Pose estimation in automated visual inspection using ANN


Hati, S. and Sengupta, S. (2002) Pose estimation in automated visual inspection using ANN. International Journal of Neural Systems, 12 (483). ISSN 0129-0657

[img] Text
Pose estimation in automated visual inspection using ANN.pdf
Restricted to Repository staff only

Download (597kB)


In this paper, we present an accurate and robust pose estimator of rigid, polyhedral objects, based on Artificial Neural Networks (ANN), as suitable for Automated Visual Inspection (AVI) applications. The estimator is novel in the sense that it is trained with different poses of the objects having dimensional deviations within its tolerance range and is therefore robust with respect to within tolerance dimensional errors. The estimation accuracy is scalable and our computer simulation experiments in the existing configurations of ANNs have shown an accuracy better than 4% of the placement error. The ANN based pose estimator offers several advantages over the classical implementations.

Item Type: Article
Additional Information: Published in: 1998 IEEE International Conference onSystems, Man, and Cybernetics, 1998.(Volume:2 ) Date of Conference: 11-14 Oct 1998 Print ISBN: 0-7803-4778-1
Subjects: T Technology > T Technology (General)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 09 Jan 2014 04:04
Last Modified: 09 Jan 2014 04:04
URII: http://shdl.mmu.edu.my/id/eprint/4754


Downloads per month over past year

View ItemEdit (login required)