Analysing the Quality of Food on Convolution Neural Network for Fuzzy Classifier in Hyperspectral Imagery

Author:

T Arumuga Maria Devi1,P Darwin1,Jose Mebin1,P Kumar1

Affiliation:

1. Manonmaniam Sundaranar University

Abstract

Abstract Introduction: This paper is introducing a new architecture which associates convolutional neural network (CNN) formed on fuzzy neural network (FNN). The fuzzy neural network with some few connected layers which gives to add some feature information for using fuzzy neural network. Mapping of membership values, feature maps also called as outputs are produced by CNN that is given in to fuzzy layers by using training phase. The classification accuracy is increased in this proposed architecture instead we are using fuzzy neural networks that can generate not only crisp values but also fuzzy values because of more information is produced in the fuzzy set. Methods: Cross-validation tests are evaluated in our proposed model. More data is needed for executing training the sequences, we contain only less data and testing the data which contains more amount of information that will express the object classified in its ability where important information is not available. Results: The convolution neural network consists of tuned convolution layer, Heuristic Activation Operation and Parallel Element Merge Layer which is manipulated by the fuzzy classifier output based on food image context extractor. Conclusion: Finally, Quality of Food is analysed by means of Visual IDE. Based on that Hyperspectral Output Image is extracted with good accuracy

Publisher

Research Square Platform LLC

Reference46 articles.

1. Landgrebe, D. (2002). Hyperspectral image data analysis. IEEE Sig. Proc. Mag. 19: 17–28.

2. A relative evaluation of multiclass image classification by support vector machines;Foody GM;IEEE Transa on Geosci and Remote Sens,2004

3. Spectralspatial classification of hyperspectral imagery based on partitional clustering techniques;Tarabalka Y;IEEE Trans on Geosci and Remote Sens,2009

4. Locality-preserving dimensionality reduction and classification for hyperspectral image analysis;Li W;IEEE Trans on Geosci and Remote Sens,2012

5. Classification of hyperspectral remote sensing images with support vector machines;Melgani F;IEEE Trans on Geosci and Remote Sens,2004

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3