Universiti Teknologi Malaysia Institutional Repository

SVD based object recognition using functional link neural network for bin picking application

Amin, Shamsudin (2004) SVD based object recognition using functional link neural network for bin picking application. In: International Conference On High Performance Computing, IEEE, Bangalore, India, 2004, n/a.

Full text not available from this repository.

Official URL: http://www.hipc.org/hipc2004/

Abstract

A vision system attached to a bin picking robot must be able to analyze the objects in the bin and must be able to pick an object. In this paper a simple object recognition method is presented using singular value decomposition of the object image and a functional link neural network for a bin picking vision. The results of the functional link net are compared with a simple feed forward net. The net is trained using the error back propagation procedure. The proposed method seems to be robust for recognition of objects.

Item Type:Conference or Workshop Item (Paper)
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:20426
Deposited By: Mrs Liza Porijo
Deposited On:13 Aug 2017 00:18
Last Modified:13 Aug 2017 00:29

Repository Staff Only: item control page