Extended color local mapped pattern for color texture classification under varying illumination

Negri, Tamiris Trevisan; Zhou, Fang; Obradović, Zoran; Gonzaga, Adilson

doi:10.1117/1.jei.27.1.011008

Cited by 3 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We compare the thirteen representative color texture classification methods on five color texture datasets, respectively CUReT, Colored Brodatz, VisTex USPTex and KTH-TIPS. These color texture classification methods are namely Improved oppenent colour local binary pattern (IOCLBP) [34], Extended color local mapped pattern (ECLMP) [48], Multichannel decoded local binary patterns (mdLBP) [49], Local binary pattern + Local colour contrast (LBP+LCC) [50], Local color vector local binary patters This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.…”

Section: Comparisons With Other Methodsmentioning

confidence: 99%

Completed Extremely Nonnegative DMD for Color Texture Classification

et al. 2020

View full text Add to dashboard Cite

Dense micro-block difference (DMD) has achieved good performance in gray texture representation and classification. However, its performance is not satisfactory when representing color texture. To alleviate this problem, we propose a novel color texture representation method based on Completed Extremely Nonnegative DMD (CEN-DMD) in this paper. In particular, we first use DMD to model interchannel features and interchannel features of color texture images. Considering that negative value is meaningless in a digital image, we perform a nonnegative operation during the difference process. Due to that the maximum value in a nonnegative difference patch represents a significant difference, we construct the Extremely Nonnegative DMD (EN-DMD) by fusing the maximum values of the intrachannel features and the maximum of interchannel features, and further build Completed Extremely Nonnegative DMD (CEN-DMD) by fusing EN-DMDs at five scales and the global feature of the color texture images. Finally, the Fisher Vector is used to encode the CEN-DMD to obtain a color texture descriptor. Experimental results on five published standard color texture datasets (CUReT, Colored Brodatz, VisTex, USPTex and KTH-TIPS) reveal that CEN-DMD is effective when compared to the thirteen representative color texture classification methods. INDEX TERMS color texture representation, dense micro-block difference (DMD), extremely nonnegative multiresolution, texture classification

show abstract

Section: Comparisons With Other Methodsmentioning

confidence: 99%

Completed Extremely Nonnegative DMD for Color Texture Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…(3.10) A Figura 18 apresenta uma textura RGB e a imagem resultante do mapeamento realizado pelo CILMP utilizando a função dada pela Eq. (3.10), considerando-se oito vizinhos e raio igual a dois: (P,r)= (8,2).…”

Section: Color Intensity Local Mapped Pattern (Cilmp)unclassified

“…As configurações (16, 3, 2)RGB + (16, 3, 2)L e aquelas que combinam quatro resoluções de vizinhança apresentaram a mesma acurácia geral, quando se considera os três experimentos: 73, 86%. A maior acurácia geral foi de 74, 24%, obtida pela configuração (8,2,1)…”

Section: Eclmpunclassified

“…Geração do vetor de características ECLMP de uma imagem RGB, considerando P = 8, r out = 2, r in = 1, Q = 16 e β = 0, 1. Fonte: Adaptado de(NEGRI et al, 2018) pelos operadores ECLM P c e ECLM P r em um histograma conjunto (Figura 23). Cada entrada do histograma conjunto armazena o número de vizinhanças da imagem descrita que contém uma determinada combinação de códigos ECLM P c e ECLM P r .…”

unclassified

“…2.2 e 5.2.3: OCLMP(24,5), CILMP(8,2)RGB + (16, 3)RGB + (8, 1)L + (16, 3)L + (24, 5)L e ECLMP (16, 2, 1)RGB + (24, 3, 2)RGB + (16, 2, 1)L + (24, 3, 2)L. Os descritores propostos foram comparados a outros cinco descritores locais de textura, apresentados no Capítulo 2 e listados a seguir:• Local Color Contrast (LCC), aplicado ao espaço de cores RGB (CUSANO; NAPO-LETANO; SCHETTINI, 2014); • Local Binary Pattern (LBP) (OJALA; PIETIKAINEN; MAENPAA, 2002), (MAEN-PAA; PIETIKAINEN, 2004), utilizando a configuração de vizinhança (P, r) = (16, 2), aplicado nos espaços de cores RGB, L * a * b * , I 1 I 2 I 3 e canal de luminância L (imagem em nível de cinza), conforme apresentado por Cusano et. al (2016); • Opponent Color Local Binary Pattern (OCLBP) (MAENPAA; PIETIKAINEN, 2004), utilizando a configuração de vizinhança (P, r) = (24, 5), conforme resultados apresentados na Seção 5.2.4;…”

unclassified

See 2 more Smart Citations