Scale and rotational invariant object recognition using fractal transformations

Author

Neil, G. ; Curtis, K.M.

Author_Institution

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

Volume

6

fYear

1996

fDate

7-10 May 1996

Firstpage

3458

Abstract

Fractal object recognition is an exciting new technique which may be used for rapid object recognition. A novel classification technique using fractal transformations is presented which allows a transformation to be compared directly to an object. This scale invariant technique is then made rotationally invariant before being applied to real world objects. This application shows that the technique is fast, robust to illumination effects and needs little prior knowledge to be successful. Finally work currently underway is detailed

Keywords

feature extraction; fractals; image classification; object recognition; classification technique; fractal object recognition; fractal transformations; illumination effects; real world objects; rotational invariant object recognition; scale invariant object recognition; scale invariant technique; Data mining; Fractals; Image coding; Image recognition; Lighting; Machine vision; Mathematics; Neural networks; Noise robustness; Object recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.550772

Filename

550772