Publicación:
Multilayer complex network descriptors for color–texture characterization
Multilayer complex network descriptors for color–texture characterization
| dc.contributor.author | Scabini L.F.S. | es_PE |
| dc.contributor.author | Condori R.H.M. | es_PE |
| dc.contributor.author | Gonçalves W.N. | es_PE |
| dc.contributor.author | Bruno O.M. | es_PE |
| dc.date.accessioned | 2024-05-30T23:13:38Z | |
| dc.date.available | 2024-05-30T23:13:38Z | |
| dc.date.issued | 2019 | |
| dc.description | L. F. S. Scabini acknowledges support from CNPq (Grants #134558/2016-2 and #142438/2018-9). O. M. Bruno acknowledges support from CNPq (Grant #307797/2014-7 and Grant #484312/2013-8) and FAPESP (grant #14/08026-1 and #16/18809-9). R. H. M. Condori acknowledges support from Cienciactiva, an initiative of the National Council of Science, Technology and Technological Innovation-CONCYTEC (Peru). W. N. Gonçalves acknowledges support from CNPq (Grant #304173/2016-9) and Fundect (Grant #071/2015). The authors are grateful to Abdelmounaime Safia for the feedback concerning the MBT dataset construction, and the NVIDIA GPU Grant Program for the donation of the Quadro P6000 and the Titan Xp GPUs used on this research. | |
| dc.description.abstract | A new method based on complex networks is proposed for color–texture analysis. The proposal consists of modeling the image as a multilayer complex network where each color channel is a layer, and each pixel (in each color channel) is represented as a network vertex. The network dynamic evolution is accessed using a set of modeling parameters (radii and thresholds), and new characterization techniques are introduced to capt information regarding within and between color channel spatial interaction. An automatic and adaptive approach for threshold selection is also proposed. We conduct classification experiments on 5 well-known datasets: Vistex, Usptex, Outex13, CURet, and MBT. Results among various literature methods are compared, including deep convolutional neural networks. The proposed method presented the highest overall performance over the 5 datasets, with 97.7 of mean accuracy against 97.0 achieved by the ResNet convolutional neural network with 50 layers. | |
| dc.description.sponsorship | Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - Concytec | |
| dc.identifier.doi | https://doi.org/10.1016/j.ins.2019.02.060 | |
| dc.identifier.scopus | 2-s2.0-85063901933 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12390/522 | |
| dc.language.iso | eng | |
| dc.publisher | Elsevier Inc. | |
| dc.relation.ispartof | Information Sciences | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | Threshold selection | |
| dc.subject | Classification (of information) | es_PE |
| dc.subject | Color | es_PE |
| dc.subject | Convolution | es_PE |
| dc.subject | Deep neural networks | es_PE |
| dc.subject | Feature extraction | es_PE |
| dc.subject | Multilayers | es_PE |
| dc.subject | Network layers | es_PE |
| dc.subject | Neural networks | es_PE |
| dc.subject | Textures | es_PE |
| dc.subject | Adaptive approach | es_PE |
| dc.subject | Characterization techniques | es_PE |
| dc.subject | Convolutional neural network | es_PE |
| dc.subject | Multi-layer network | es_PE |
| dc.subject | Spatial interaction | es_PE |
| dc.subject | Texture analysis | es_PE |
| dc.subject | Texture characterizations | es_PE |
| dc.subject | Complex networks | es_PE |
| dc.subject.ocde | https://purl.org/pe-repo/ocde/ford#1.02.02 | |
| dc.title | Multilayer complex network descriptors for color–texture characterization | |
| dc.type | info:eu-repo/semantics/article | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# |