|
Morphological Based Grain Comparison of Three Rice Grain Variety
[Full Text]
AUTHOR(S)
Cyril L. Macalalad, Edwin R. Arboleda, Adonis A. Andilab and Rhowel M. Dellosa
KEYWORDS
Comparison, Fuzzification, Fuzzy Logic, Image Processing, MatLab, Morphological Features Rice Grain Varities
ABSTRACT
In the Philippines, rice grains have their distinct characteristics from each other variety in terms of quality and on how they plant. The quality and variety of different rice grains is usually determined by visual inspection and pure instincts, which is subjective, laborious, and prone to error. Due to this errors, many consumers were deceived by the retailers in buying pure quality rice. In result, a formulation of an alternative method with the help of the current technology to determine the different rice variety is conducted. This research was conducted with the objective of developing an appropriate computer routine algorithm that can characterize rice grains of different origins in different parts of the Philippines. Morphological analyses through image processing techniques were employed to automatically classify and determine the ranges of the parameters of the rice grain samples according to their variety. Important rice grain features based in morphology such as area of the grain, perimeter, equivalent diameter and percentage of roundness from 60 training images and 20 testing images were gathered and evaluated. Fuzzy Logic technique was conducted to classify the rice grain as well as the K Nearest Neighbor (KNN) that was employed to automatically categorize the variety of the rice grains. In conclusion, the results of this study have revealed that imaging technique with the aid of artificial intelligence could be used as an effective method to classify rice grain characteristics.
REFERENCES
[1]. Gupta N. “Identification and Classification of Rice varieties using Mahalanobis Distance by Computer Vision”. International Journal of Scientific and Research Publications, Volume 5, Issue 5, May 2015
[2]. Piramli, M, et. al. “Rice Grain Grading Classification Based On Perimeter Using Moore-Neighbor Tracing Method”. ISSN: 2180 – 1843 e-ISSN: 2289-8131 Vol. 8 No. 2
[3]. Guzman J and Peralt E “Classification of Philippine Rice Grains Using Machine Vision and Artificial Neural Networks”. Philippines
[4]. Chathurika Sewwandi Silva, Upul Sonnadara, “Classification of Rice Grains Using Neural Networks” Proceedings of Technical Sessions, 29 (2013) 9-14.
[5]. https://en.wikipedia.org/wiki/Glutinous_rice
[6]. http://www.unitedricemills.com/sinandomeng-rice/
[7]. http://www.unitedricemills.com/maharlika-rice/
[8]. Abirami. S, Neelamegam. P, Kala. H “Analysis of Rice Granules using Image Processing and Neural Network Pattern Recognition Tool”. International Journal of Computer Applications Volume 96– No.7, June 2014
[9]. Arboleda, E. R., Fajardo, A. C., & Medina, R. P. (2018a). Classification of Coffee Bean Species Using Image Processing , Artificial Neural Network and K Nearest Neighbors. 2018 IEEE International Conference on Innovative Research and Development (ICIRD), (May), 1–5.
[10]. Arboleda, E. R. (2019). Comparing Performances of Data Mining Algorithms for Classification of Green Coffee Beans. International Journal of Engineering and Advanced Technology (IJEAT), 8(5), 1563–1567.
[11]. Arboleda, E. R., Fajardo, A. C., & Medina, R. P. (2018b). An Image Processing Technique for Coffee Black Beans Identification. In 2018 IEEE International Conference on Innovative Research and Development (ICIRD) (pp. 1–5). IEEE.
[12]. Kausal S, More S, “Review on Identification and Classification of Grains Using Image Processing” International Journal of Science and Research (IJSR) Volume 4 Issue 4, April 2015
[13]. Dellosa R, Fajardo A and Medina R. “A Heuristic Approach of Location Estimation Based on Pre-defined Coordinates” IJRTE, Vol 7, Issue 6, pp 1110-1113, March 2019
[14]. Arboleda, E. R. (2018). Discrimination of civet coffee using near infrared spectroscopy and artificial neural network. International Journal of Advanced Computer Research, 8(39), 324–334.
|
