Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition
Abstract
:1. Introduction
2. Related Works
3. Background
3.1. Convolutional Neural Networks
3.2. Non-Additive Tsallis Entropy
4. Proposed Method
5. Validation Setup
6. Results and Discussion
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Scalco, E.; Rizzo, G. Texture analysis of medical images for radiotherapy applications. Br. J. Radiol. 2017, 90, 20160642. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Nurzynska, K.; Iwaszenko, S. Application of Texture Features and Machine Learning Methods to Grain Segmentation in Rock Material Images. Image Anal. Stereol. 2020, 39, 73–90. [Google Scholar] [CrossRef]
- Ansari, R.A.; Buddhiraju, K.M.; Malhotra, R. Urban change detection analysis utilizing multiresolution texture features from polarimetric SAR images. Remote Sens. Appl. Soc. Environ. 2020, 20, 100418. [Google Scholar] [CrossRef]
- Liu, L.; Chen, J.; Fieguth, P.W.; Zhao, G.; Chellappa, R.; Pietikäinen, M. From BoW to CNN: Two Decades of Texture Representation for Texture Classification. Int. J. Comput. Vis. 2019, 127, 74–109. [Google Scholar] [CrossRef] [Green Version]
- Haralick, R.; Shanmugam, K.; Dinstein, I. Texture Features for Image Classification. IEEE Trans. Syst. Man Cybern. 1973, 3, 610–621. [Google Scholar] [CrossRef] [Green Version]
- Ojala, T.; Pietikäinen, M.; Mäenpää, T. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Trans. Pattern Anal. Mach. Intell. 2002, 24, 971–987. [Google Scholar] [CrossRef]
- Florindo, J.B.; Assirati, L.; Bruno, O.M. Locally enhancing fractal descriptors by using the non-additive entropy. Pattern Recognit. Lett. 2016, 70, 32–37. [Google Scholar] [CrossRef]
- Hayman, E.; Caputo, B.; Fritz, M.; Eklundh, J.O. On the Significance of Real-World Conditions for Material Classification. In Computer Vision—ECCV 2004; Pajdla, T., Matas, J., Eds.; Springer: Berlin/Heidelberg, Germany, 2004; pp. 253–266. [Google Scholar]
- Sharan, L.; Rosenholtz, R.; Adelson, E.H. Material perceprion: What can you see in a brief glance? J. Vis. 2009, 9, 784. [Google Scholar] [CrossRef]
- Lazebnik, S.; Schmid, C.; Ponce, J. A Sparse Texture Representation Using Local Affine Regions. IEEE Trans. Pattern Anal. Mach. Intell. 2005, 27, 1265–1278. [Google Scholar] [CrossRef] [Green Version]
- Xu, Y.; Ji, H.; Fermüller, C. Viewpoint Invariant Texture Description Using Fractal Analysis. Int. J. Comput. Vis. 2009, 83, 85–100. [Google Scholar] [CrossRef]
- Casanova, D.; de Mesquita Sá Junior, J.J.; Bruno, O.M. Plant leaf identification using Gabor wavelets. Int. J. Imaging Syst. Technol. 2009, 19, 236–243. [Google Scholar] [CrossRef]
- Donahue, J.; Jia, Y.; Vinyals, O.; Hoffman, J.; Zhang, N.; Tzeng, E.; Darrell, T. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In Proceedings of the 31st International Conference on International Conference on Machine Learning (ICML’14), Beijing, China, 21–26 June 2014; Volume 32, pp. I-647–I-655. [Google Scholar]
- Zhang, H.; Xue, J.; Dana, K. Deep TEN: Texture Encoding Network. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 2896–2905. [Google Scholar]
- Cimpoi, M.; Maji, S.; Kokkinos, I.; Vedaldi, A. Deep Filter Banks for Texture Recognition, Description, and Segmentation. Int. J. Comput. Vis. 2016, 118, 65–94. [Google Scholar] [CrossRef] [Green Version]
- Song, Y.; Zhang, F.; Li, Q.; Huang, H.; O’Donnell, L.J.; Cai, W. Locally-Transferred Fisher Vectors for Texture Classification. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 4922–4930. [Google Scholar]
- Xue, J.; Zhang, H.; Dana, K. Deep Texture Manifold for Ground Terrain Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018. [Google Scholar]
- Zhai, W.; Cao, Y.; Zhang, J.; Zha, Z.J. Deep Multiple-Attribute-Perceived Network for Real-World Texture Recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October–2 November 2019. [Google Scholar]
- Wan, W.; Chen, J.; Li, T.; Huang, Y.; Tian, J.; Yu, C.; Xue, Y. Information Entropy Based Feature Pooling for Convolutional Neural Networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October–2 November 2019. [Google Scholar]
