Multilayer Complex Network Descriptors for Color-Texture Characterization
arXiv:1804.00501 · doi:10.1016/j.ins.2019.02.060
Abstract
A new method based on complex networks is proposed for color-texture analysis. The proposal consists on 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 with pre-trained architectures. 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.
arXiv comment20 pages, 7 figures and 4 tables
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Emergence of scaling in random networks
- Characterization of complex networks: A survey of measurements
- Extracting the multiscale backbone of complex weighted networks
- Analyzing and Modeling Real-World Phenomena with Complex Networks: A Survey of Applications
- Information filtering in complex weighted networks
- Improved texture image classification through the use of a corrosion-inspired cellular automaton
- Multislice Modularity Optimization in Community Detection and Image Segmentation