Title :
A study on quality grading of ´Jonagold´ apples
Author :
Unay, D. ; Gosselin, B.
Author_Institution :
TCTS Lab, Faculte Polytech de Mons, Belgium
Abstract :
In this paper preliminary results on quality grading of ´Jonagold´ apples are presented. Apple area is divided into subregions from where various features are extracted. Another segmentation method, ´geometric centers´, is also introduced. Effects of direct vs. separate principle components analysis and k-nearest neighbor vs. neural network classifiers on the performance are discussed.
Keywords :
feature extraction; image classification; image segmentation; neural nets; principal component analysis; Jonagold apples; geometric centers; k-nearest neighbor; neural network classifiers; quality grading; separate principle components analysis; Bayesian methods; Control systems; Feature extraction; Image databases; Image processing; Infrared imaging; Neural networks; Performance analysis; Reflectivity; Skin;
Conference_Titel :
Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on
Print_ISBN :
0-7803-8292-7
DOI :
10.1109/ISSPIT.2003.1341112
