Paper No: 93
Perception of Transformation-invariance in the Visual Pathway
Author(s): Wenlu Yang, Liqing Zhang, Libo Ma
Abstract
Visual perception of transformation invariance, such as translation, rotation and scaling, is one of the important functions of processing visual information in the Brain. To stimulate this perception properties, we propose a computational model for perception of transformation. First, we briefly introduce the transformation-invariant basis functions learned from natural scenes using Independent Component Analysis (ICA). Then we use these basis functions to construct the perceptual model. By using the correlation coefficients of two neural responses as the measure of transformation-invariance, the model is able to perform the task of perception of transformation. Comparison with Bilinear Sparse Coding presented by Grimes and Rao and Topo-ICA by Hayvarinen shows that the perceptual model have some advantages such as a simple algorithm and more transformation-invariant basis functions. Computer simulation results demonstrate that the model successfully simulates the mechanism of visual perception of transformation invariance. |
