Abstract
While most existing image recognition benchmarks consist of relatively high quality data, in the practical applications images can be affected by various types of distortions. In this paper we experimentally evaluate the extent to which image distortions affect classification based on HOG feature descriptors. In an experimental study based on several benchmark datasets and classification algorithms we evaluate the impact of Gaussian, quantization and salt-and-pepper noise. We examine both known and random types of distortion, and evaluate the possibility of applying distortions on training data and using denoising to mitigate the negative impact of distortions. Although presence of distortions significantly impede classification with the HOG features, in the paper we show how this negative effect can be greatly mitigated in practical realizations. Experimental results underpin our findings.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, Y., Guo, L., Jin, L., Huang, Q.: A novel feature extraction method using pyramid histogram of orientation gradients for smile recognition. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 3305–3308. IEEE (2009)
Bertozzi, M., Broggi, A., Del Rose, M., Felisa, M., Rakotomamonjy, A., Suard, F.: A pedestrian detector using histograms of oriented gradients and a support vector machine classifier. In: 2007 IEEE Intelligent Transportation Systems Conference, ITSC 2007, pp. 143–148. IEEE (2007)
Chuang, C.H., Huang, S.S., Fu, L.C., Hsiao, P.Y.: Monocular multi-human detection using augmented histograms of oriented gradients. In: 2008 19th International Conference on Pattern Recognition, ICPR 2008, pp. 1–4. IEEE (2008)
Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)
Cyganek, B.: Recognition of solid objects in images invariant to conformal transformations. In: Conference on Computer Recognition Systems CORES 2009. Advances in Soft Computing, vol. 57, pp. 247–255 (2009)
Cyganek, B.: Object Detection and Recognition in Digital Images: Theory and Practice. Wiley, Hoboken (2013)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image restoration by sparse 3D transform-domain collaborative filtering. In: Image Processing: Algorithms and Systems VI, vol. 6812, p. 681207. International Society for Optics and Photonics (2008)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. IEEE (2005)
Déniz, O., Bueno, G., Salido, J., De la Torre, F.: Face recognition using histograms of oriented gradients. Pattern Recogn. Lett. 32(12), 1598–1603 (2011)
Do, T.T., Kijak, E.: Face recognition using co-occurrence histograms of oriented gradients. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1301–1304. IEEE (2012)
Dodge, S., Karam, L.: Understanding how image quality affects deep neural networks. In: 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1–6. IEEE (2016)
Dutta, A., Veldhuis, R.N., Spreeuwers, L.J.: The impact of image quality on the performance of face recognition. In: 33rd WIC Symposium on Information Theory in the Benelux. Centre for Telematics and Information Technology (CTIT) (2012)
Ebrahimzadeh, R., Jampour, M.: Efficient handwritten digit recognition based on histogram of oriented gradients and SVM. Int. J. Comput. Appl. 104(9), 10–13 (2014)
Freeman, W.T., Roth, M.: Orientation histograms for hand gesture recognition. In: International Workshop on Automatic Face and Gesture Recognition, vol. 12, pp. 296–301 (1995)
Karahan, S., Yildirum, M.K., Kirtac, K., Rende, F.S., Butun, G., Ekenel, H.K.: How image degradations affect deep CNN-based face recognition? In: 2016 International Conference of the Biometrics Special Interest Group (BIOSIG), pp. 1–5. IEEE (2016)
Karami, E., Prasad, S., Shehata, M.: Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images. arXiv preprint arXiv:1710.02726 (2017)
Khan, N.Y., McCane, B., Wyvill, G.: SIFT and SURF performance evaluation against various image deformations on benchmark dataset. In: 2011 International Conference on Digital Image Computing Techniques and Applications (DICTA), pp. 501–506. IEEE (2011)
Kobayashi, T., Hidaka, A., Kurita, T.: Selection of histograms of oriented gradients features for pedestrian detection. In: International Conference on Neural Information Processing, pp. 598–607. Springer (2007)
Koziarski, M., Cyganek, B.: Image recognition with deep neural networks in presence of noise-dealing with and taking advantage of distortions. Integr. Comput.-Aided Eng. 24(4), 337–349 (2017)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Phillips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 22(10), 1090–1104 (2000)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012)
Suard, F., Rakotomamonjy, A., Bensrhair, A., Broggi, A.: Pedestrian detection using infrared images and histograms of oriented gradients. In: 2006 IEEE Intelligent Vehicles Symposium, pp. 206–212. IEEE (2006)
Tan, H., Yang, B., Ma, Z.: Face recognition based on the fusion of global and local HOG features of face images. IET Comput. Vis. 8(3), 224–234 (2013)
Vasiljevic, I., Chakrabarti, A., Shakhnarovich, G.: Examining the impact of blur on recognition by convolutional networks. arXiv preprint arXiv:1611.05760 (2016)
Wang, C.C.R., Lien, J.J.J.: AdaBoost learning for human detection based on histograms of oriented gradients. In: Asian Conference on Computer Vision, pp. 885–895. Springer (2007)
Watanabe, T., Ito, S., Yokoi, K.: Co-occurrence histograms of oriented gradients for pedestrian detection. In: Pacific-Rim Symposium on Image and Video Technology, pp. 37–47. Springer (2009)
Zhu, Q., Yeh, M.C., Cheng, K.T., Avidan, S.: Fast human detection using a cascade of histograms of oriented gradients. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1491–1498. IEEE (2006)
Acknowledgment
This work was supported by the Polish National Science Center under the grant no. 2014/15/B/ST6/00609 and the PLGrid infrastructure.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Bukała, A., Koziarski, M., Cyganek, B., Koc̨, O.N., Kara, A. (2020). The Impact of Distortions on the Image Recognition with Histograms of Oriented Gradients. In: Choraś, M., Choraś, R. (eds) Image Processing and Communications. IP&C 2019. Advances in Intelligent Systems and Computing, vol 1062. Springer, Cham. https://doi.org/10.1007/978-3-030-31254-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-31254-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31253-4
Online ISBN: 978-3-030-31254-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)