Next Article in Journal
Wireless Magnetoelasticity-Based Sensor for Monitoring the Degradation Behavior of Polylactic Acid Artificial Bone In Vitro
Next Article in Special Issue
Fully Symmetric Convolutional Network for Effective Image Denoising
Previous Article in Journal
Suppression of the Hydrodynamic Noise Induced by the Horseshoe Vortex through Mechanical Vortex Generators
Previous Article in Special Issue
Effective Crack Damage Detection Using Multilayer Sparse Feature Representation and Incremental Extreme Learning Machine
Article

Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions

1
Department of Engineering, Università degli Studi di Perugia, Via Goffredo Duranti 93–06125 Perugia (PG), Italy
2
Department of Informatics, Systems and Communication, Università degli studi di Milano-Bicocca, Viale Sarca 336–20125 Milano (MI), Italy
3
School of Electronic Engineering and Computer Science, Queen Mary University of London, 10 Godward Square, Mile End Road, London E1 4FZ, UK
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(4), 738; https://doi.org/10.3390/app9040738
Received: 16 January 2019 / Revised: 4 February 2019 / Accepted: 15 February 2019 / Published: 20 February 2019
(This article belongs to the Special Issue Advanced Intelligent Imaging Technology)
Convolutional Neural Networks (CNN) have brought spectacular improvements in several fields of machine vision including object, scene and face recognition. Nonetheless, the impact of this new paradigm on the classification of fine-grained images—such as colour textures—is still controversial. In this work, we evaluate the effectiveness of traditional, hand-crafted descriptors against off-the-shelf CNN-based features for the classification of different types of colour textures under a range of imaging conditions. The study covers 68 image descriptors (35 hand-crafted and 33 CNN-based) and 46 compilations of 23 colour texture datasets divided into 10 experimental conditions. On average, the results indicate a marked superiority of deep networks, particularly with non-stationary textures and in the presence of multiple changes in the acquisition conditions. By contrast, hand-crafted descriptors were better at discriminating stationary textures under steady imaging conditions and proved more robust than CNN-based features to image rotation. View Full-Text
Keywords: colour texture; feature extraction; image classification; convolutional neural networks; hand-crafted image descriptors colour texture; feature extraction; image classification; convolutional neural networks; hand-crafted image descriptors
Show Figures

Figure 1

MDPI and ACS Style

Bello-Cerezo, R.; Bianconi, F.; Di Maria, F.; Napoletano, P.; Smeraldi, F. Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions. Appl. Sci. 2019, 9, 738. https://doi.org/10.3390/app9040738

AMA Style

Bello-Cerezo R, Bianconi F, Di Maria F, Napoletano P, Smeraldi F. Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions. Applied Sciences. 2019; 9(4):738. https://doi.org/10.3390/app9040738

Chicago/Turabian Style

Bello-Cerezo, Raquel, Francesco Bianconi, Francesco Di Maria, Paolo Napoletano, and Fabrizio Smeraldi. 2019. "Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions" Applied Sciences 9, no. 4: 738. https://doi.org/10.3390/app9040738

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop