method is as follows: for all part images, the visual attention mechanism is used to choose salient regions in an image, achieving the goal of target segmentation. Then an image recognition method based on deep learning is applied to recognize the chosen salient regions. Experimental results show the effectiveness of the proposed method and the cognitive rationality.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbim00196}, url = {http://global-sci.org/intro/article_detail/jfbi/4761.html} }
TY - JOUR T1 - Part Recognition Method Based on Visual Selective Attention Mechanism and Deep Learning AU - Dan Zhou & NanfengXiao JO - Journal of Fiber Bioengineering and Informatics VL - 4 SP - 791 EP - 800 PY - 2015 DA - 2015/08 SN - 8 DO - http://doi.org/10.3993/jfbim00196 UR - https://global-sci.org/intro/article_detail/jfbi/4761.html KW - Visual Selective Attention Mechanism KW - Part Recognition KW - Deep Learning KW - Feature Learning AB - In order to enable the industrial robots to recognize the specific targets quickly and accurately on the assembly line, an object recognition method driven by visual selective attention mechanism is proposed. With mass training data and a machine learning model containing a number of hidden layers, deep learning can learn more useful features, and thus ultimately improve the classification or the prediction accuracy. The main idea of this method is as follows: for all part images, the visual attention mechanism is used to choose salient regions in an image, achieving the goal of target segmentation. Then an image recognition method based on deep learning is applied to recognize the chosen salient regions. Experimental results show the effectiveness of the proposed method and the cognitive rationality.
Dan Zhou and NanfengXiao. (2015). Part Recognition Method Based on Visual Selective Attention Mechanism and Deep Learning. Journal of Fiber Bioengineering and Informatics. 8 (4). 791-800. doi:10.3993/jfbim00196
Copy to clipboard
The citation has been copied to your clipboard