Models of the Visual Cortex for Object Representation: Learning and Wired Approaches

Antonio Jose Rodríguez-Sánchez, Justus H. Piater

Abstract

Computational modeling now spans more than three decades. Biologically-plausible models are usually organized into a hierarchy that models the brain in primates after carefully examining neurophysiological and psychophysical studies. Currently, these models extract some values (corners, edges, textures, contours) from images and then apply machine learning algorithms to learn objects or shapes. Are they really that different from classical, non-biologically-inspired, computer vision methods? What facts can we learn from the primate visual system other than the extensively used edge extraction by means of Gabor filters? Should we work more on the representation along this hierarchy before applying a learning strategy? We review the status of computational modeling for object recognition and propose what can be the next challenges to solve.
BibTeX
@inproceedings{rodriguezsanchez2013models,
  author = {Antonio Jose Rodríguez-Sánchez and Justus H. Piater},
  title = {{Models of the Visual Cortex for Object Representation: Learning and Wired Approaches}},
  booktitle = {BrainComp},
  year = {2013},
  doi = {10.1007/978-3-319-12084-3\_5},
}

Loading related content...

Figure