Multilayer deep feature extraction for visual texture recognition

TL;DR

This paper enhances texture classification accuracy by extracting and aggregating features from multiple convolutional layers of pretrained CNNs using Fisher vectors, outperforming existing methods on benchmark and real-world datasets.

Contribution

It introduces a novel multilayer feature extraction and aggregation approach using Fisher vectors for improved texture recognition accuracy.

Findings

Multilayer features outperform single-layer features in texture classification.

Fisher vector aggregation improves the discriminative power of extracted features.

Method achieves state-of-the-art results on benchmark datasets and plant species identification.

Abstract

Convolutional neural networks have shown successful results in image classification achieving real-time results superior to the human level. However, texture images still pose some challenge to these models due, for example, to the limited availability of data for training in several problems where these images appear, high inter-class similarity, the absence of a global viewpoint of the object represented, and others. In this context, the present paper is focused on improving the accuracy of convolutional neural networks in texture classification. This is done by extracting features from multiple convolutional layers of a pretrained neural network and aggregating such features using Fisher vector. The reason for using features from earlier convolutional layers is obtaining information that is less domain specific. We verify the effectiveness of our method on texture classification of benchmark datasets, as well as on a practical task of Brazilian plant species identification. In both scenarios, Fisher vectors calculated on multiple layers outperform state-of-art methods, confirming that early convolutional layers provide important information about the texture image for classification.