The role of local scale and orientation in feature location using neural nets

Author

Lisboa, P.J.G. ; Mallaiah, M.

Author_Institution

Dept. of Electr. Eng. & Electron., Liverpool Univ., UK

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

672

Lastpage

675

Abstract

The application of one pass orientation and scale selective filters to feature location is investigated. The particular case study developed deals with the location of eyes in head-and-shoulders images using artificial neural networks trained by back-error-propagation. Three types of filters were studied. Conventional Marr edge detectors, Gabor filters selective to the horizontal and vertical directions, and also edge detectors which extract high resolution information along each of the two directions using 2D separable wavelet filters. Tests were conducted to locate the centre of the pupil in the right eye in sixty head-and-shoulders images. The results are compared for the different filters, and also using the raw pixel image directly

Keywords

backpropagation; edge detection; feature extraction; filtering and prediction theory; neural nets; 2D separable wavelet filters; Gabor filters; Marr edge detectors; back-error-propagation; feature extraction; feature location; head-and-shoulders images; local scale; neural nets; one pass orientation; scale selective filters; Artificial neural networks; Data mining; Detectors; Eyes; Gabor filters; Image edge detection; Information filtering; Information filters; Pixel; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2920-7

Type

conf

DOI

10.1109/ICPR.1992.202076

Filename

202076