A Remote Sensing Ship Recognition Method Based on Co-Training Model

Wei Ya Guo; Xiao Fei Wang; Xue Zhi Xia

doi:10.4028/www.scientific.net/AMM.713-715.2077

Paper Titles

Multi-Information Model Fused Framework for Chinese Dialect Identification
p.2058

A Prototype Selection Method for Synthetic Object Recognition Based on Structural Graph Model
p.2063

A Parallel Test Task Scheduling of Integrated Avionics System Based on the Ant Colony Algorithm
p.2069

Image Color Recognition System Based on Labview
p.2073

A Remote Sensing Ship Recognition Method Based on Co-Training Model
p.2077

Research on Network Intrusion Detection Based on Data Mining Technology
p.2081

Numerical Simulations of Elliptical Hollow Gaussian Beams Propagating in Strongly Nonlocal Media
p.2085

Study of Driver’s Reaction Time (DRT) during Car Following
p.2089

Calibration of Saturation Flow for Signalized Intersections
p.2093

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 713-715A Remote Sensing Ship Recognition Method Based on...

A Remote Sensing Ship Recognition Method Based on Co-Training Model

Abstract:

Aiming at detecting sea targets efficiently, an approach using optical remote sensing data based on co-training model is proposed. Firstly, using size, texture, shape, moment invariants features and ratio codes, feature extraction is realized. Secondly, based on rough set theory, the common discernibility degree is used to select valid recognition features automatically. Finally, a co-training model for classification is introduced. Firstly, two diverse ruducts are generated, and then the model employs them to train two base classifiers on labeled dada, and makes two base classifiers teach each other on unlabeled data to boot their performance iteratively. Experimental results show the proposed approach can get better performance than K-Nearest Neighbor (KNN), Support Vector Machines (SVM), traditional hierarchical discriminant regression (HDR).