Statistical features analysis and discrimination of maize seeds utilizing machine vision approach

Article type: Research Article

Authors: Ali, Aqib^a | Mashwani, Wali Khan^{b; *} | Tahir, Muhammad H.^c | Belhaouari, Samir Brahim^d | Alrabaiah, Hussam^e | Naeem, Samreen^a | Nasir, Jamal Abdul^f | Jamal, Farrukh^g | Chesneau, Christophe^h

Affiliations: [a] Department of Computer Science & IT, Glim Institute of Modern Studies, Bahawalpur, Pakistan | [b] Institute of Numerical Sciences, Kohat University of Sciences & Technology, Kohat, Pakistan | [c] Department of Statistics, The Islamia University of Bahawalpur, Bahawalpur, Pakistan | [d] Division of Information and Computing Technology, College of Science and Engineering, Hamad Bin Khalifa University, Education City, Qatar Foundation, Doha, Qatar | [e] College of Engineering al Ain University, al Ain, UAE & Department of Mathematics, Tafila Technical University Tafila, Jordan | [f] Department of Statistics, GC University Lahore, Pakistan | [g] Department of Statistics, The Islamia University of Bahawalpur, Pakistan | [h] Department of Mathematics, Université de Caen, LMNO, Campus II, Science 3, Caen, France

Correspondence: [*] Corresponding author. Wali Khan Mashwani, Institute of Numerical Sciences, Kohat University of Sciences & Technology, Kohat, Pakistan. E-mail: [email protected].

Abstract: The purpose of this study is the statistical analysis and discrimination of maize seed using a machine vision (MV) approach. The foundation of the digital image dataset holds six maize seed varieties named as Kargal K-9803, Gujjar Khan, Desi White, Pioner 30Y87, Syngenta ST-6142, and Pioner 31R88. The digital image dataset acquired via a digital imaging laboratory. For preprocessing, we crop the image into a size of 600×600 pixels, and convert it into a gray level image format. After that, line and edge detection are performed by using a Prewitt filter, and five non-overlapping areas of interest (AOIs) size of (200×200), and (250×250) are drawn. A total of 56 statistical features, containing texture features, histogram features, and spectral features, is extracted from each AOI. The 11 optimized statistical features have been selected by deploying “Correlation-based Feature Selection” (CFS) with the Greedy algorithm. For the discrimination analysis, four MV classifiers named as “Support Vector Machine” (SVM), “Logistic” (Lg), “Bagging” (B), and “LogitBoost” (LB) have been deployed on optimized statistical features dataset. After analysis, the SVM classifier has shown a promising accuracy of 99.93% on AOIs size (250×250). The obtained accuracy by SVM classifier on six maize seed varieties, namely Kargal K-9803, Gujjar Khan, Desi White, Pioner 30Y87, Syngenta ST-6142, and Pioner 31R88, were 99.9%, 99.8%, 100%, 100%, 99.9%, and 99.8%, respectively.

Keywords: Maize seeds, statistical features, discrimination, machine vision, support vector machine

DOI: 10.3233/JIFS-200635

Journal: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 1, pp. 703-714, 2021