Process Neural Network Method: Case Study I: Discrimination of Sweet Red Peppers Prepared by Different Methods. (27th February 2011)

• Record Type: Journal Article
• Authors: Unluturk Unluturk, Sevcan Sevcan; Unluturk Unluturk, Mehmet S. Mehmet S.; Pazir Pazir, Fikret Fikret; Kuscu Kuscu, Alper Alper
• Other Names: Capobianco Capobianco Enrico Enrico Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2011(2011)
• Publication Date: 2011-02-27
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2011/290950
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : This study utilized a feed-forward neural network model along with computer vision techniques to discriminate sweet red pepper products prepared by different methods such as freezing and pureeing. The differences among the fresh, frozen and pureed samples are investigated by studying their bio-crystallogram images. The dissimilarity in visually analyzed bio-crystallogram images are defined as the distribution of crystals on the circular glass underlay and the thin or the thick structure of crystal needles. However, the visual description and definition of bio-crystallogram images has major disadvantages. A methodology called process neural network (ProcNN) has been studied to overcome these shortcomings.