Object recognition by saccadic parts verification

Author

Jakubowicz, Oleg G.

Author_Institution

Jireh Syst., Leola, PA, USA

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4247

Abstract

A model for the sequential processing of image `parts´ alias subobjects for the purpose of identifying visual objects is presented. The implementation uses three different coherently working neural networks to accomplish the task. One is for coarse resolution hypothesizing, one for verification via fine resolution subobject identification, and the third is a sequentially processing saccade generation net. The mathematical/architectural model is implemented on a UNIX computer with MOTIF interface. In addition a comprehensive set of positional, scale and rotational invariance (PSRI) conditions are tested using CCD camera inputs of real world objects. The data collected from experiments describe the system to have 100% PSRI for real photographs. Samples over a wide range of other real world conditions such as varied illumination and cluttered scenes are also correctly recognized

Keywords

computer vision; image recognition; neural nets; object recognition; CCD camera; MOTIF interface; PSRI conditions; SIGHT; UNIX computer; coarse resolution hypothesizing; fine resolution subobject identification; neural networks; object recognition; photographs; saccade generation net; saccadic parts verification; sequential processing; Computer interfaces; Control systems; Image recognition; Layout; Lighting; Mathematical model; Neural networks; Object recognition; Pixel; Retina;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374948

Filename

374948