Content area
Full text
Abstract: The automatic classification and identification of maize varieties is one of the important research contents in agriculture. A multi-kernel maize varieties classification approach was proposed in this paper in order to improve the recognition rate of maize varieties. In this approach, four kinds of maize varieties were selected, in each variety 200 grains were selected randomly as the samples, and in each sample 160 grains were taken as the training samples randomly; the characteristics of maize grain were extracted as the typical characteristics to distinguish maize varieties, by which the dictionary required by K-SVD was constructed; for the test samples, the feature-matrixes were extracted by dimension reduction method which were mapped to the high-dimension space by muti-kernel function mapping. The high-dimension characteristic matrixes were trained by K-SVD method and the corresponding feature dictionary was obtained respectively. Finally, the test samples representing were trained and classified by l2,1 minimization sparse coefficient. The experiment results showed that recognition rate was improved obviously through this approach, and the poor-effect to maize variety identification from partial occlusion can be eliminated effectively.
Keywords: multi-kernel, sparse representation, dictionary learning, maize classification
DOI: 10.25165/j.ijabe.20181103.3091
(ProQuest: ... denotes formulae omitted.)
1 Introduction
Maize is one of the main grain crops in the world, and it is also the main grain and economic crop in China. As the main grain crop, maize plays an important role in meeting people's dietary requirements. By maize varieties identification technology, maize classifying automatically and high-quality maize selecting effectively can be realized to promote the process of maize production, processing and export trade. At present, the classification of maize mainly depends on manual evaluation of its shape, color and other aspects. It has the disadvantages of strong subjectivity and low efficiency, which increases the uncertainty of maize varieties classification. With the continuous development of computer technology, machine vision technology is used more and more widely in quality inspection and classification of agricultural products, and it has effectively improved the efficiency of agricultural production. Machine vision instead of manual identification has the following advantages: (1) Multi-parameters measurement, comprehensive evaluation and classification; (2) Reduce human subjective factors and realize classification automatically; (3) Reduce inspecting error and improve accuracy.
There are many different kinds of maize with big different...