ANN analysis in a vision approach for potato inspection
Open Access
- 1 August 2008
- journal article
- Published by Universidad Nacional Autonoma de Mexico in Journal of Applied Research and Technology
- Vol. 6 (02)
Abstract
An image processing methodology for the extraction of potato properties is explained. The objective is to determine their quality evaluating physical properties and using Artificial Neural Networks (ANN’s) to find misshapen potatoes. A comparative analysis for three connectionist models (Backpropagation, Perceptron and FuzzyARTMAP), evaluating speed and stability for classifying extracted properties is presented. The methodology for image processing and pattern feature extraction is presented together with some results. These results showed that FuzzyARTMAP outperformed the other models due to its stability and convergence speed with times as low as 1 ms per pattern which demonstrates its suitability for real-time inspection. Several algorithms to determine potato defects such as greening, scab, cracks are proposed which can be affectively used for grading different quality of potatoes.Keywords
This publication has 6 references indexed in Scilit:
- Sensor and Data Fusion: A Tool for Information Assessment and Decision Making2004
- Improving quality inspection of food products by computer vision––a reviewJournal of Food Engineering, 2004
- Inspection and grading of agricultural and food products by computer vision systems—a reviewComputers and Electronics in Agriculture, 2002
- PC-based machine vision system for real-time computer-aided potato inspectionInternational Journal of Imaging Systems and Technology, 1998
- Machine Vision for Color Inspection of Potatoes and ApplesTransactions of the ASAE, 1995
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989