Author:
Salam Somayeh,Kheiralipour Kamran,Jian Fuji
Abstract
The existence of dockage, unripe kernels, and foreign materials in chickpea mixtures is one of the main concerns during chickpea storage and marketing. Novel algorithms based on image processing were developed to detect undesirable, foreign materials, and matured chickpea kernels in the chickpea mixture. Images of 270 objects including 54 sound samples and 36 samples of each undesired object were prepared and features of these acquired images were extracted. Different models based on linear discriminant analysis (LDA), support vector machine (SVM), and artificial neural networks (ANN) methods were developed by using MATLAB. Three classification algorithms based on LDA, SVM, and ANN methods were developed. The classification accuracy in training, testing, and overall detection showed the superiority of ANN (99.4, 92.6, and 94.4%, respectively) and LDA (91.1, 94.0, and 91.9%, respectively) over the SVM (100, 53.7, and 88.5%, respectively). The developed image processing technique can be incorporated with a vision-based real-time system.
Subject
Plant Science,Agronomy and Crop Science,Food Science
Reference42 articles.
1. Process for Fractionating Legumes to Obtain Pure Starch and a Protein Concentrate. Washington State University Research Fundation;Czuchajowska;U.S. Patent,1993
2. Description and Culture of Chickpeas;Muehlbauer,1982
3. Major diseases of chickpea in Iran;Sabaghpour;Proceedings of the Symposium on Grain Legumes in the Mediterranean. Agriculture, (LEGUMED),2001
4. Segregation in stored grain bulks: Kinematics, dynamics, mechanisms, and minimization – A review
5. Automatic Seed Classification by Shape and Color Features using Machine Vision Technology
Cited by
12 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献