Hyperbolic Hopfield neural networks for image classification in content-based image retrieval

被引:17
作者
Anitha, K. [1 ]
Dhanalakshmi, R. [2 ]
Naresh, K. [3 ]
Devi, D. Rukmani [4 ]
机构
[1] SIMATS, Saveetha Sch Engn, Chennai, Tamil Nadu, India
[2] Anna Univ, RMK Engn Coll, Chennai, Tamil Nadu, India
[3] VIT Univ, Vellore, Tamil Nadu, India
[4] Anna Univ, RMD Engn Coll, Chennai, Tamil Nadu, India
关键词
Content-based image retrieval; machine learning; hyperbolic valued Hopfield neural network; image classifiers; pattern recognition; SYSTEM;
D O I
10.1142/S0219691320500599
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Neural networks play a significant role in data classification. Complex-valued Hopfield Neural Network (CHNN) is mostly used in various fields including the image classification. Though CHNN has proven its credibility in the classification task, it has a few issues. Activation function of complex-valued neuron maps to a unit circle in the complex plane affecting the resolution factor, flexibility and compatibility to changes, during adaptation in retrieval systems. The proposed work demonstrates Content-Based Image Retrieval System (CBIR) with Hyperbolic Hopfield Neural Networks (HHNN), an analogue of CHNN for classifying images. Activation function of the Hyperbolic neuron is not cyclic in hyperbolic plane. The images are mathematically represented and indexed using the six basic features. The proposed HHNN classifier is trained, tested and evaluated through extensive experiments considering individual features and four combined features for indexing. The obtained results prove that HHNN guides retrieval process, enhances system performance and minimizes the cost of implementing Neural Network Classifier-based image retrieval system.
引用
收藏
页数:39
相关论文
共 43 条
[1]   Time-Frequency Analysis of Biosignals A Wavelet Transform Overview [J].
Addison, Paul S. ;
Walker, James ;
Guido, Rodrigo C. .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2009, 28 (05) :14-29
[2]   Content-based image retrieval with compact deep convolutional features [J].
Alzu'bi, Ahmad ;
Amira, Abbes ;
Ramzan, Naeem .
NEUROCOMPUTING, 2017, 249 :95-105
[3]   NPFAM: Non-Proliferation Fuzzy ARTMAP for Image Classification in Content Based Image Retrieval [J].
Anitha, K. ;
Chilambuchelvan, A. .
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2015, 9 (07) :2683-2702
[4]  
[Anonymous], 2012, IEEE T NEUR NET LEAR
[5]   Image retrieval: Ideas, influences, and trends of the new age [J].
Datta, Ritendra ;
Joshi, Dhiraj ;
Li, Jia ;
Wang, James Z. .
ACM COMPUTING SURVEYS, 2008, 40 (02)
[6]  
Dhariwal S., 2011, ADV INTELL SYST COMP, V167, P793
[7]   Semantic interactive image retrieval combining visual and conceptual content description [J].
Ferecatu, Marin ;
Boujemaa, Nozha ;
Crucianu, Michel .
MULTIMEDIA SYSTEMS, 2008, 13 (5-6) :309-322
[8]   Flotation froth image recognition with convolutional neural networks [J].
Fu, Y. ;
Aldrich, C. .
MINERALS ENGINEERING, 2019, 132 :183-190
[9]  
Grissa D., 2019, DISCRET APPL MATH
[10]  
Guariglia E., 2009, ENTROPY-SWITZ, V21, P304