Thumbnail
Access Restriction
Open

Author Zhang, Yudong ♦ Wu, Lenan ♦ Neggaz, Nabil ♦ Wang, Shuihua ♦ Wei, Geng
Source World Health Organization (WHO)-Global Index Medicus
Content type Text
Publisher Multidisciplinary Digital Publishing Institute
File Format HTM / HTML
Language English
Difficulty Level Medium
Subject Domain (in DDC) Technology ♦ Medicine & health
Abstract This paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/ decomposition, and the GLCM-based texture features. Then, a probabilistic neural network (PNN) was adopted for classification, and a novel algorithm proposed to enhance its performance. Principle component analysis (PCA) was chosen to reduce feature dimensions, random division to reduce the number of neurons, and Brent's search (BS) to find the optimal bias values. The results on San Francisco and Flevoland sites are compared to that using a 3-layer BPNN to demonstrate the validity of our algorithm in terms of confusion matrix and overall accuracy. In addition, the importance of each improvement of the algorithm was proven.
Description Author Affiliation: Zhang Y ( School of Information Science and Engineering, Southeast University, Nanjing 210009, China)
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Reading ♦ Research ♦ Self Learning
Interactivity Type Expositive
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2009-01-01
Publisher Place Switzerland
e-ISSN 14248220
Journal Sensors
Volume Number 9
Issue Number 9


Source: WHO-Global Index Medicus