Ear Recognition Based on Improved Features Representations

  • Hakim DoghmaneEmail author
  • Hocine Bourouba
  • Kamel Messaoudi
  • El Bey Bournene
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 146)


This paper presents an ear recognition framework based on an improved representation of multi-bag of visual features model, which relies on significantly Binarized Statistical Image Features, clustering algorithm and Spatial Pyramid Histogram decomposition method. The following steps can enhance the recognition accuracy. Firstly, the Binarized Statistical Image Features is used to capture the texture information in ear image. Secondly, the multi bag-of visual features dictionary is learned from the training image responses in the feature space, using K-means algorithm. Thirdly, the spatial pyramid histogram of horizontal decomposition is applied to obtain local ear feature descriptors. Next, the histograms obtained are normalized. Then, the global representation of the ear image is obtained by concatenating all histograms calculated at each level. After that, the discriminant representation of ear image is constructed, using kernel Fisher discriminant analysis. Finally, the k-nearest neighbor and the support vector machine classifiers are used for ear identification. The experimental results achieve average rank-1 recognition accuracy of 97.81%, 97.91% and 99.20%, respectively, in the IIT-Delhi-1, IIT-Delhi-2 and USTB-1 publicly available database. This shows that the proposed approach provides a significant improvement performance over the state-of-the-art in terms of accuracy.


Ear recognition Spatial pyramidal histogram (SPH) Multi bag of features KNN SVM 


  1. 1.
    Singh, D., Singh, S.K.: A survey on human ear recognition system based on 2D and 3D ear images. Open J. Inf. Secur. Appl. 1(2) (2014)CrossRefGoogle Scholar
  2. 2.
    Nanni, L., Lumini, A.: Fusion of color spaces for ear authentication. Pattern Recognit. 42(9), 1906–1913 (2009)zbMATHCrossRefGoogle Scholar
  3. 3.
    Ansari, S., Gupta, P.: Localization of ear using outer helix curve of the ear. In: Proceedings of the International Conference on Computing: Theory and Applications (ICCTA’07) (2007)Google Scholar
  4. 4.
    Islam, S.M.S., Bennamoun, M., Davies, R.: Fast and fully automatic ear detection using cascaded Adaboost. In: IEEE Workshop on Applications of Computer Vision (2008)Google Scholar
  5. 5.
    Yuan, L., Zhang, F.: Ear detection based on improved Adaboost algorithm. In: Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Boading, vol. 4, pp. 2414–2417 (2009)Google Scholar
  6. 6.
    Emeršič, Ž., Štruc, V., Peer, P.: Ear recognition: more than a survey. Neurocomput. J. 255, 26–39 (2017)CrossRefGoogle Scholar
  7. 7.
    Zhang, H., Mu, Z.: Compound structure classifier system for ear recognition. In: Proceedings of the IEEE International Conference on Automation and Logistics (ICAL), pp. 2306–2309 (2008)Google Scholar
  8. 8.
    Benzaoui, A., Hadid, A., Boukrouche, A.: Ear biometric recognition using local texture descriptors. J. Electron. Imaging 23(5), 0530081–05300812 (2014)CrossRefGoogle Scholar
  9. 9.
    Benzaoui, A., Adjabi, I., Boukrouche, A.: Experiments and improvements of ear recognition based on local texture descriptors. J. Opt. Eng. 56(4), 0431091–04310913 (2017)CrossRefGoogle Scholar
  10. 10.
    Prakash, S., Grupta, P.: An efficient ear recognition technique invariant to illumination and pose. Telecommun. Syst. 52(3), 1435–1448 (2013)CrossRefGoogle Scholar
  11. 11.
    Doghmane, H., et al.: A novel discriminant multi-scale representation for ear recognition. Int. J. Biom. 11(1), 50–66 (2019)CrossRefGoogle Scholar
  12. 12.
    Kumar, A., Chan, T.-S.T.: Robust ear identification using sparse representation of local texture descriptors. Pattern Recogn. 46(1), 73–85 (2013)CrossRefGoogle Scholar
  13. 13.
    Galdamez, P., Ganzalez, A., Ramon, M.: Ear recognition using a hybrid approach based a neural networks. In: Proceedings of the International Conference on Information Fusion, pp. 1–6 (2014)Google Scholar
  14. 14.
    Pflug, A., Paul, P.N., Busch, C.: A comparative study on texture and surface descriptors for ear biometrics. In: Proceedings of the International Carnhan Conference on Security Technology, pp. 1–6. IEEE (2014)Google Scholar
  15. 15.
    Huang, H., Liu, J., Feng, H., He, T.: Ear recognition based on uncorrelated local Fisher discriminant analysis. Neurocomputing 74, 3103–3113 (2011)CrossRefGoogle Scholar
  16. 16.
    Kannala, J., Esa, R.: Bsif: binarized statistical image features. In: Proceedings IEEE International Conference on Pattern Recognition (ICPR), pp 1363–1366, Tsukuba, Japan (2012)Google Scholar
  17. 17.
    Foncubierta-Rodríguez, A., Depeursinge, A., Müller, H.: Using multiscale visual words for lung texture classification and retrieval. Medical Content-Based Retrieval for Clinical Decision Support, pp. 69–79. Springer, Berlin, Heidelberg (2012)CrossRefGoogle Scholar
  18. 18.
    Li, Z., Imai, J.I., Kaneko, M.: Robust face recognition using block-based bag of words. In: 20th International Conference on Pattern Recognition (ICPR), pp. 1285–1288. IEEE (2010)Google Scholar
  19. 19.
    Triggs, B., Jurie, F.: Creating efficient codebooks for visual recognition. ICCV 1, 604–610 (2005)Google Scholar
  20. 20.
    Bourouba, H., Doghmane, H., Benzaoui, A., Boukrouche, A.: Ear recognition based on multi-bags-of-features histogram. In: Proceedings of the 3rd International Conference on Control, Engineering and Information Technology (CEIT), pp. 1–6 (2015)Google Scholar
  21. 21.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178. IEEE Computer Society (2006)Google Scholar
  22. 22.
    Kumar, A.: IIT Delhi ear image database version1.0. New Delhi, India (2007).
  23. 23.
    Mu, Z.: USTB ear image database. Beijing, China (2009).
  24. 24.
    Basit, A., Shoaib, M.: A human ear recognition method using non-linear curvelet feature subspace. Int. J. Comput. Math. 91(3), 616–624 (2014)zbMATHCrossRefGoogle Scholar
  25. 25.
    Chan, T.S., Kumar, A.: Reliable ear identification using 2-D quadrature filters. Pattern Recognit. Lett. 33(14), 1870–1881 (2012)CrossRefGoogle Scholar
  26. 26.
    Kumar, A., Wu, C.: Automated human identification using ear imaging. Pattern Recognit. 45(3), 956–968 (2012)CrossRefGoogle Scholar
  27. 27.
    Mamta, M.H.: Robust ear based authentication using local principal independent components. Expert Syst. Appl. 40(16), 6478–6490 (2013)CrossRefGoogle Scholar
  28. 28.
    Omara, I., et al.: A novel geometric feature extraction method for ear recognition. Expert Syst. Appl. 65, 127–135 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Hakim Doghmane
    • 1
    Email author
  • Hocine Bourouba
    • 1
  • Kamel Messaoudi
    • 2
  • El Bey Bournene
    • 3
  1. 1.Université 8 Mai 1945 GuelmaGuelmaAlgeria
  2. 2.Mohamed Cherif Messaadia UniversitySouk-AhrasAlgeria
  3. 3.LE2I LaboratoryBurgundy UniversityDijonFrance

Personalised recommendations