- Park, E.; Ahn, J.; Yoo, S. Weighted-Entropy-Based Quantization for Deep Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017. [Google Scholar]
- Gibert, D.; Mateu, C.; Planes, J.; Vicens, R. Classification of Malware by Using Structural Entropy on Convolutional Neural Networks. In Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–7 February 2018; Volume 32. [Google Scholar]
- Li, H.; Huang, J.; Yang, X.; Luo, J.; Zhang, L.; Pang, Y. Fault Diagnosis for Rotating Machinery Using Multiscale Permutation Entropy and Convolutional Neural Networks. Entropy 2020, 22, 851. [Google Scholar] [CrossRef]
- Gao, X.; Yan, X.; Gao, P.; Gao, X.; Zhang, S. Automatic detection of epileptic seizure based on approximate entropy, recurrence quantification analysis and convolutional neural networks. Artif. Intell. Med. 2020, 102, 101711. [Google Scholar] [CrossRef] [PubMed]
- Liao, S.; Fan, W.; Chung, A.C.; Yeung, D.Y. Facial Expression Recognition using Advanced Local Binary Patterns, Tsallis Entropies and Global Appearance Features. In Proceedings of the 2006 International Conference on Image Processing, Atlanta, GA, USA, 8–11 October 2006; pp. 665–668. [Google Scholar]
- Raja, N.M.; Fernandes, S.; Dey, N.; Satapathy, S.; Rajinikanth, V. Contrast enhanced medical MRI evaluation using Tsallis entropy and region growing segmentation. J. Ambient Intell. Humaniz. Comput. 2018, 1–12. [Google Scholar] [CrossRef]
- Florindo, J.B.; Assirati, L.; Bruno, O.M. Enhancing texture descriptors by a neighborhood approach to the non-additive entropy. Digit. Signal Process. 2015, 44, 14–25. [Google Scholar] [CrossRef]
- Bishop, C.M. Pattern Recognition and Machine Learning (Information Science and Statistics); Springer: Berlin/Heidelberg, Germany, 2006. [Google Scholar]
- Tsallis, C. Possible generalization of Boltzmann-Gibbs statistics. J. Stat. Phys. 1988, 52, 479–487. [Google Scholar] [CrossRef]
- Deppman, A.; Frederico, T.; Megías, E.; Menezes, D.P. Fractal Structure and Non-Extensive Statistics. Entropy 2018, 20, 633. [Google Scholar] [CrossRef] [Green Version]
- Liu, L.; Fieguth, P.; Guo, Y.; Wang, X.; Pietikäinen, M. Local binary features for texture classification: Taxonomy and experimental study. Pattern Recognit. 2017, 62, 135–160. [Google Scholar] [CrossRef] [Green Version]
- Varma, M.; Zisserman, A. A Statistical Approach to Texture Classification from Single Images. Int. J. Comput. Vis. 2005, 62, 61–81. [Google Scholar] [CrossRef]
- Varma, M.; Zisserman, A. A Statistical Approach to Material Classification Using Image Patch Exemplars. IEEE Trans. Pattern Anal. Mach. Intell. 2009, 31, 2032–2047. [Google Scholar] [CrossRef]
- Kannala, J.; Rahtu, E. BSIF: Binarized statistical image features. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan, 11–15 November 2012; pp. 1363–1366. [Google Scholar]
- Guo, Z.; Zhang, L.; Zhang, D. A Completed Modeling of Local Binary Pattern Operator for Texture Classification. IEEE Trans. Image Process. 2010, 19, 1657–1663. [Google Scholar]
- Bruna, J.; Mallat, S. Invariant Scattering Convolution Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2013, 35, 1872–1886. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Cimpoi, M.; Maji, S.; Kokkinos, I.; Mohamed, S.; Vedaldi, A. Describing Textures in the Wild. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14), Columbus, OH, USA, 23–28 June 2014; IEEE Computer Society: Washington, DC, USA, 2014; pp. 3606–3613. [Google Scholar]
- Alkhatib, M.; Hafiane, A. Robust Adaptive Median Binary Pattern for Noisy Texture Classification and Retrieval. IEEE Trans. Image Process. 2019, 28, 5407–5418. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Song, T.; Feng, J.; Wang, Y.; Gao, C. Color Texture Description Based on Holistic and Hierarchical Order-Encoding Patterns. In Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 10–15 January 2021; pp. 1306–1312. [Google Scholar]
- Song, T.; Feng, J.; Wang, S.; Xie, Y. Spatially weighted order binary pattern for color texture classification. Expert Syst. Appl. 2020, 147, 113167. [Google Scholar] [CrossRef]
