Statistical Class Feature in Texture Analysis of Remote Sensing Imagery

Xin Peng Teng; Shun Lin Song; Yong Zhao Zhan

doi:10.4028/www.scientific.net/AMR.518-523.5749

Paper Titles

Research and Development of the Quick Mapping System on Rural Planning
p.5729

Retrievals of Aerosol Optical Depth and Angstrom Exponent for Identification of Aerosols at Kuching, Sarawak
p.5734

Road Extraction Based on the Algorithms of K-Means Clustering and Hybrid Model of SVM and FCM
p.5738

Spatial Variation of Temperature Monthly at Kuroshio of East China Sea
p.5744

Statistical Class Feature in Texture Analysis of Remote Sensing Imagery
p.5749

The Distribution Regularity of Geohazard in the Dry-Hot Valley of Jinsha River: Case Study in Derong County
p.5754

The Evaluation of Eco-Environmental Sensitivity Based on Grid Cell and Gray Clustering Method
p.5760

The Study of Wuhan Metropolis Circle Land Use and Ecological Service Value Change Nearly Twenty Years
p.5766

Visual Management and Analysis on Drainage Networks in Kunming Based on GIS
p.5770

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 518-523Statistical Class Feature in Texture Analysis of...

Statistical Class Feature in Texture Analysis of Remote Sensing Imagery

Abstract:

This paper we selected 5 typical texture class samples from Quick Bird RGB fused data with 0.61m resolution. We used GLCMs to quantitatively calculate texture features, which parameter values are suitable for the specific texture classifications. Six statistical features for every class sample in four orientations and 1 pixel of pair-wise distance were obtained, including: energy, entropy, contrast, homogeneity, correlation, and dissimilarity respectively. The average values in four directions were computed and compared. The results show that dissimilarity and entropy have biggest value differences among six samples. They are the most important features for classification or recognition of class samples. The statistics of dissimilarity, entropy, homogeneity, contrast have been demonstrated a decrease in classification ability. The results of the research supplied important references for the quantitative interpretation of VHR Quick Bird imagery in the applications of land cover/use classification and mapping.