Shape Features Based Conic Arcs for Unclassified Wheat Identification

Year 2019, Volume: 3 Issue: 2, 152 - 156, 10.10.2019

Kemal Özkan Ahmet Okan Onarcan Erol Seke Murat Olgun

Abstract

Wheat is one of the main nutrients used
in the world. Consumption of foodstuff produced from quality wheat is of great
importance for healthy generations. It is necessary to separate the high and
low quality wheat. In this paper, a new recognition method for quality wheat
and unclassified wheat is presented. The most distinctive feature for
determination of wheat quality is its shape. In this study, objects are first
represented by a few descriptive points on their contours obtained from their
images. Neighboring points are connected by linear or conical curve fitting.
The objects are then represented by an attribute vector constructed from
parameters of the curves. Finally, these vectors are used to classify objects
(wheat) using support vector machines (svm). Performance is improved with cross
validation for each class.

Keywords

feature extraction, unclassified wheat, shape descriptor

References

• [1]. C.H. Teh, R.T. Chin, "On the detection of dominant points on digital curves", IEEE Transactions 0/ Pattern Analysis and Machine intelligence 11 (1989) 859-872.
• [2]. B. Kerautret, J.-O. Lachaud, B. Naegel, Comparison of discrete curvature estimators and application to corner detection, in:ISVC (1), Vol. 5358 of LNCS, 2008, pp. 710-719.
• [3]. A. Rosenfeld, E. Johnston, Angle detection on digital curves, IEEE Trans. Comput. 22 (1973) 940-941.
• [4]. Wen-Yen Wu, "Dominant point detection using adaptive bending value", Image and Vision Computing 21 (2003) 517-525
• [5]. M. Marji, P. Siy, "Polygonal representation of digital planar curves through dominant point detection - a nonparametrie algorithm", Pattern Recognition 37 (2004) 2113-2130.
• [6]. B.K. Ray, K.S. Ray, "Detection of significant points and polygonal aproximation of digitized curves", Pattern Recognition Letters 22 (1992) 443-452.
• [7]. Z. Kurt, K. Özkan, "Description of Contour with Meaningful Points", SIU 2013 Semposium, Cyprus – Girne (2013).
• [8]. T. Avcı, G. Kökdemir, Z. Kurt, K. Özkan, “Shape Features Based Conic Arcs for Leaf Recognition”, IEEE 22nd Signal Processing and Communications Applications Conference (SIU 2014), Trabzon, Turkey. 2014 22nd Signal Processing and Communications Applications Conference (SIU).
• [9]. D. Cremers, M. Rousson and R. Deriche, "A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape", International Journal of Computer Vision Vol. 72, no. 2, (2007) 195-215.
• [10]. H.T. Sheu, W.c. Hu, "Multiprimitive segmentation of planar curves- A two-level breakpoint classification and tuning approach", IEEE Transactions on Pattern Analysis and Machine Intelligence 21 (1999) 791-797.
• [11]. Wu-Chih Hu, "Multiprimitive segmentation based on meaningful breakpoints for fitting digital planar curves with line segments and conic ares", Image and Vision Computing 23 (2005) 783-789.
• [12]. Hsu, Chih-Wei; Chang, Chih-Chung & Lin, Chih-Jen, "A Practical Guide to Support Vector Classification", Department of Computer Science and Information Engineering, National Taiwan University (2003).