Line Detection using a Biologically-Motivated, Continuous-Time, Feedback System Based on the Visual Cortex: Part I

Abstract

The visual cortex is a well studied structure in the brain. Numerous laboratory tests have produced a wealth of data concerning the input-output behavior of the cortex. One of the main functions of the cortex is to detect lines in the visual image. Many theories as to how the cortex performs this task have been proposed. What we have done is to take several of these theories and combine them with the concept of a continuous-time, feedback system. Our results show that the orientation and length of the lines in an image can be detected using our system. This article is part one of two and covers the main detection engine consisting of Gabor filters used as the kernel of an integral transform.

Meeting Name

Artificial Neural Networks in Engineering Conference, ANNIE 2003 (2003: Nov. 2-5, St. Louis, MO)

Department(s)

Electrical and Computer Engineering

Keywords and Phrases

Gabor Filters; Bandwidth; Brain; Data Reduction; Feedback; Image Processing; Integral Transforms; Integration; Line Detection; Mathematical Transformations; Sensitivity Analysis; Visual Cortex

International Standard Book Number (ISBN)

0-7918-0204-3

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2003 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Nov 2003

This document is currently not available here.

Share

 
COinS