- Song, T.; Xin, L.; Gao, C.; Zhang, G.; Zhang, T. Grayscale-Inversion and Rotation Invariant Texture Description Using Sorted Local Gradient Pattern. IEEE Signal Process. Lett. 2018, 25, 625–629. [Google Scholar] [CrossRef]
- Singh, C.; Walia, E.; Kaur, K.P. Color texture description with novel local binary patterns for effective image retrieval. Pattern Recognit. 2018, 76, 50–68. [Google Scholar] [CrossRef]
- Song, T.; Li, H.; Meng, F.; Wu, Q.; Cai, J. LETRIST: Locally Encoded Transform Feature Histogram for Rotation-Invariant Texture Classification. IEEE Trans. Circuits Syst. Video Technol. 2018, 28, 1565–1579. [Google Scholar] [CrossRef]
- Pan, Z.; Wu, X.; Li, Z. Central pixel selection strategy based on local gray-value distribution by using gradient information to enhance LBP for texture classification. Expert Syst. Appl. 2019, 120, 319–334. [Google Scholar] [CrossRef]
- Florindo, J.B. DSTNet: Successive applications of the discrete Schroedinger transform for texture recognition. Inf. Sci. 2020, 507, 356–364. [Google Scholar] [CrossRef]
- Xiao, B.; Wang, K.; Bi, X.; Li, W.; Han, J. 2D-LBP: An Enhanced Local Binary Feature for Texture Image Classification. IEEE Trans. Circuits Syst. Video Technol. 2019, 29, 2796–2808. [Google Scholar] [CrossRef]
- da Silva, N.R.; Florindo, J.B.; Gómez, M.C.; Rossatto, D.R.; Kolb, R.M.; Bruno, O.M. Plant Identification Based on Leaf Midrib Cross-Section Images Using Fractal Descriptors. PLoS ONE 2015, 10, e0130014. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Guo, Z.; Zhang, L.; Zhang, D. Rotation Invariant Texture Classification Using LBP Variance (LBPV) with Global Matching. Pattern Recognit. 2010, 43, 706–719. [Google Scholar] [CrossRef]
- Gonçalves, W.N.; da Silva, N.R.; da Fontoura Costa, L.; Bruno, O.M. Texture Recognition Based on Diffusion in Networks. Inf. Sci. 2016, 364, 51–71. [Google Scholar] [CrossRef]
- Florindo, J.B.; Metze, K. A cellular automata approach to local patterns for texture recognition. Expert Syst. Appl. 2021, 179, 115027. [Google Scholar] [CrossRef]
- Florindo, J.B.; Lee, Y.S.; Jun, K.; Jeon, G.; Albertini, M.K. VisGraphNet: A complex network interpretation of convolutional neural features. Inf. Sci. 2021, 543, 296–308. [Google Scholar] [CrossRef]
Method | KTH2b | FMD | UIUC | UMD |
---|---|---|---|---|
VZ-MR8 [31] | 46.3 | 22.1 | 92.9 | - |
VZ-Joint [32] | 53.3 | 23.8 | 78.4 | - |
BSIF [33] | 54.3 | - | 73.4 | 96.1 |
CLBP [34] | 57.3 | 43.6 | 95.7 | 98.6 |
ScatNet (NNC) [35] | 63.7 | - | 88.6 | 93.4 |
DeCAF [36] | 70.7 | 60.7 | 94.2 | 96.4 |
SIFT + BoVW [36] | 58.4 | 49.5 | 96.1 | 98.1 |
FC-CNN VGGM [15] | 71.0 | 70.3 | 94.5 | 97.2 |
FC-CNN AlexNet [15] | 71.5 | 64.8 | 91.1 | 95.9 |
FC-CNN VGGVD [15] | 75.4 | 77.4 | 97.0 | 97.7 |
RAMBP [37] | 68.9 | 46.8 | 94.8 | 98.6 |
H2OEP [38] | 64.2 | - | - | - |
SWOBP [39] | 66.4 | - | - | - |
SLGP [40] | 53.6 | - | - | - |
LBPC [41] | 50.7 | - | - | - |
LETRIST [42] | 65.3 | - | 97.7 | 98.8 |
BRINT [43] | - | - | 92.2 | 93.5 |
MRELBP [43] | - | - | 95.2 | 94.2 |
DSTNet [44] | 61.0 | - | 93.6 | 98.5 |
2D-LTP [45] | - | 49.0 | - | - |
Proposed | 84.4 | 77.7 | 98.5 | 98.8 |
Method | Accuracy (%) |
---|---|
LBPV [47] | 70.8 |
Network diffusion [48] | 75.8 |
FC-CNN VGGM [15] | 78.0 |
FV-CNN VGGM [15] | 83.1 |
Gabor [12] | 84.0 |
FC-CNN VGGVD [15] | 84.2 |
SIFT + BoVW [36] | 86.0 |
FV-CNN VGGVD [15] | 87.1 |
DSTNet [44] | 79.3 |
CATex [49] | 84.7 |
VisGraphNet [50] | 87.3 |
Proposed | 88.5 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Florindo, J.; Metze, K. Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition. Entropy 2021, 23, 1259. https://doi.org/10.3390/e23101259
Florindo J, Metze K. Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition. Entropy. 2021; 23(10):1259. https://doi.org/10.3390/e23101259
Chicago/Turabian StyleFlorindo, Joao, and Konradin Metze. 2021. "Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition" Entropy 23, no. 10: 1259. https://doi.org/10.3390/e23101259