Abstract
In this work, we propose a methodology for texture recognition. The combination of deep learning with texture encoding techniques has demonstrated to be a powerful strategy to solve this problem. However, one of such encoding classically used in texture images, which are PDE operators, has not been explored in deep learning frameworks. Based on that, here we introduce a pseudo-parabolic diffusion operator to the pipeline of a convolutional neural network (CNN). The method is divided into 4 major stages: 1) application of the pseudo-parabolic operator to the image; 2) use of the resulting image as input to a pre-trained CNN; 3) extraction of local features from the last convolutional layer and pooling by Fisher vectors; 4) classification of the pooled features. Our approach is compared in a texture classification task and outperforms, in terms of classification accuracy, several state-of-the-art solutions. For example, in the challenging benchmark datasets KTH2b and FMD, the proposed method achieves classification accuracy of 79% and 81.8%, respectively. From the numerical viewpoint, we also highlight the key approximation and algorithmic aspects of our computational pseudo-parabolic diffusion modeling into the pipeline of a CNN to enhance deep neural texture features. In particular, the advantage over the plain CNN architecture is substantial. Such interesting performance can be justified by the capacity of the pseudo-parabolic operator to remove spurious noise while preserving important discontinuity information on the texture. The results also suggest the potential of our approach in real-world application, as attested on a practical application to the identification of plant species. In this specific task, our method achieves an accuracy of 94% and outperforms the state-of-the-art results. This is especially the case when we do not have access to a large amount of data for training and when the computational resources are limited, as our method do not involve any fine tuning.
Similar content being viewed by others
Data Availability Statement
The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Abreu E, Durán A (2021) Spectral discretizations analysis with time strong stability preserving properties for pseudo-parabolic models. Comput Math Appl 102:15–44
Abreu E, Ferraz P, Vieira J (2020) Numerical resolution of a pseudo-parabolic buckley-leverett model with gravity and dynamic capillary pressure in heterogeneous porous media. J Comput Phys 411:109395
Abreu E, Vieira J (2017) Computing numerical solutions of the pseudo-parabolic buckley-leverett equation with dynamic capillary pressure. Mathematics and Computers in Simulation 137:29–48, mAMERN VI-2015: 6th International Conference on Approximation Methods and Numerical Modeling in Environment and Natural Resources
Akiva P, Purri M, Leotta M (2022) Self-supervised material and texture representation learning for remote sensing tasks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 8203–8215
Alkhatib M, Hafiane A (2019) Robust adaptive median binary pattern for noisy texture classification and retrieval. IEEE Trans Image Process 28(11):5407–5418
Barros Neiva M, Guidotti P, Bruno OM (2018) Enhancing lbp by preprocessing via anisotropic diffusion. Int J Mod Phys C 29(08):1850071
Bishop CM (2006) Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin, Heidelberg
Boudra S, Yahiaoui I, Behloul A (2022) Tree trunk texture classification using multi-scale statistical macro binary patterns and cnn. Appl Soft Comput 118:108473
Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35(8):1872–1886
Bu X, Wu Y, Gao Z, Jia Y (2019) Deep convolutional network with locality and sparsity constraints for texture classification. Pattern Recog 91:34–46
Casanova D, de Mesquita Sá Junior JJ, Bruno OM (2009) Plant leaf identification using gabor wavelets. Int J Imaging Syst Technol 19(3):236–243
Chan T, Jia K, Gao S, Lu J, Zeng Z, Ma Y (2015) PCANet: A simple deep learning baseline for image classification? IEEE Trans Image Process 24(12):5017–5032
Cimpoi M, Maji S, Kokkinos I, Vedaldi A (2016) Deep filter banks for texture recognition, description, and segmentation. Int J Comput Vision 118(1):65–94
Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A (2014) Describing textures in the wild. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition, IEEE Computer Society, Washington, DC, USA, CVPR ’14, pp 3606–3613
Csurka G, Perronnin F (2011) Fisher vectors: Beyond bag-of-visual-words image representations. In: Richard P, Braz J (eds) Computer vision, imaging and computer graphics. Theory and Applications, Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 28–42
Deepalakshmi P, Lavanya K, Srinivasu PN et al (2021) Plant leaf disease detection using cnn algorithm. Int J Inf Sys Model Des (IJISMD) 12(1):1–21
Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: A deep convolutional activation feature for generic visual recognition. In: Proceedings of the 31st international conference on international conference on machine learning - Volume 32, JMLR.org, ICML’14, pp I-647-I-655
Düll WP (2006) Some qualitative properties of solutions to a pseudoparabolic equation modeling solvent uptake in polymeric solids. Commun Partial Differ Equat 31(8):1117–1138
Florindo JB (2020) DSTNet: Successive applications of the discrete schroedinger transform for texture recognition. Inf Sci 507:356–364
Florindo JB, Abreu E (2021) An application of a pseudo-parabolic modeling to texture image recognition. In: Paszynski M, Kranzlmüller D, Krzhizhanovskaya VV, Dongarra JJ, Sloot PMA (eds) Computational Science - ICCS 2021. Springer International Publishing, Cham, pp 386–397
Florindo JB, Metze K (2021) A cellular automata approach to local patterns for texture recognition. Expert Syst Appl 179:115027
Florindo JB, Lee YS, Jun K, Jeon G, Albertini MK (2021) Visgraphnet: A complex network interpretation of convolutional neural features. Inf Sci 543:296–308
Géron A (2019) Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems.“O’Reilly Media, Inc.”
