ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Research on Description of Fruit Shape Based on Machine Vision

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2012 Dallas, Texas, July 29 - August 1, 2012  121340775.(doi:10.13031/2013.41953)
Authors:   Fujie Wang, Xiuqin Rao, Yibin Ying
Keywords:   Fruit shape, Shape description, Shape characters, Signature description, Moments

Shape is one of the most important indexes for fruit quality evaluation, and extracting the shape characters of fruit is the key step for the shape grading. However, it is very difficult to get the accurate description of fruit shape because of a variety of fruit shape in different attitudes. In this research, 4 images were taken for each apple respectively. There are 144 images for 36 apples, in which 12 apples being considered to have the best shape, and 11 ones having big deformation, and the other 13 ones having small deformation. Then process these images and get 245 shape character parameters of each boundary of the fruit through signature description, Hu moments, Zernike moments, wavelet moments, Fourier description, and wavelet description. This paper is trying to get efficient and practical shape indexes and find a feasible way for describing fruit shape.

(Download PDF)    (Export to EndNotes)