Abstract
In 3D face analysis research, automated classification to recognize gender and ethnicity has received an increasing amount of attention in recent years. Feature extraction and feature calculation have a fundamental role in the process of classification construction. In particular, the challenge of 3D low-quality face data, including inconsistent mesh numbers or holes, makes it difficult to extract and calculate facial features. To overcome this challenge, we propose a shape descriptor Scaling invariant harmonic wave kernel signature (SIHWKS) that is robust to scaling, topology and sampling and can effectively describe the global and local properties of 3D shapes simultaneously by involving two energy parameters. We extract a local nose region in the center of the face using isogeodesic stripes replacing full facial information, which has a lower probability of occlusion and lower calculation complexity. Actually, the local nose region is constrained by the skull so that it has high distinction gender and ethnicity property and stability property that are robust to 3D facial expression for gender and ethnicity classification. Compared with gender and ethnicity classification based on 2D deep-learning methods influenced by texture information, the proposed method does not require complex processes for model training and only considers the geometric information of the 3D nose region. In addition, to estimate the effectiveness of our point descriptor SIHWKS for gender and ethnicity classification, we compare our SIHWKS with four existing descriptors – global point signature (GPS), heat kernel signature (HKS), wave kernel signature (WKS) and harmonic wave kernel signature (HWKS) – on four databases, namely, FRGC2.0, Bosphorus3D, Facewarehouse and Asian Mongolian craniofacial. Finally, we perform experiments comparing our method with other recent existing classification methods. The experimental results show that our proposed method can achieve a higher accuracy rate for gender and ethnicity classification.
Similar content being viewed by others
References
Aflalo Y, Kimmel R, Raviv D (2013) Scale invariant geometry for nonrigid shapes[J]. SIAM J Imaging Sci
Altameemi A, Abbas HH (2019) Biological landmark Vs quasi-landmarks for 3D face recognition and gender classification[J]. Int J Electric Comput Eng 9 (5):1–9
Aubry M, Schlickewei U, Cremers D (2011) The wave kernel signature: a quantum mechanical approach to shape analysis. In: Computer vision workshop conf, pp 1626–1633
Ballihi L, Amor B, Daoudi M et al (2012) Geometric based 3D facial gender classification. In: International symposium on communications control and signal processing, pp 1–5
Ballihi L, Amor B et al (2013) Boosting 3-D-Geometric features for efficient face recognition and gender classification[J]. IEEE Trans Inf Foren Secur 7(6):1766–1779
Bekios-Calfa J, Buenaposada JM, Baumela L (2011) Revisiting linear discriminant techniques in gender recognition. IEEE Trans Pattern Anal Mach Intell 33(4):858–864
Berretti S, Bimbo D, Pala P (2010) 3D face recognition using isogeodesic stripes. IEEE Trans Pattern Anal Mach Intell 32(12):2162–2177
Bronstein AM, Bronstein MM, Castellani U et al (2010) Shrec2010: robust large-scale shape retrieval benchmark
Bronstein MM, Kokkinos I (2010) Scale-invariant heat kernel signatures for non-rigid shape recognition[C]. In: 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 1704–1711
Chenlei L, Zhongke W, Xingce W, Mingquan Z (2019) Constructing 3D facial hierarchical structure based on surface measurements. Multimedia Tools Appl 78(11):14753–14776
Drira H, Amor B, Srivastava A, Daoudi M (2009) A Riemannian analysis of 3D nose shapes for partial human biometrics. In: Computer vision conf, pp 459–451
Drira H, Amor BB, Srivastava A et al (2009) A riemannian analysis of 3D nose shapes for partial human biometrics. In: Computer vision conf. pp 1–8
Emambakhsh M, Evans A (2016) Nasal patches and curves for Expression-Robust 3D face recognition. IEEE Trans Pattern Anal Mach Intell 1:12–19
Gilani SZ, Shafait F, Mian A (2013) Biologically significant facial landmarks: how significant are they for gender classification. In: Digital image computing conf, pp 1–8
Guo G, Mu G (2010) A study of large-scale ethnicity estimation with gender and age variations. In: IEEE Computer society conference on computer vision and pattern recognition workshops, pp 79–86
Guo G, Mu G (2010) A study of large-scale ethnicity estimation with gender and age variations. In: IEEE Computer society conference on computer vision and pattern recognition workshops, pp 79–86
Han H, Otto C, Liu X, Jain A (2015) Demographic estimation from face images: Human vs. machine performance. IEEE Trans Pattern Anal Mach Intell 37(6):1148–1161
Han X, Ugail H, Palmer I (2009) Gender classification based on 3d face geometry features using SVM. In: Cyberworlds conf, pp 114–118
Hawraa A, Yulia H et al (2018) A 3D morphometric perspective for facial gender analysis and classification using geodesic path curvature features. Comput Vis Media 4(1):1–16
Hosoi S, Takikawa E, Kawade M (2004) Ethnicity estimation with facial images. In: Automatic face and gesture recognition conf, pp 195–200
Hu J, Hua J (2009) Salient spectral geometric features for shape matching and retrieval. Vis Comput 25(7):667–675
Huang D, Ding H, Wang C et al (2014) Local circular patterns for multi-modal facial gender and ethnicity classification. Image Vis Comput 32(12):1181–1193
