Please use this identifier to cite or link to this item:
Title: Discrimination of bio-crystallogram images using neural networks
Authors: Ünlütürk, Sevcan
Ünlütürk, Mehmet S.
Pazır, Fikret
Kuşçu, Alper
Keywords: Back propagation learning algorithm
Bayes optimal decision rule
Bio-crystallogram images
Gram-Charlier series
Hinton diagrams
Neural networks
Publisher: Springer Verlag
Source: Ünlütürk, S., Ünlütürk, M.S., Pazır, F., and Kuşçu, A. (2014). Discrimination of bio-crystallogram images using neural networks. Neural Computing and Applications, 24(5), 1221-1228. doi:10.1007/s00521-013-1346-6
Abstract: This study utilized a unique neural network model for texture image analysis to differentiate the crystallograms from pairs of fresh red pepper fruits from conventional and organic farms. The differences in visually analyzed samples are defined as the distribution of crystals on the circular glass underlay, the thin or thick structure of crystal needles, the angles between branches and side needles, etc. However, the visual description and definition of bio-crystallogram images has major disadvantages. A novel methodology called an image neural network (INN) has been developed to overcome these shortcomings. The 1,488 × 2,240 pixel bio-crystallogram images were acquired in a lab and cropped to 425 × 1,025 pixel images. These depicted either a conventional sweet red pepper or an organic sweet red pepper. A set of 19 images was utilized to train the image neural network. A new set of 4 images was then prepared to test the INN performance. Overall, the INN achieved an average recognition performance of 100 %. This high level of recognition suggests that the INN is a promising method for the discrimination of bio-crystallogram images. In addition, Hinton diagrams were utilized to display the optimality of the INN weights.
ISSN: 0941-0643
Appears in Collections:Food Engineering / Gıda Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
5528.pdfMakale1.18 MBAdobe PDFThumbnail
Show full item record

CORE Recommender


checked on Mar 29, 2024


checked on May 10, 2024

Page view(s)

checked on May 6, 2024


checked on May 6, 2024

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.