Deep Neural Networks Fused with Textures for Image Classification

TL;DR

This paper introduces a fusion approach combining texture analysis and patch-based deep features to improve fine-grained image classification across diverse datasets.

Contribution

It proposes a novel fusion method that integrates global texture features with local patch-based deep features for enhanced FGIC performance.

Findings

Achieved higher classification accuracy than existing methods.

Effective across diverse datasets including faces, skin lesions, and marine life.

Utilized multiple CNN backbones with notable improvements.

Abstract

Fine-grained image classification (FGIC) is a challenging task in computer vision for due to small visual differences among inter-subcategories, but, large intra-class variations. Deep learning methods have achieved remarkable success in solving FGIC. In this paper, we propose a fusion approach to address FGIC by combining global texture with local patch-based information. The first pipeline extracts deep features from various fixed-size non-overlapping patches and encodes features by sequential modelling using the long short-term memory (LSTM). Another path computes image-level textures at multiple scales using the local binary patterns (LBP). The advantages of both streams are integrated to represent an efficient feature vector for image classification. The method is tested on eight datasets representing the human faces, skin lesions, food dishes, marine lives, etc. using four standard backbone CNNs. Our method has attained better classification accuracy over existing methods with notable margins.