Fusion of complex networks and randomized neural networks for texture analysis

PATTERN RECOGNITION

卷:103

Article

Ribas, Lucas C.^1,3  Sa Junior, Jarbas Joaci de Mesquita²  Scabini, Leonardo F. S.³  Bruno, Odemir M.^1,3 

[1] Univ Sao Paulo, Inst Math & Comp Sci, Ave Trabalhador Sao Carlense, Sao Carlos 13566590, SP, Brazil

[2] Univ Fed Ceara, Curso Engn Computacao, Programa Posgrad Engn Eletr & Computacao, Campus Sobral,Rua Coronel Estanislau Frota 563, Sobral 62010560, CE, Brazil

[3] Univ Sao Paulo, Sao Carlos Inst Phys, POB 369, Sao Carlos 13560970, SP, Brazil

关键词: Randomized neural networks;    Complex networks;    Texture analysis;    Feature extraction;   

DOI  :  10.1016/j.patcog.2019.107189

来源: Elsevier

【 摘 要 】

This paper presents a high discriminative texture analysis method based on the fusion of complex networks and randomized neural networks. In this approach, the input image is modeled as a complex network and its topological properties as well as the image pixels are used to train randomized neural networks to create a signature that represents the deep characteristics of the texture. The results obtained surpassed the accuracy of many methods available in the literature. This performance demonstrates that our proposed approach opens a promising source of research, which consists of exploring the synergy of neural networks and complex networks in the texture analysis field. (C) 2019 Published by Elsevier Ltd.

【 授权许可】

Free