Artificial neural network-based segmentation and apple grading by machine vision

Author

Unay, Devrim ; Gosselin, Bernard

Author_Institution

TCTS Lab., Faculte Polytech de Mons, Belgium

Volume

2

fYear

2005

fDate

11-14 Sept. 2005

Abstract

In this paper, a computer vision based system is introduced to automatically sort apple fruits. An artificial neural network segments the defected regions on fruit by pixel-wise processing. Statistical features are extracted from the defected regions and then fruit is graded by a supervised classifier. Linear discriminant, nearest neighbor, fuzzy nearest neighbor, adaboost and support vector machines classifiers are tested for fruit grading, where the last two are found to perform best with 90 % recognition.

Keywords

computer vision; feature extraction; fuzzy set theory; image classification; image segmentation; neural nets; statistical analysis; support vector machines; apple grading; artificial neural network-based segmentation; computer vision based system; fuzzy nearest neighbor; linear discriminant; machine vision; pixel-wise processing; supervised classifier; support vector machines classifiers; Artificial neural networks; Computer vision; Image databases; Image resolution; Image segmentation; Machine vision; Nearest neighbor searches; Neural networks; Skin; Sorting;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2005. ICIP 2005. IEEE International Conference on

Print_ISBN

0-7803-9134-9

Type

conf

DOI

10.1109/ICIP.2005.1530134

Filename

1530134