Ear Alignment Based on Convolutional Neural Network

  • Li YuanEmail author
  • Haonan Zhao
  • Yi Zhang
  • Zeyu Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)


The ability of biometric systems has recently been dramatically improved by the emergency of deep learning. In the process of ear verification, the accuracy is often lower than expected because of the influence of pose variation and occlusion. In this paper, we propose a novel ear alignment approach. According to the morphological characteristics and the geometric characteristics of the ear, we define six key points on the ear, three located in the inner ear region, and three located on the outer contour of the ear. In order to detect these key points on the ear image automatically, we train a cascaded convolutional neural network using our newly released USTB-Helloear database. Then the alignment of the test ear image is accomplished by radiological transformation which will minimize the mean square error of the six key points between the test image and the template image. Experimental results show that using ear alignment, the accuracy of the ear verification system can be improved.


Ear verification Cascaded convolutional neural network Ear alignment USTB-Helloear 



This article is supported by the National Natural Science Foundation of China (Grant No. 61300075).


  1. 1.
    Nixon, M.S., Bouchrika, I., Arbab-Zavar, B., et al.: On use of biometrics in forensics: gait and ear. In: 2010 European Signal Processing Conference, pp. 1655–1659. IEEE (2010)Google Scholar
  2. 2.
    Huang, H., Liu, J., Feng, H., et al.: Ear recognition based on uncorrelated local Fisher discriminant analysis. Neurocomputing 74(17), 3103–3113 (2011)CrossRefGoogle Scholar
  3. 3.
    Lakshmanan, L.: Efficient person authentication based on multi-level fusion of ear scores. IET Biometrics 2(3), 97–106 (2013)CrossRefGoogle Scholar
  4. 4.
    Mu, Z.: Robust classification for occluded ear via Gabor scale feature-based non-negative sparse representation. Opt. Eng. 53(6), 061702 (2014)Google Scholar
  5. 5.
    Taigman, Y., Yang, M., Ranzato, M., et al.: DeepFace: closing the gap to human-level performance in face verification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708. IEEE Computer Society (2014)Google Scholar
  6. 6.
    Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891–1898. IEEE Computer Society (2014)Google Scholar
  7. 7.
    Sun, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification, vol. 27, pp. 1988–1996 (2014)Google Scholar
  8. 8.
    Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: Computer Vision and Pattern Recognition, pp. 2892–2900. IEEE (2015)Google Scholar
  9. 9.
    Emeršič, Ž., Štruc, V., Peer, P.: Ear recognition: more than a survey. Neurocomputing 255, 26–39 (2017)Google Scholar
  10. 10.
    Yuan, L., Mu, Z., Liu, L.: Ear recognition based on kernel principal component analysis and support vector machine. J. Eng. Sci. 28(9), 890–895 (2006)Google Scholar
  11. 11.
    Gao, S., Mu, Z., Yuan, L., et al.: Normalization of ear image based on active shape model. In: National Conference on Image and Graphics, p. 4 (2006)Google Scholar
  12. 12.
    Tian, Y., Fan, W.: Ear recognition based on fusion of scale invariant feature transform and geometric feature. J. Opt. 28(8), 1485–1491 (2008)Google Scholar
  13. 13.
    Tian, L., Mu, Z.: Ear recognition based on deep convolutional network. In: International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, pp. 437–441. IEEE (2017)Google Scholar
  14. 14.
    Zhang, Y., Mu, Z., Yuan, L., et al.: Ear verification under uncontrolled conditions with convolutional neural networks. IET Biometrics 7, 185–198 (2018)Google Scholar
  15. 15.
    Zhang, Y., Mu, Z., Yuan, L., Yu, C., Liu, Q.: USTB-Helloear: a large database of ear images photographed under uncontrolled conditions. In: Zhao, Y., Kong, X., Taubman, D. (eds.) ICIG 2017. LNCS, vol. 10667, pp. 405–416. Springer, Cham (2017). Scholar
  16. 16.
    Qi, N., Li, L., Zhao, W.: Chinese adult auricular morphology measurement and classification. Tech. Acoust. 29(5), 518–522 (2010)Google Scholar
  17. 17.
    Dai, J., Li, Y., He, K., et al.: R-FCN: object detection via region-based fully convolutional networks (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina
  2. 2.School of Artificial IntelligenceHebei University of TechnologyTianjingChina

Personalised recommendations