Feature Selection for Cotton Matter Classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Feature Selection for Cotton Matter Classification

(1) , (1) , (1) , (1) , (1) , (1) , (1)
1

Abstract

Feature selection are highly important to improve the classification accuracy of recognition systems for foreign matter in cotton. To address this problem, this paper presents six filter approaches of feature selection for obtaining the good feature combination with high classification accuracy and small size, and make comparisons using support vector machine and k-nearest neighbor classifier. The result shows that filter approach can efficiently find the good feature sets with high classification accuracy and small size, and the selected feature sets can effectively improve the performance of recognition system for foreign matter in cotton. The selected feature combination has smaller size and higher accuracy than original feature combination. It is important for developing the recognition systems for cotton matter using machine vision technology.
Fichier principal
Vignette du fichier
478221_1_En_48_Chapter.pdf (295.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02179962 , version 1 (11-07-2019)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Xuehua Zhao, Ying Huang, Zhao Li, Shukai Wu, Xiuhong Ma, et al.. Feature Selection for Cotton Matter Classification. 10th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Oct 2016, Dongying, China. pp.473-480, ⟨10.1007/978-3-030-06155-5_48⟩. ⟨hal-02179962⟩
20 View
2 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More