Verifying The Accuracy Of Machine Vision Algorithms And Systems
- 24 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10586393) , 955-961
- https://doi.org/10.1109/acssc.1988.754690
Abstract
The Purpose of this paper is threefold: (a) to summarize important parameters and procedures for verifying the measurement and recognition (classification) accuracy of machine vision algorithins/systems; (b) to alert the machine vision research community to the current, very inadequate practice in this important area; and (c) to propose some measures to improve this situation. Two example applications from our practice are given in order to illustrate experimental verification procedures we presented. The motivation for the paper is based on the fact that machine vision systems are very hard to model or simulate accurately, so realistic large scale experiments seem to be the only reliable means of assessing their accuracy. However, in the machine vision (research) community this veffication is seldomly done ade- quately. We feel that until this situation is improved, the transfer of research ideas into practice will be difficult.Keywords
This publication has 7 references indexed in Scilit:
- Projection-based high accuracy measurement of straight line edgesMachine Vision and Applications, 1988
- Machine vision algorithms for automated inspection thin-film disk headsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Validating Expert System PerformanceIEEE Expert, 1987
- Candide's Practical Principles of Experimental Pattern RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- Pattern Classifiers and Trainable MachinesPublished by Springer Nature ,1981
- Bibliography on estimation of misclassificationIEEE Transactions on Information Theory, 1974
- Considerations of sample and feature sizeIEEE Transactions on Information Theory, 1972