“School of Cognitive Sciences”

Back to Papers Home
Back to Papers of School of Cognitive Sciences

Paper   IPM / Cognitive Sciences / 12285
School of Cognitive Sciences
  Title:   How can selection of biologically inspired features improve the performance of a robust object recognition model?
1.  Masoud Ghodrati
2.  Seyed-Mahdi Khaligh-Razavi
3.  Reza Ebrahimpour
4.  Karim Rajaei
5.  Mohammad Pooyan
  Status:   Published
  Journal: Plos One
  Vol.:  7
  Year:  2012
  Pages:   1-15
  Supported by:  IPM
Humans can effectively and swiftly recognize objects in complex natural scenes. This outstanding ability has motivated many computational object recognition models. Most of these models try to emulate the behavior of this remarkable system. The human visual system hierarchically recognizes objects in several processing stages. Along these stages a set of features with increasing complexity is extracted by different parts of visual system. Elementary features like bars and edges are processed in earlier levels of visual pathway and as far as one goes upper in this pathway more complex features will be spotted. It is an important interrogation in the field of visual processing to see which features of an object are selected and represented by the visual cortex. To address this issue, we extended a hierarchical model, which is motivated by biology, for different object recognition tasks. In this model, a set of object parts, named patches, extracted in the intermediate stages. These object parts are used for training procedure in the model and have an important role in object recognition. These patches are selected indiscriminately from different positions of an image and this can lead to the extraction of nondiscriminating patches which eventually may reduce the performance. In the proposed model we used an evolutionary algorithm approach to ssssselect a set of informative patches. Our reported results indicate that these patches are more informative than usual random patches. We demonstrate the strength of the proposed model on a range of object recognition tasks. The proposed model outperforms the original model in diverse object recognition tasks. It can be seen from the experiments that selected features are generally particular parts of target images. Our results suggest that selected features which are parts of target objects provide an efficient set for robust object recognition.

Download TeX format
back to top
scroll left or right