Classification of Single Cereal Grain Kernel Using Shape Parameters Based on Machine Vision

Abstract:

The study was conducted to identify three types of non-touching grain kernels using a colour machine vision system. Images of individual cereal grain kernels were acquired using an camera. Shape feature was extracted from binary and edge images of cereal grain kernels obtained by iamge processing for classification. A total of 13 shape feature parameters, including region area, perimeter, length, width, the maximum radius, the smallest radius etc, were extracted from each kernel to use as input to the Bayesian classifier. Experimental results showed that the Bayesian classifier gave better classification with a calssificaiton accuracy of 99.67% for indica type rice, followed by 98.67% and 78.33% for japonica rice and glutinous rice using training set, respectively. The classification system was developed with Bayesian classifier that achieved an overall recognition rate of 92.22% with training data set and furthermore, a classification accuracy of 90% for the testing data set.

• Periodical: Advanced Materials Research (Volumes 605-607)
• Pages: 2179-2182
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.605-607.2179
• Online since: December 2012
• Authors: Lan Lan Wu, Jie Wu, You Xian Wen, Li Rong Xiong, Yu Zheng
• Keywords: Classification, Grain, Machine Vision, Shapes Feature

References

[1] Firatligil-Durmus E, Sarka E and Bubnik Z. Image vision technology for characterization of shape and geometrical properties of two varieties of lentil grown in Turkey. Czech J. Food Sci. Vol. 26(2008), pp.109-116.

DOI: 10.17221/1/2008-cjfs

[2] Paliwal J, Visen N S, Jayas D S and White N D G. Cereal grain and dockage identification using machine vision. Biosystems Eng. Vol. 85(2003) pp.51-57.

DOI: 10.1016/s1537-5110(03)00034-5

[3] Majumdar S and Jayas D S . Classification of cereal grains using machine vision: I. Morphology models. Trans. ASAE. Vol. 43(2000), pp.1669-1675.

DOI: 10.13031/2013.3107

[4] Zayas I, Pomeranz Y and Lai F S. Discrimination of wheat and non-wheat components in grain samples by image analysis. Cereal Chem. Vol. 66(1989), pp.233-237.

[5] Zapotoczny P, Zielinska M and Nita Z 2008. Application of image analysis for the varietal classification of barley: morphological features. J cereal Sci. Vol. 48 pp.104-110.

DOI: 10.1016/j.jcs.2007.08.006

[6] Choudhary R, Paliwal J, and Jayas D S. Classification of cereal grains using wavelet, morphological, colour, and textural features of non-touching kernel images. Biosystems Eng. Vol. 99(2008), pp.330-337.

DOI: 10.1016/j.biosystemseng.2007.11.013

[7] Mebatsin H K, Paliwal J, and Jayas D S. Evaluation of variations in the shape of grain types using principal cmponents analysis of the elliptic Fourier descriptors. Comput. Electron. Agr. Vol. 80(2012), pp.63-70.

DOI: 10.1016/j.compag.2011.10.016

[8] Shouche S P, Rastogi R, Bhagwat S G and Sainis J K. Shape analysis of grains of Indian wheat varieties. Comput. Electron. Agr. Vol. 33(2001), pp.55-76.

DOI: 10.1016/s0168-1699(01)00174-0

[9] Zapotoczny P. Discrimination of wheat grain varieties using image analysis and neural networks. Part I. single kernel texture. J cereal Sci. Vol. 54(2011), pp.60-68.

DOI: 10.1016/j.jcs.2011.02.012

[10] Lirong Xiong and Yu Zheng . Identification of cereal seeds using morphological features. Cereals Oils Proc. Vol. 6(2010), pp.45-48 (in Chinese).

[11] Marchant J A and Onyango C M. Comparison of a Bayesian classifier with a multilayer feed-forward neural network using the example of plant/weed/soil discrimination. Comput. Electron. Agr. Vol. 39(2003), pp.3-22.

DOI: 10.1016/s0168-1699(02)00223-5