Feature measurement and analysis using Gabor filters

Author

Buse, Richard ; Liu, Zhi-Qiang

Author_Institution

Dept. of Comput. Sci., Melbourne Univ., Parkville, Vic., Australia

Volume

4

fYear

1995

fDate

9-12 May 1995

Firstpage

2447

Abstract

An innovative and powerful method is proposed for measuring physical parameters of lines using the responses from a bank of Gabor (1946) filters. These measurements are made without resorting to an image ruler. First the system is calibrated by establishing a relationship between the frequency of the Gabor filter and line length, then the length and angle of of isolated lines can be measured. A constraint on this method is that the lines in the scene need to be separated and isolated by a minimum distance. Results indicate that Gabor filters can be successfully applied to the measurement of geometric properties of objects, especially where Gabor filters are already being used for processing tasks. The best accuracies in terms of measurement error for the line length and angle measurements were 0.81% and 0.0% respectively

Keywords

angular measurement; band-pass filters; edge detection; feature extraction; filtering theory; length measurement; measurement errors; Gabor filter bank; angle measurement; calibration; feature analysis; feature measurement; frequency; geometric properties measurement; images; line length measurement; measurement error; minimum distance; physical parameters measurement; processing tasks; Computer science; Computer vision; Frequency measurement; Gabor filters; Goniometers; Layout; Length measurement; Machine intelligence; Measurement errors; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.480043

Filename

480043