A Model of Visual Attention for Natural Image Retrieval

Guanghai Liu1 Deng-Ping Fan1

1 Guanxi Normal University


In this paper, saliency textons model is proposed to encode color, orientation and saliency cue and spatial information as image features for CBIR, where the image representation is so called saliency textons histogram. Experimental results indicate that the performances of saliency textons histogram outperform Gabor filter and multi-texton histogram. The saliency textons histogram can combine color feature, edge feature and spatial layout together. Furthermore, saliency textons model can simulate visual attention mechanism.


If you find our work is helpful, please cite

  title={A Model of Visual Attention for Natural Image Retrieval}, 
  author={Guanghai Liu, Deng-Ping Fan}, 



1601total visits,6visits today

Leave a Reply

Your email address will not be published. Required fields are marked *