High Impact Factor : 4.396 icon | Submit Manuscript Online icon | UGC Approved icon

Image Classification by Combining Wavelet Transform and Neural Network

Author(s):

Ashok Yadav , RKDF(SRK) Bhopal, India ; Jyoti J.Gurav, RKDF(RGPV) Bhopal, India; Usha Yadav, ACE(MU) Mumbai, India

Keywords:

Image Classification, Wavelet Transform, Neural Network

Abstract

This paper gives you a detail idea of a method of classification of image by combining wavelet transform and neural network. Our main objective in this work is to get an optimal approach of classification by combining wavelet transform and neural network. The proposed scheme for successful classification is combination of a wavelet domain feature extractor and back propagation neural networks (BPNN) classifier. This new approach of classification of image is based on the texture, information of colour and shape. For achieve a suitable way for classification of image here we first use wavelet transform which will go off our main image into sub image and after that this decomposed image are in turn analyzed and the image features are extracted. In this proposed method of image classification first we divide all given image into six parts. For obtaining the required information from each part of the given divided image we use first order movements of colour and daubechies 4 types of wavelet transform. This proposed method for classification of image is fully based on back propagation neural network (BPNN). The highly adaptive and parallel processing ability of back propagation neural network make it widely used classifiers. The RGB colour movement and decomposition coefficient which obtained from each highly adaptive and parallel processing ability of back propagation neural network make it widely used classifiers. The RGB colour movement and decomposition coefficient which obtained from each parts of image by using wavelet decomposer is used as input vector for neural network.170 aircraft colour image were used for training and 200 for testing. Resulting data having 98% and 90% efficiency for training and testing respectively.

Other Details

Paper ID: NCTAAP003
Published in: Conference 4 : NCTAA 2016
Publication Date: 29/01/2016
Page(s): 9-12

Article Preview




Download Article