Investigating Shape Representation in Visual Cortex with HMAX
نویسندگان
چکیده
The Problem: The ventral pathway of the primate cortex is thought to mediate object recognition. Within the early visual areas along the pathway, neurons tend to respond well to oriented bars or edges. Neurons in the intermediate visual areas are no longer tuned to the oriented bars only, but to other forms and shapes of intermediate complexity [3, 4, 5, 6, 7]. Finally in the high visual areas, such as the inferior temporal cortex (IT), neurons are responsive to complex shapes like the image of a face or a hand [2]. However, the neural mechanism by which such progression of selectivity arises is an open question.
منابع مشابه
Investigating Shape Representation in Area V4 with HMAX
Motivation: Based on the known properties of the neurons in the earlier information-processing areas, such as V1, it is possible to make a very quantitative model of how the visual cortex may be organized. In fact, Riesenhuber and Poggio’s HMAX model has been useful in making several physiologically consistent predictions about the properties of the visual cortex [4]. The HMAX model can also be...
متن کاملInvestigating Shape Representation in Area V4 with HMAX: Orientation and Grating Selectivities
The question of how shape is represented is of central interest to understanding visual processing in cortex. While tuning properties of the cells in early part of the ventral visual stream, thought to be responsible for object recognition in the primate, are comparatively well understood, several different theories have been proposed regarding tuning in higher visual areas, such as V4. We used...
متن کاملHow a Part of the Brain Might or Might Not Work: A New Hierarchical Model of Object Recognition
The classical model of visual processing in cortex is a hierarchy of increasingly sophisticated representations, extending in a natural way the model of simple to complex cells of Hubel and Wiesel. Somewhat surprisingly, little quantitative modeling has been done in the last 15 years to explore the biological feasibility of this class of models to explain higher level visual processing, such as...
متن کاملSparsity-Regularized HMAX for Visual Recognition
About ten years ago, HMAX was proposed as a simple and biologically feasible model for object recognition, based on how the visual cortex processes information. However, the model does not encompass sparse firing, which is a hallmark of neurons at all stages of the visual pathway. The current paper presents an improved model, called sparse HMAX, which integrates sparse firing. This model is abl...
متن کاملScale Invariant Object Recognition Using Cortical Computational Models and a Robotic Platform
This paper proposes an end-to-end, scale invariant, visual object recognition system, composed of computational components that mimic the cortex in the brain. The system uses a two stage process. The first stage is a filter that extracts scale invariant features from the visual field. The second stage uses inference based spacio-temporal analysis of these features to identify objects in the vis...
متن کامل