Title of article :
A Coupled-ART neural network capable of modularized categorization of patterns
Author/Authors :
Lee، Nam I1 نويسنده ,
Issue Information :
روزنامه با شماره پیاپی سال 1999
Pages :
-130
From page :
131
To page :
0
Abstract :
This paper presents a technique for obtaining the distance of a step edge from the lens of a camera using a single defocused image of that edge. The proposed technique does not suffer from the correspondence and occlusion problems associated with methods based on multiple images. The technique employs a Multi-Layer Perceptron network trained by backpropagation to compute distances from derivative images of blurred edges. The paper gives experimental results which clearly show the accuracy of the proposed technique. (C) 1999 Published by Elsevier Science Ltd on behalf of the Pattern Recognition Society. All rights reserved.
Keywords :
Global and local features , Coupled-ART , Pattern recognition , Neural networks
Journal title :
PATTERN RECOGNITION LETTERS
Serial Year :
1999
Journal title :
PATTERN RECOGNITION LETTERS
Record number :
14687
Link To Document :
بازگشت