Share Email Print

Proceedings Paper

Pomegranate MR images analysis using ACM and FCM algorithms
Author(s): Ghobad Morad; Mousa Shamsi; M. H. Sedaaghi; M. R. Alsharif
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Segmentation of an image plays an important role in image processing applications. In this paper segmentation of pomegranate magnetic resonance (MR) images has been explored. Pomegranate has healthy nutritional and medicinal properties for which the maturity indices and quality of internal tissues play an important role in the sorting process in which the admissible determination of features mentioned above cannot be easily achieved by human operator. Seeds and soft tissues are the main internal components of pomegranate. For research purposes, such as non-destructive investigation, in order to determine the ripening index and the percentage of seeds in growth period, segmentation of the internal structures should be performed as exactly as possible. In this paper, we present an automatic algorithm to segment the internal structure of pomegranate. Since its intensity of stem and calyx is close to the internal tissues, the stem and calyx pixels are usually labeled to the internal tissues by segmentation algorithm. To solve this problem, first, the fruit shape is extracted from its background using active contour model (ACM). Then stem and calyx are removed using morphological filters. Finally the image is segmented by fuzzy c-means (FCM). The experimental results represent an accuracy of 95.91% in the presence of stem and calyx, while the accuracy of segmentation increases to 97.53% when stem and calyx are first removed by morphological filters.

Paper Details

Date Published: 30 September 2011
PDF: 8 pages
Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82850H (30 September 2011);
Show Author Affiliations
Ghobad Morad, Sahand Univ. of Technology (Iran, Islamic Republic of)
Mousa Shamsi, Sahand Univ. of Technology (Iran, Islamic Republic of)
M. H. Sedaaghi, Sahand Univ. of Technology (Iran, Islamic Republic of)
M. R. Alsharif, Univ. of the Ryukyus (Japan)

Published in SPIE Proceedings Vol. 8285:
International Conference on Graphic and Image Processing (ICGIP 2011)
Yi Xie; Yanjun Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?