Fusion of Complex Networks-based Global and Local Features for Texture Classification

TL;DR

This paper introduces a novel multi-feature fusion approach combining complex network-based global features and deep local features for improved texture classification accuracy.

Contribution

It proposes a new method that fuses complex network global features with deep CNN local features, enhancing texture recognition performance.

Findings

Outperforms state-of-the-art statistical descriptors

Achieves better accuracy than existing CNN models

Effectively combines global and local texture features

Abstract

To realize accurate texture classification, this article proposes a complex networks (CN)-based multi-feature fusion method to recognize texture images. Specifically, we propose two feature extractors to detect the global and local features of texture images respectively. To capture the global features, we first map a texture image as an undirected graph based on pixel location and intensity, and three feature measurements are designed to further decipher the image features, which retains the image information as much as possible. Then, given the original band images (BI) and the generated feature images, we encode them based on the local binary patterns (LBP). Therefore, the global feature vector is obtained by concatenating four spatial histograms. To decipher the local features, we jointly transfer and fine-tune the pre-trained VGGNet-16 model. Next, we fuse and connect the middle outputs of max-pooling layers (MP), and generate the local feature vector by a global average pooling layer (GAP). Finally, the global and local feature vectors are concatenated to form the final feature representation of texture images. Experiment results show that the proposed method outperforms the state-of-the-art statistical descriptors and the deep convolutional neural networks (CNN) models.