Block-based cloud classification with statistical features and distribution of local texture features

NCUIR > College of Electrical Engineering & Computer Science > Department of Computer Science and information Engineering > journal & Dissertation > Item 987654321/106416

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/106416

Title:	Block-based cloud classification with statistical features and distribution of local texture features
Authors:	鄭旭詠;Cheng, H.-Y.;Yu, C.-C.
Contributors:	資訊電機學院資訊工程學系
Keywords:	Accuracy;Bayesian analysis;Blocking;Cameras;Classification;Classifiers;Cloud classification;Cloud types;Clouds;Feature extraction;Fourier transforms;Image classification;K-nearest neighbors algorithm;Preserves;Principal components analysis;Probability theory;Solar energy;Standard deviation;Statistics;Sun;Support vector machines;Surface layer;Texture
Date:	2015-03-10
Issue Date:	2026-04-23 13:22:03 (UTC+8)
Publisher:	Copernicus Gesellschaft mbH;Katlenburg-Lindau: Copernicus Publications
Abstract:	摘要： This work performs cloud classification on all-sky images. To deal with mixed cloud types in one image, we propose performing block division and block-based classification. In addition to classical statistical texture features, the proposed method incorporates local binary pattern, which extracts local texture features in the feature vector. The combined feature can effectively preserve global information as well as more discriminating local texture features of different cloud types. The experimental results have shown that applying the combined feature results in higher classification accuracy compared to using classical statistical texture features. In our experiments, it is also validated that using block-based classification outperforms classification on the entire images. Moreover, we report the classification accuracy using different classifiers including the k-nearest neighbor classifier, Bayesian classifier, and support vector machine. 出版者： Katlenburg-Lindau: Copernicus Publications 出版日期： 2015-03-10 出處： Atmospheric measurement techniques, 2015-03, Vol.8 (3), p.1173-1182 資源來源： Publicly Available Content Database 版權： COPYRIGHT 2015 Copernicus GmbH 版權： Copyright Copernicus GmbH 2015 版權： 2015. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 識別號： ISSN: 1867-8548 識別號： ISSN: 1867-1381 識別號： EISSN: 1867-8548 識別號： EISSN: 1867-1381 識別號： DOI: 10.5194/amt-8-1173-2015
Appears in Collections:	[Department of Computer Science and information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	11	View/Open

社群 sharing

Loading...