Abstract
Recently, second-order statistical modeling methods with convolutional features have shown impressive potential as image representation for vision tasks. Among them, bilinear convolutional neural network (B-CNN) has attracted a lot of attentions due to its simplicity and effectiveness. It captures the second-order local feature statistics via outer product, which approximately explores the covariance between convolutional features and achieves promising performance for texture recognition. In order to inherit the merits of B-CNN while further improving its performance, we introduce a Gaussian descriptor into B-CNN and propose a novel robust deep Gaussian descriptor (RDGD) method for texture recognition. We first compute Gaussian by using the output of outer product of B-CNN, and then embed it into the space of symmetric positive definite (SPD) matrices. Finally, matrix power normalization operation is employed to obtain more robust Gaussian descriptor. Experimental results on three texture databases demonstrate that RDGD is superior to its baseline B-CNN and the state-of-the-arts.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Sharan, L., Liu, C., Rosenholtz, R., et al.: Recognizing materials using perceptually inspired features. Int. J. Comput. Vision. 103(3), 348–371 (2013)
Oyallon, E., Mallat, S.: Deep roto-translation scattering for object classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2865–2873 (2015)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Varma, M., Garg, R.: Locally invariant Fractal features for statistical texture classification. In: International Conference on Computer Vision, pp. 1–8 (2007)
Russakovsky, O., Deng, J., Su, H., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision. 115(3), 211–252 (2014)
Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix backpropagation for deep networks with structured layers. In: International Conference on Computer Vision, pp. 2965–2973 (2015)
Lin, T.Y., Roychowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: International Conference on Computer Vision, pp. 1449–1457 (2016)
Wang, Q., Li, P., Zuo, W., et al.: RAID-G: robust estimation of approximate infinite dimensional Gaussian with application to material recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4433–4441 (2016)
Li, P.H., Xie, J.T., Wang, Q.L., et al.: Is second-order information helpful for large-scale visual recognition? In: International Conference on Computer Vision, pp. 2089–2097 (2017)
Sun, Q.L., Wang, Q.L., Zhang, J.X., et al.: Hyperlayer bilinear pooling with application to fine-grained categorization and image retrieval. Neurocomputing 282, 174–183 (2018)
Lin, T.Y., Maji, S.: Visualizing and understanding deep texture representations. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2791–2799 (2016)
Wang, Q.L., Li, P.H., Zhang, L., et al.: Towards effective codebookless model for image classification. Pattern Recog. 59(C), 63–71 (2016)
Lovric, M., Min-Oo, M., Ruh, E.A.: Multivariate normal distributions parametrized as a Riemannian symmetric space. J. Multivariate Anal. 74(1), 36–48 (2000)
Ledoit, O., Wolf, M.: A well-conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88(2), 365–411 (2004)
Chen, Y., Wiesel, A., Eldar, Y.C., et al.: Shrinkage algorithms for MMSE covariance estimation. IEEE Trans. Signal Process. 58(10), 5016–5029 (2010)
Haran, L., Rosenholtz, R., Adelson, E.H.: Material perception: what can you see in a brief glance? J. Vision 9(8), 784–784 (2009)
Cimpoi, M., Maji, S., Kokkinos, I., et al.: Describing textures in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3603–3613 (2014)
Caputo, B., Hayman, E., Mallikarjuna, P.: Class-specific material categorisation. In: International Conference on Computer Vision, pp. 1597–1604 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, pp. 1–9 (2015)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Interact. Intell. 2(3), 1–27 (2011)
Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3828–3836 (2015)
Gao, Y., Beijbom, O., Zhang, N., et al.: Compact bilinear pooling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 317–326 (2016)
Kong, S., Fowlkes, C.: Low-rank bilinear pooling for fine-grained classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025–7034 (2017)
Song, Y., Zhang, F., Li, Q., et al.: Locally-transferred Fisher vectors for texture classification. In: International Conference on Computer Vision, pp. 4922–4930 (2017)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Nos. 61202251 and 91546123), Program for Changjiang Scholars and Innovative Research Team in University (No. IRT_15R07), the Liaoning Provincial Natural Science Foundation (No. 201602035) and the High-level Talent Innovation Support Program of Dalian City (No. 2016RQ078).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, J., Zhang, J., Sun, Q., Liu, B., Zhang, Q. (2018). Robust Deep Gaussian Descriptor for Texture Recognition. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11164. Springer, Cham. https://doi.org/10.1007/978-3-030-00776-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-00776-8_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00775-1
Online ISBN: 978-3-030-00776-8
eBook Packages: Computer ScienceComputer Science (R0)