Performance Analysis Of Neural Network Model For Automated Visual Inspection With Robotic Arm Controller System

The concept of Automated Visual Inspection (AVI) have emerged as a powerful platform for industrial machine vision where it used to inspect a large number of products rapidly.However,a major problem with this kind of application is the quality produced by the recognition process.In this paper,a sys...

Full description

Saved in:
Bibliographic Details
Main Authors: Ab Hadi, Nik Azran, Kadmin, Ahmad Fauzan, A Aziz, Khairul Azha, Abd Rahman, Mohd Soufhwee, Abd Razak, S. S., Salehan, M. Z., Abdul Hadi, N. A., Hamzah, Rostam Affendi, Abd Rashid, Wan Norhisyam
Format: Article
Language:en
Published: Penerbit Universiti,UTeM 2018
Subjects:
Online Access:http://eprints.utem.edu.my/id/eprint/21929/2/2018%20Performance%20Analysis%20of%20Neural%20Network%20Model%20for%20Automated%20Visual%20Inspection%20with%20Robotic%20Arm%20Controller%20System%20Scopus%20Uris.pdf
http://eprints.utem.edu.my/id/eprint/21929/
http://journal.utem.edu.my/index.php/jtec/article/view/3952
https://www.scopus.com/record/display.uri?eid=2-s2.0-85048827856&origin=resultslist&sort=plf-f&src=s&st1=Performance+Analysis+of+Neural+Network+Model+for+Automated+Visual+Inspection+with+Robotic+Arm+Controller+System&st2=&sid=dfb4c410d052684263e7ee7d16119
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The concept of Automated Visual Inspection (AVI) have emerged as a powerful platform for industrial machine vision where it used to inspect a large number of products rapidly.However,a major problem with this kind of application is the quality produced by the recognition process.In this paper,a system with the capability of identifying and categorizing a product based on image processing has been implemented.The image was processed by using Radial Basis Function (RBF) based on output center and spread values optimization.Robotic arm controller developed for pick and place the product based on their categories.Two performance measures are used to validate the model classification range and the spread values.The results of this project indicate that the model used able to identify the product and classify it according to their shape.