Academic Journals Database
Disseminating quality controlled scientific knowledge

Performance Analysis of Image Classification Algorithm Based on Feature Fusing Technique Model

ADD TO MY LIST
 
Author(s): Mukul Yadav | Gaje ndra Singh Chandel | Ravindra Gupta

Journal: International Journal of Advanced Computer Research
ISSN 2249-7277

Volume: 3;
Issue: 10;
Start page: 200;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: image classification | feature reduction | FLDA | RBF

ABSTRACT
Unclassified region deceases the efficiency andperformance ofPLSA and FLDA. The properselection of feature sub set reduced the unclassifiedregion ofPLSA and FLDA. Now a day‟sbinaryclassification are widely used in image classification.The mappingof data one space to another spacecreates diversity of outlier and noise and generateunclassified region for image classification. For thereduction of unclassified region we used radial basisfunction for sampling of feature and reduce the noiseand outlier for feature space of data and increase theperformance and efficiency of image classification.Our proposed method optimized the feature selectionprocess and finally sends data toFLDAclassifier forclassification of data. Here we usedfisher classifier.As a classifierFLDAsuffering two problems (1) howto choose optimal feature sub set input and (2) how toset best kernel parameters. These problems influencethe performance and accuracy ofFLDA. Now thepre-sampling of feature reduced the featureselectionprocess ofFLDAfor image classification.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?