Thresholding-based segmentation and apple grading by machine vision

Author

Unay, Devrim ; Gosselin, Bernard

Author_Institution

TCTS Labs., Fac. Polytech. de Mons, Mons, Belgium

fYear

2005

fDate

4-8 Sept. 2005

Firstpage

1

Lastpage

4

Abstract

In this paper, a computer vision based system is introduced to automatically grade apple fruits. Segmentation of defected skin is done by three global thresholding techniques (Otsu, isodata and entropy). Stem-end/calyx regions falsely classified as defect are removed. Segmentations were visually best with isodata technique applied on 750nm filter image. Statistical features are extracted from the segmented areas 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 latter outperformed others with 89% recognition.

Keywords

agricultural engineering; agricultural products; computer vision; image segmentation; production engineering computing; quality control; support vector machines; Otsu thresholding technique; adaboost; apple defected skin; apple grading; computer vision; entropy; fuzzy nearest neighbor method; isodata technique; linear discriminant analysis; machine vision; support vector machines classifiers; thresholding-based segmentation; Entropy; Feature extraction; Image color analysis; Image segmentation; Object segmentation; Skin; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Conference, 2005 13th European

Conference_Location

Antalya

Print_ISBN

978-160-4238-21-1

Type

conf

Filename

7078105