Colour in Context
Research group
Computer Vision Center

Modulating Shape Features by Color Attention for Object Recognition

International Journal of Computer Vision (IJCV), Volume 98, Number 1, page 49--64 - 2012
IF: 3.623. area: COMPUTER SCIENCE, A. I.. Quartile: Q1.
Download the publication : Modulating_shape_features_by_color_attention_for_object_recognition.pdf [5.1Mo]  
Bag-of-words based image representation is a successful approach for object recognition. Generally, the subsequent stages of the process: feature detection,feature description, vocabulary construction and image representation are performed independent of the intentioned object classes to be detected. In such a framework, it was found that the combination of different image cues, such as shape and color, often obtains below expected results. This paper presents a novel method for recognizing object categories when using ultiple cues by separately processing the shape and color cues and combining them by modulating the shape features by category specific color attention. Color is used to compute bottom up and top-down attention maps. Subsequently, these color attention maps are used to modulate the weights of the shape features. In regions with higher attention shape features are given more weight than in regions with low attention. We compare our approach with existing methods that combine color and shape cues on five data sets containing varied importance of both cues, namely, Soccer (color predominance), Flower (color and hape parity), PASCAL VOC 2007 and 2009 (shape predominance) and Caltech-101 (color co-interference). The experiments clearly demonstrate that in all five data sets our proposed framework significantly outperforms existing methods for combining color and shape information.

Images and movies

 

BibTex references

@Article\{SVV2012,
  author       = "Fahad Shahbaz Khan and Joost van de Weijer and Maria Vanrell",
  title        = "Modulating Shape Features by Color Attention for Object Recognition",
  journal      = "International Journal of Computer Vision (IJCV)",
  number       = "1",
  volume       = "98",
  pages        = "49--64",
  year         = "2012",
  abstract     = "Bag-of-words based image representation is a successful approach for object recognition. Generally, the subsequent stages of the process: feature detection,feature description, vocabulary construction and image representation are performed independent of the intentioned object classes to be detected. In such a framework, it was found that the combination of different image cues, such as shape and color, often obtains below expected results. This paper presents a novel method for recognizing object categories when using ultiple cues by separately processing the shape and color cues and combining them by modulating the shape features by category specific color attention. Color is used to compute bottom up and top-down attention maps. Subsequently, these color attention maps are used to modulate the weights of the shape features. In regions with higher attention shape features are given more weight than in regions
with low attention. We compare our approach with existing methods that combine color and shape cues on five data sets containing varied importance of both cues, namely, Soccer (color predominance), Flower (color and hape parity), PASCAL VOC 2007 and 2009 (shape predominance) and Caltech-101 (color co-interference). The experiments clearly demonstrate that in all five data sets our proposed framework significantly outperforms existing methods for combining color and shape information.",
  ifactor      = "3.623",
  quartile     = "Q1",
  area         = "COMPUTER SCIENCE, A. I.",
  url          = "http://cat.uab.es/Public/Publications/2012/SVV2012"
}

Other publications in the database

  2008 Colour in context Group | Computer Vision Center. All rights reserved | Contact webmaster |  Last updated: Monday 11 May 2009     eXTReMe Tracker