Abstract
Periocular region has emerged as a key biometric trait with potential applications in the forensics domain. In this paper, we explore two convolutional neural network (CNN)-based approaches for gender classification using near-infrared images of the periocular region. In the first stage, our approaches automatically detect and extract left and right periocular regions. The first approach utilizes a domain-specific pre-trained CNN to extract deep features from the periocular images. A trained support vector machine (SVM) then utilizes these features to predict the gender information. The second approach employs an end-to-end classifier obtained by fine-tuning a pre-trained CNN on the periocular images. Performance evaluations have been carried out on three databases, which includes an in-house and two public databases. Local binary pattern and histogram of oriented gradient-based methods have been used as baseline methods to ascertain the effectiveness of the proposed approaches. Our results indicate that the proposed approaches achieve higher classification accuracy than the baseline methods, particularly on one of the public databases that contains a large number of non-ideal images. In addition, accuracy of the proposed approaches is consistently higher than the existing eyebrow feature-based method.
References
Merkow J, Jou B, Savvides M (2010) An exploration of gender identification using only the periocular region. In: IEEE international conference on biometrics: theory applications and systems, pp 1–5
Lyle JR, Miller PE, Pundlik SJ, Woodard DL (2012) Soft biometric classification using local appearance periocular region features. Pattern Recogn 45:3877–3885
Jain AK, Dass SC, Nandakumar K (2004) Can soft biometric traits assist user recognition? In: Defense and security, pp 561–572
Wang JG, Li J, Yau WY and Sung E (2010) Boosting dense sift descriptors and shape contexts of face images for gender recognition. In: Computer vision and pattern recognition—workshops, pp 96–102
Thomas V, Chawla NV, Bowyer KW, Flynn PJ (2007) Learning to predict gender from iris images. In: IEEE international conference on biometrics: theory, applications, and systems, pp 1–5
Shafey LE, Khoury E, Marcel S (2014) Audio-visual gender recognition in uncontrolled environment using variability modeling techniques. In: IEEE international joint conference on biometrics, pp 1–8
Lee L, Grimson WEL (2002) Gait analysis for recognition and classification. In: IEEE international conference on automatic face and gesture recognition, pp 148–155
Rattani A, Chen C, Ross A (2014) Evaluation of texture descriptors for automated gender estimation from fingerprints. In: European conference on computer vision. Springer, pp 764–777
Amayeh G, Bebis G, Nicolescu M (2008) Gender classification from hand shape. In: IEEE Computer Society conference on computer vision and pattern recognition workshops, pp 1–7
Dantcheva A, Elia P, Ross A (2015) What else does your biometric data reveal? A survey on soft biometrics. IEEE Trans Inf Forensics Secur 11(3):1–26
Ross A, Chen C (2011) Can gender be predicted from near-infrared face images? In: Image analysis and recognition, pp 120–129
Chen C, Ross A (2011) Evaluation of gender classification methods on thermal and near-infrared face images. In: International joint conference on biometrics (IJCB), pp 1–8
Park U, Ross A, Jain AK (2009) Periocular biometrics in the visible spectrum: a feasibility study. In: Biometrics: theory, applications and systems, pp 1–6
Alonso-Fernandez F, Bigun J (2015) A survey on periocular biometrics research. Pattern Recogn Lett 82:92–105
Phillips PJ, Flynn PJ, Scruggs T, Bowyer KW et al (2005) Overview of the face recognition grand challenge. In: International conference on computer vision and pattern recognition, pp 947–954
Castrillón-Santana M, Lorenzo-Navarro J, Ramón-Balmaseda E (2015) On using periocular biometric for gender classification in the wild. Pattern Recogn Lett 82:181–189
Dong Y. and Woodard DL (2011) Eyebrow shape-based features for biometric recognition and gender classification: a feasibility study. In: International joint conference on biometrics (IJCB), pp 1–8
Phillips PJ, Flynn PJ, Beveridge JR, Scruggs WT et al (2009) Overview of the multiple biometrics grand challenge. In: International conference on biometrics, pp 705–714
Viola P (2004) Robust real-time face detection. Int J Comput Vis 57:137–154
Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 806–813
Ozbulak G, Aytar Y, Ekenel HK (2016) How transferable are CNN-based features for age and gender classification? In: International Conference of the Biometrics Special Interest Group (BIOSIG), pp 1–6
Parkhi OM, Vedaldi A, Zisserman A (2015) Deep face recognition. In: British machine vision conference, pp 1–6
Cholakkal H, Johnson J, Rajan D (2016) Weakly supervised top-down salient object detection. arXiv preprint arXiv:1611.05345
Vapnik V (1998) Statistical learning theory. Wiley-Interscience, New York
Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27
Janocha K, Czarnecki WM (2017) On loss functions for deep neural networks in classification. CoRR arXiv:abs/1702.05659
Dago-Casas P, González-Jiménez D, Yu LL, Alba-Castro JL (2011) Single-and cross-database benchmarks for gender classification under unconstrained settings. In: IEEE international conference on computer vision workshops (ICCV workshops), pp 2152–2159
Sharma A, Verma S, Vatsa M, Singh R (2014) On cross spectral periocular recognition. In: IEEE international conference on image processing (ICIP), pp 5007–5011
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition, pp 886–893
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Russakovsky O, Deng J, Su H, Krause J et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115:211–252
Zheng L, Zhao Y, Wang S, Wang J, Tian Q (2016) Good practice in CNN feature transfer. CoRR arXiv:abs/1604.00133
Acknowledgements
The authors would like to acknowledge Jubin Johnson, PhD candidate from School of Computer Science and Engineering at NTU, Singapore, for his support and valuable suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Manyala, A., Cholakkal, H., Anand, V. et al. CNN-based gender classification in near-infrared periocular images. Pattern Anal Applic 22, 1493–1504 (2019). https://doi.org/10.1007/s10044-018-0722-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-018-0722-3