Improved texture image classification through the use of a corrosion-inspired cellular automaton

Silva, Núbia Rosa da; Weeën, Pieter Van der; Baets, Bernard De; Bruno, Odemir Martinez

doi:10.1016/j.neucom.2014.08.036

Cited by 24 publications

(21 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, very large feature vectors do not assure the highest performance, once the success rates tend to stabilize at a determined value. For instance, if we compare the vector Θ(04) 19,29,39 , which has 270 features, with the vector Θ(04) 04,09,14 , which has 90 attributes, the former has a lower performance in all the databases. This suggests that the proposed signature reaches its limit in terms of discrimination.…”

Section: Methodsmentioning

confidence: 99%

Fusion of complex networks and randomized neural networks for texture analysis

Ribas

Sá

Scabini

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

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 networks and its topological properties as well as the image pixels are used to train randomized neural networks in order to create a signature that represents the deep characteristics of the texture. The results obtained surpassed the accuracies 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.

show abstract

Section: Methodsmentioning

confidence: 99%

Fusion of complex networks and randomized neural networks for texture analysis

Ribas

Sá

Scabini

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…The model is constructed on the basis of a tessellation of squared cells (i.e., a 100×100 cell array), in which each cell interacts according to the Moore neighborhood criterion [32,33], with discrete time steps representing monthly variations. The model is capable of reproducing the coupled interaction of n populations in the same time and space.…”

Section: Model Structurementioning

confidence: 99%

Approaching the concepts of ecosystems resilience and stability through spatiotemporal system dynamics and agent-based modelling

Peña-Alzate

Barriga

2017

Rev. Fac. Ing. Univ. Antioquia

View full text Add to dashboard Cite

Abstract:We introduce a simplified ecohydrological model to quantitatively assess the resiliency and stability of ecosystems over long periods. The model couples a hydrological soil moisture balance with a set of spatiotemporal systems dynamics and agent-based algorithms to represent the interactions among several plant populations in a gridded area under different water, soil and temperature constraints. We characterize the plant populations by allometric rules (i.e., power laws for generational and reproductive times; linear approximations for water and temperature gains, losses and optimal values; and a set of intra and interspecific interaction rules based on high, optimal and low competition responses among the populations), that represent different plant phenotypes. We define the disturbances by a clearance of populations in an area within the model's domain and calculate the resiliency and stability with simple indices to determine the ability of the ecosystem to recover from a disturbance. The indices evaluated on each population and over the structure of the entire ecosystem show how the populations respond differently to disturbances, following patterns similar to those expected in nature. The model can represent the spatial and temporal succession of the ecosystem after being disturbed, suggesting how the differences in the phenotypical characteristics of plant populations can be advantageous or disadvantageous for the ecosystem recovery.Resumen: Se presenta un modelo ecohidrológico simplificado para evaluar cuantitativamente la resiliencia y estabilidad de los ecosistemas durante largos períodos. El modelo acopla el balance hidrológico de humedad del suelo con un conjunto de dinámicas espaciotemporales de sistemas y algoritmos basados en agentes para representar las interacciones entre varias poblaciones de plantas en un área de grilla bajo diferentes restricciones de agua, suelo y temperatura. Las poblaciones de plantas se caracterizan por reglas alométricas (por ejemplo, leyes de potencia para tiempos generacionales y reproductivos; aproximaciones lineales para ganancias de agua y temperatura; pérdidas y valores óptimos; y un conjunto de reglas de interacción intra e interespecíficas basadas en respuestas de competencia altas, óptimas y bajas entre las poblaciones), que representan diferentes fenotipos de plantas. Los trastornos se determinan por una remoción de las poblaciones en un área dentro del dominio del modelo. La resistencia y la estabilidad se calculan con índices simples para determinar la capacidad del ecosistema para recuperarse de una perturbación. Los índices evaluados en cada población y sobre la estructura de todo el ecosistema muestran cómo las poblaciones responden de manera diferente a los disturbios, siguiendo patrones similares a los esperados en la naturaleza. El modelo puede representar la sucesión espacial y temporal del ecosistema después de ser perturbado, lo que sugiere que las diferencias en las características fenotípicas de las poblaciones de plantas pueden ser ventaj...

show abstract

“…In case of abrupt changes in the corrosion rate, the method is not seen as efficient enough. Using of texture descriptor constructed by means of a cellular automaton from the pitting corrosion phenomenon was shown by Silva and Van Der Weeen [7]. Fractals are used in computer systems (data compression) [8], simulation of turbulent flows [9], description of complex surfaces [10], as well as in medicine and biology.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Corrosion Process Development on Metals by Means of Computer Vision

Enikeev¹,

Gubaydullin²,

Малеева³

2017

View full text Add to dashboard Cite

Abstract. The paper deals with computer vision and image processing methods applied to the task of corrosion damage search. A step-by-step algorithm is given for processing of the data from a chemical corrosion experiment on a metal surface: image preprocessing, image binarization and identification of object contours, and analysis of object characteristics. The application of the developed methods is exemplified by detection and recognition of corrosion damage on a steel specimen, pitting corrosion, and corrosion of an aluminum specimen. Furthermore, the mechanism of fractal analysis for corrosion cracking specimens was studied and fractal dimension was selected as characteristics of corrosion damage.

show abstract

Improved texture image classification through the use of a corrosion-inspired cellular automaton

Cited by 24 publications

References 37 publications

Fusion of complex networks and randomized neural networks for texture analysis

Fusion of complex networks and randomized neural networks for texture analysis

Approaching the concepts of ecosystems resilience and stability through spatiotemporal system dynamics and agent-based modelling

Analysis of Corrosion Process Development on Metals by Means of Computer Vision

Contact Info

Product

Resources

About