Li H, Li S, Wu X et al (2018) Scale-Invariant Wave kernel signature for Non-Rigid 3D shape retrieval. In: Big data and smart computing conf
Lian HC, Lu BL, Talikawa E, Hosoi S (2005) Gender recognition using a min-max modular support vector machine. In: Natural computation conf
Lu X, Jain AK (2004) Ethnicity identification from face images. In: SPIE international symposium on defense and security: biometric technology for human identification, pp 114–123
Lu H, Lin H (2007) Gender recognition using adaboosted feature. In: IEEE Natural computation conf
Lv C, Wu Z, Zhang D et al (2018) 3D Nose shape net for human gender and ethnicity classification. Pattern Recognit Lett
Moeini A, Moeini H (2015) Pose-invariant gender classification based on 3D face reconstruction and synthesis from single 2D image. Electron Lett 51 (10):760–762
Mostafa E, Farag A, Shalaby A et al (2013) Long term facial parts tracking in thermal imaging for uncooperative emotion recognition. In: IEEE 6Th international conference on BTAS
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans PAMI 24(7):971–987
Ovsjanikov M, Sun J, Guibas L (2008) Global intrinsic symmetries of shapes. Comput Graphics Forum 27:1341–1348
Ra PA, Shaogang GB, Michael W (1991) A Eigenfaces for recognition
Ranjan R, Patel VM, Chellappa R (2019) Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans Pattern Anal Mach Intell (PAMI) 41(1):121–135
Ren J, Poulenard A, Wonka P et al (2018) Continuous and orientation-preserving correspondences via functional maps. In: SIGGRAPH Asia, pp 1–16
Savelonas MA, Pratikakis I, Sfikas K (2015) An overview of partial 3D object retrieval methodologies[J]. Multimed Tools Appl 74(24):11783–11808
Shakhnarovich G, Viola PA, Moghaddam B (2002) A unified learning framework for real time face detection and classification. In: Automatic face and gesture recognition conf
Sol J, Dodson K, Scharcanski J (2017) Face recognition based on geodesic distance approximations between multivariate normal distributions. In: Imaging systems and techniques conf
Sun J, Ovsjanikov M, Guibas L (2009) A concise and provably informative multi-scale signature based on heat diffusion. Comput Graphics Forum 28:1383–1392
Ter Haar FB, Remco C, Veltkamp A (2009) 3D face matching framework for facial curves. Graph Model 71(2):77–91
Tian Q, Chen S (2016) Joint gender classification and age estimation by nearly orthogonalizing their semantic spaces[J]. Image Vis Comput 69
Tokola R, Mikkilineni A, Boehnen C. (2015) 3D face analysis for demographic biometrics. In: International conference on biometrics, pp 201–207
Wagner A, Wright J, Ganesh A, Zhou Z, Ma Y (2009) Towards a practical face recognition system: Robust registration and illumination by sparse representation. In: IEEE conference on computer vision and pattern recognition, pp 597–604
Wang C, Deng C, Wang S (2020) Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost. Pattern Recognit Lett
Xia B, Amor B, Daoudi M, Gender Joint (2017) Ethnicity and age estimation from 3D faces: An experimental illustration of their correlations. Image Vis Comput 64:90–102
Xia B, Amor B, Drira H, Daoudi M, Ballihi L (2015) Combining face averageness and symmetry for 3D based gender classification. Pattern Recognit 48(3):746–758
Xia B, Amor B, Drira H et al (2013) Gender and 3D facial symmetry: What’s the relationship. In: Workshops on automatic face and gesture recognition conf, vol 5, pp 1–6
Zhang J, Cai H, Guo Y et al (2020) Landmark detection and 3D face reconstruction for caricature using a nonlinear parametric model. Comput Vis Pattern Recognit
Zhang D et al (2020) 3D skull and face similarity measurements based on a harmonic wave kernel signature. Vis Comput 7:142–156
Zhao HY (2012) 3D facial gender classification based on multi-angle LBP feature. Acta Automatica Sinica 38(9):1544
Acknowledgements
We thank the National Natural Science Foundation of China (No. 61972041, No. 62072045), National Key Cooperation between the BRICS of China (No. 2017YFE0100500), National Key R&D Program of China (No. 2017YFB1002604 and No. 2017YFB1402105), National Natural Science Foundation of China (No. 62102213), and Young Middle-aged Scientific Research Foundation of Qinghai Normal University (No. KJQN2021004). We also thank the facial database providers (FRGCv2.0, Bosphorus3D and FaceWareHouse) and the method code provider in GitHub.
Funding
This work is partially supported by the National Natural Science Foundation of China (No. 61972041, No. 62072045), National Key Cooperation between the BRICS of China (No. 2017YFE0100500), National Key R&D Program of China (No. 2017YFB1002604 and No. 2017YFB1402105), National Natural Science Foundation of China (No. 62102213), and Young Middle-aged Scientific Research Foundation of Qinghai Normal University (No. KJQN2021004).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This study was funded by Beijing Normal University, Beijing, China, and the Key Laboratory of Digital Protection of Cultural Heritage and Virtual Reality, Beijing, China.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, N., Zhang, D., Wang, X. et al. Gender and ethnicity classification of the 3D nose region based on scaling invariant harmonic wave kernel signature. Multimed Tools Appl 82, 41791–41811 (2023). https://doi.org/10.1007/s11042-023-14750-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14750-1