Abstract
Sex determination in forensic analysis involves individual examination of different sites of the skull and combination of these sites to understand their impact on the estimation results. Conventionally, forensic experts perform a stepwise combination of several skull region assessment parameters to determine the most important regions with regard to the sex estimation results. This paper introduces a novel group variable selection algorithm: Graph Laplacian Based Group Lasso with split augmented Lagrangian shrinkage algorithm (SALSA) to automatically learn from data by structuring the data into a set of disjointed groups and imposing a number of group sparsity to discover the salient groups which influence the sex determination results. In order to attain this, the skull is partitioned into smaller regions (local regions) using fuzzy c-means (FCM), which are further arranged into clusters as structured groups. Then, we implement the SALSA based group lasso algorithm to impose sparsity on the groups. Our experiments are conducted on 100 skull samples obtained from hospital kuala lumpur (HKL) and the best estimation result obtained is 84.5%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Afonso, M.V., Bioucas-Dias, J.M., Figueiredo, M.A.: An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems. IEEE Trans. Image Process. 20(3), 681–695 (2011)
Arigbabu, O.A., Liao, I.Y., Abdullah, N., Noor, M.H.M.: Can computer vision techniques be applied to automated forensic examinations? A study on sex identification from human skulls using head CT scans. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10114, pp. 342–359. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54190-7_21
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers Foundations and Trends\(^{\textregistered }\). Mach. Learn. 3(1), 1–122 (2011)
Buikstra, J.E., Ubelaker., D. H.: Standards for data collection from human skeletal remains. In: Proceedings of a Seminar at the Field Museum of Natural History, Arkansas Archaeology Research Series, vol. 44 (1994)
Friedman, J., Hastie, T., Tibshirani, R.: A note on the group lasso and a sparse group lasso. arXiv:1001.0736 [math, stat], p. 8 (2010)
Garcia, D.: Robust smoothing of gridded data in one and higher dimensions with missing values. Comput. Stat. Data Anal. 54(4), 1167–1178 (2010)
Garvin, H., Klales, A.: A validation study of the Langley et al. (2017) decision tree model for sex estimation. J. Forensic Sci. 63, 1243–1251 (2017)
Graw, M., Czarnetzki, A., Haffner, H.T.: The form of the supraorbital margin as a criterion in identification of sex from the skull: investigations based on modern human skulls. Am. J. Phys. Anthropol. 108, 91–96 (1999)
He, X., Niyogi, P.: Locality preserving projections. In: Neural Information Processing Systems, vol. 16, p. 153 (2004)
Hestenes, M.R.: Multiplier and gradient methods. J. Optim. Theory Appl. 4(5), 303–320 (1969)
Langley, N.R., Dudzik, B., Cloutier, A.: A decision tree for nonmetric sex assessment from the skull. J. Forensic Sci. 61(3), 743–751 (2017)
Luo, L., Chang, L., Liu, R., Duan, F.: Morphological investigations of skulls for sex determination based on sparse principal component analysis. In: Sun, Z., Shan, S., Yang, G., Zhou, J., Wang, Y., Yin, Y.L. (eds.) CCBR 2013. LNCS, vol. 8232, pp. 449–456. Springer, Cham (2013). https://doi.org/10.1007/978-3-319-02961-0_56
Pinto, S.C.D., Urbanová, P., Cesar, R.M.: Two-dimensional wavelet analysis of supraorbital margins of the human skull for characterizing sexual dimorphism. IEEE Trans. Inf. Forensics Secur. 11(7), 1542–1548 (2016)
Powell, M.J.: A method for non-linear constraints in minimization problems. In: UKAEA (1969)
Ren, J., Jiang, J., Wang, D., Ipson, S.S.: Fusion of intensity and inter-component chromatic difference for effective and robust colour edge detection. IET Image Process. 4, 294–301 (2010)
Scheuer, L.: Application of osteology to forensic medicine. Clin. Anat. 15(4), 297–312 (2002)
Selesnick, I.: L1-norm penalized least squares with SALSA. Connexions (2014). http://cnx.org/content/m48933/
Spradley, M.K., Jantz, R.L.: Sex estimation in forensic anthropology: skull versus postcranial elements. J. Forensic Sci. 56(2), 289–296 (2011)
Walker, P.L.: Sexing skulls using discriminant function analysis of visually assessed traits. Am. J. Phys. Anthropol. 136(1), 39–50 (2008)
Wang, Z., Ren, J., Zhang, D., Sun, M., Jiang, J.: A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos. Neurocomputing 287, 68–83 (2018)
Williams, B.A., Rogers, T.L.: Evaluating the accuracy and precision of cranial morphological traits for sex determination. J. Forensic Sci. 51(4), 729–735 (2006)
Yan, Y., Ren, J., Li, Y., Windmill, J., Ijomah, W.: Fusion of dominant colour and spatial layout features for effective image retrieval of coloured logos and trademarks. In: 2015 IEEE International Conference on Multimedia Big Data (BigMM), pp. 306–311 (2015)
Yan, Y., Ren, J., Sun, G., Zhao, H., Han, J., Li, X.: Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement. Pattern Recognit. 79, 65–78 (2018)
Yan, Y., Ren, J., Zhao, H., Sun, G., Wang, Z., Zheng, J.: Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos. Cogn. Comput. 10, 94–104 (2018)
Zheng, J., Liu, Y., Ren, J., Zhu, T., Yan, Y., Yang, H.: Fusion of block and keypoints based approaches for effective copy-move image forgery detection. Multidimens. Syst. Signal Process. 27, 989–1005 (2016)
Zhou, Y., Zeng, F.Z., Zhao, H.M., Murray, P., Ren, J.: Hierarchical visual perception and two-dimensional compressive sensing for effective content-based color image retrieval. Cogn. Comput. 8(5), 877–889 (2016)
Acknowledgement
This research is sponsored by the eScienceFund grant 01-02-12-SF0288, Ministry of Science, Technology, and Innovation (MOSTI), Malaysia. The project has received full ethical approval from the Medical Research & Ethics Committee (MREC), