Abstract
Convolutional Neural Networks (CNNs) have been proven very effective in image classification and object recognition tasks, often exceeding the performance of traditional image analysis techniques. However, training a CNN requires very extensive datasets, as well as very high computational burden. In this work, we test the hypothesis that if the input includes the responses of established image analysis filters that detect salient image structures, the CNN should be able to perform better than an identical CNN fed with the plain RGB images only. Thus, we employ a number of families of image analysis filter banks and use their responses to compile a small number of filtered responses for each original RGB image. We perform a large number of CNN training/testing repetitions for a 40-class building recognition problem, on a publicly available image database, using the original images, as well as the original images augmented by the compiled filter responses. Results show that the accuracy achieved by the CNN with the augmented input is consistently higher than that of the RGB image input, both in terms of different repetitions of the execution, as well as throughout the iterations of each repetition.
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
Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. CoRR, abs/1506.05163 (2015)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Georgakopoulos, S.V., Kottari, K., Delibasis, K., Plagianakos, V.P., Maglogiannis, I.: Pose recognition using convolutional neural networks on omni-directional images. Neurocomputing 280(6), 23–31 (2018)
Georgakopoulos, S.V., Kottari, K., Delibasis, K., Plagianakos, V.P., Maglogiannis, I.: Detection of malignant melanomas in dermoscopic images using convolutional neural network with transfer learning. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds.) EANN 2017. CCIS, vol. 744, pp. 404–414. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-65172-9_34
https://imagej.net/Trainable_Weka_Segmentation\#Training_panel
Li, J., Allinson, N.M.: Dimensionality reduction-based building recognition. In: Proceedings of the Ninth IASTED International Conference on Visualization, Imaging and Image Processing, Cambridge UK, pp. 13–15, July 2009
Mikolajczyk, K., et al.: A comparison of affine region detectors. Int. J. Comput. Vis. 65(43), 43–72 (2005)
Tuytelaars, T., Mikolajczy, K.: Local invariant feature detectors: a survey. Comput. Graph. Vis. 3(3), 177–280 (2007)
Daugman, J.G.: Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Opt. Soc. Am. J. Opt. Image Sci. 2(7), 1160–1169 (1985)
Weldon, T.P., Higgins, W.E., Dunn, D.F.: Efficient gabor filter design for texture segmentation. Pattern Recogn. 29(12), 2005–2015 (1996)
Li, M., Staunton, R.C.: Optimum gabor filter design and local binary patterns for texture segmentation. Pattern Recogn. Lett. 29(5), 664–672 (2008)
Jia Y., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large dataset for nonparametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1958–1970 (2008)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometr. Bull. 1(6), 80–83 (1945)
Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0056195
Krissian, K., Malandain, G., Ayache, N., Vaillant, R., Trousset, Y.: Model based detection of tubular structures in 3D images. Comput. Vis. Image Underst. 80(2), 130–171 (2000)
Acknowledgment
This work has been partly supported by the University of Piraeus Research Center. We also gratefully acknowledge the support of NVDIA Corporation for the donation of the Titan X Pascal GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Delibasis, K., Maglogiannis, I., Georgakopoulos, S., Kottari, K., Plagianakos, V. (2018). Assessing Image Analysis Filters as Augmented Input to Convolutional Neural Networks for Image Classification. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11139. Springer, Cham. https://doi.org/10.1007/978-3-030-01418-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-01418-6_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01417-9
Online ISBN: 978-3-030-01418-6
eBook Packages: Computer ScienceComputer Science (R0)