Identification and classification of three Iranian rice seed varieties in mixed samples by morphological features using image processing and Learning Vector Quantization neural network

مجله پژوهشهای علوم و صنایع غذایی ایران

Article 11, Volume 10, Issue 3 - Serial Number 29, October 2014   

Document Type: Research Article

DOI: 10.22067/ifstrj.v10i3.38214

Authors

Saeideh Fayyazi^* ; Mohammad Hossein Abaspour fard¹; Abbas Rohani²; Hassan Sadrnia; Seyed Amir Hasan Monadjemi

¹Ferdowsi University of Mashhad

².

Abstract

Due to variation in economic value of different varieties of rice, reports indicating the possibility of mixing different varieties on the market. Applying image processing and neural networks techniques to classify rice varieties is a method which can increase the accuracy of the classification process in real applications. In this study, several morphological features of rice seeds’ images were examined to evaluate their efficacy in identification of three Iranian rice varieties (Tarom (Mahali), Fajr, Shiroodi) in the mixed samples of these three varieties. On the whole, 666 images of rice seeds (222 images of each variety) were acquired at a stable illumination condition and totally, 17 morphological features were extracted from seed images. Fisher's coefficient (FC), Principal component analysis (PCA) methods and a combination of these two methods (FC-PCA) were employed to select and rank the most significant features for the classification. The so called LVQ4 (Learning Vector Quantization) neural network classifier was employed for classification using top selected features. The classification accuracy of 98.87, 100 and 100% for Fajr, Tarom and Shiroodi, 100 and 100% for Fajr and Shiroodi, 100 and 100% for Tarom and Shiroodi and 97.62 and 95.74% for Fajr and Tarom were obtained, respectively. These results indicate that image processing is a promising tool for identification and classification of different rice varieties.

Keywords

Rice; morphological features; Image processing; Neural Networks

References