Gonçalves WN, da Silva NR, da Fontoura Costa L, Bruno OM (2016) Texture recognition based on diffusion in networks. Inf Sci 364(C):51–71
Guidotti P (2015) Anisotropic diffusions of image processing from perona-malik on. In: AIP Conference Proceeding, pp 46
Guo Z, Zhang L, Zhang D (2010) A completed modeling of local binary pattern operator for texture classification. Trans Img Proc 19(6):1657–1663
Guo Z, Zhang L, Zhang D (2010) Rotation invariant texture classification using lbp variance (lbpv) with global matching. Pattern Recog 43(3):706–719
Hayman E, Caputo B, Fritz M, Eklundh JO (2004) On the significance of real-world conditions for material classification. In: Pajdla T, Matas J (eds) Computer Vision - ECCV 2004. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 253–266
Hazgui M, Ghazouani H, Barhoumi W (2022) Genetic programming-based fusion of hog and lbp features for fully automated texture classification. Vis Comput 38(2):457–476
Kannala J, Rahtu E (2012) Bsif: Binarized statistical image features. In: ICPR, IEEE Computer society, pp 1363–1366
Keys R (1981) Cubic convolution interpolation for digital image processing. IEEE Trans Acoust Speech Sig Process 29(6):1153–1160
Koenderink JJ (1984) The structure of images. Biol Cybern 50(5):363–370
Kuznetsov I, Sazhenkov S (2022) Strong solutions of impulsive pseudoparabolic equations. Nonlinear Anal Real World Appl 65:103509
Lazebnik S, Schmid C, Ponce J (2005) A sparse texture representation using local affine regions. IEEE Trans Pattern Anal Mach Intell 27(8):1265–1278
LeVeque RJ (2007) Finite difference methods for ordinary and partial differential equations: steady-state and time-dependent problems. SIAM
Liu S, Deng W (2015) Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR), pp 730–734
Mao S, Rajan D, Chia LT (2021) Deep residual pooling network for texture recognition. Pattern Recog 112:107817
Mikelić A (2010) A global existence result for the equations describing unsaturated flow in porous media with dynamic capillary pressure. J Differ Equ 248(6):1561–1577
Ojala T, Pietikäinen M, Mäenpää T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987
Pan Z, Wu X, Li Z (2019) Central pixel selection strategy based on local gray-value distribution by using gradient information to enhance lbp for texture classification. Expert Syst Appl 120:319–334
Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639
Ranganath A, Sahu PK, Senapati MR (2022) A novel approach for detection of coronavirus disease from computed tomography scan images using the pivot distribution count method. Comput MethodsBiomech Biomed Eng Imaging Vis 10(2):145–156
Saad Y (2003) Iterative methods for sparse linear systems. SIAM
Seam N, Vallet G (2011) Existence results for nonlinear pseudoparabolic problems. Nonlinear Anal Real World Appl 2(5):2625–2639
Sharan L, Rosenholtz R, Adelson EH (2009) Material perceprion: What can you see in a brief glance? J Vis 9(8):784
Showalter RE (2010) Hilbert space methods in partial differential equations. Cour Corp
Showalter R (1970) Well-posed problems for a partial differential equation of order 2m+1. SIAM J Math Anal 1(2):214–231
Showalter R (1975) A nonlinear parabolic-sobolev equation. J Math Anal Appl 50(1):183–190
Showalter RE, Ting TW (1970) Pseudoparabolic partial differential equations. SIAM J Math Anal 1(1):1–26
Shu X, Pan H, Shi J, Song X, Wu XJ (2022) Using global information to refine local patterns for texture representation and classification. Pattern Recog 131:108843
Singh C, Walia E, Kaur KP (2018) Color texture description with novel local binary patterns for effective image retrieval. Pattern Recog 76:50–68
Song T, Li H, Meng F, Wu Q, Cai J (2018) Letrist: Locally encoded transform feature histogram for rotation-invariant texture classification. IEEE Trans Circ Syst Video Technol 28(7):1565–1579
Song T, Xin L, Gao C, Zhang G, Zhang T (2018) Grayscale-inversion and rotation invariant texture description using sorted local gradient pattern. IEEE Signal Process Lett 25(5):625–629
Song T, Feng J, Wang S, Xie Y (2020) Spatially weighted order binary pattern for color texture classification. Expert Syst Appl 147:113167
Song T, Feng J, Wang Y, Gao C (2021) Color texture description based on holistic and hierarchical order-encoding patterns. In: 2020 25th International conference on pattern recognition (ICPR), pp 1306–1312
Song Y, Zhang F, Li Q, Huang H, O’Donnell LJ, Cai W (2017) Locally-transferred fisher vectors for texture classification. In: 2017 IEEE International conference on computer vision (ICCV), pp 4922–4930
Srinivasu PN, JayaLakshmi G, Jhaveri RH, Praveen SP (2022) Ambient assistive living for monitoring the physical activity of diabetic adults through body area networks. Mob Inf Syst 2022:1–18
Van Duijn C, Peletier LA, Pop IS (2007) A new class of entropy solutions of the buckley-leverett equation. SIAM J Math Anal 39(2):507–536
Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis 62(1):61–81
Varma M, Zisserman A (2009) A statistical approach to material classification using image patch exemplars. IEEE Trans Pattern Anal Mach Intell 31(11):2032–2047
Vieira J, Abreu E, Florindo JB (2022) Texture image classification based on a pseudo-parabolic diffusion model. Multimedia Tools Appl 1–24
Wang G, Bo F, Chen X, Lu W, Hu S, Fang J (2022) A collaborative despeckling method for sar images based on texture classification. Remote Sens 14(6)
Witkin AP (1983) Scale-space filtering. In: Proceedings of the eighth international joint conference on artificial intelligence - Volume 2, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI’83, pp 1019–1022
Xiao B, Wang K, Bi X, Li W, Han J (2019) 2d-lbp: An enhanced local binary feature for texture image classification. IEEE Trans Circ Syst Video Technol 29(9):2796–2808
Xu Y, Ji H, Fermüller C (2009) Viewpoint invariant texture description using fractal analysis. Int J Comput Vis 83(1):85–100
Xue J, Zhang H, Dana K (2018) Deep texture manifold for ground terrain recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 558–567
Yang Z, Lai S, Hong X, Shi Y, Cheng Y, Qing C (2022) Dfaen: Double-order knowledge fusion and attentional encoding network for texture recognition. Expert Syst Appl 209:118223
Zhai W, Cao Y, Zhang J, Zha ZJ (2019) Deep multiple-attribute-perceived network for real-world texture recognition. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV), pp 3612–3621
Zhang H, Xue J, Dana K (2017) Deep ten: Texture encoding network. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2896–2905
Zhou Y, Wu W, Wang H, Zhang X, Yang C, Liu H (2022) Identification of soil texture classes under vegetation cover based on sentinel-2 data with svm and shap techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing pp 1–1
Acknowledgements
J. B. Florindo gratefully acknowledges the financial support of São Paulo Research Foundation (FAPESP) (Grants #2020/01984-8 and #2020/09838-0) and from National Council for Scientific and Technological Development, Brazil (CNPq) (Grants #306030/2019-5 and #423292/2018-8). E. Abreu gratefully acknowledges the financial support from National Council for Scientific and Technological Development - Brazil (CNPq) (Grant 306385/2019-8).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Florindo, J.B., Abreu, E. A pseudo-parabolic diffusion model to enhance deep neural texture features. Multimed Tools Appl 83, 11507–11528 (2024). https://doi.org/10.1007/s11042-023-15886-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15886-w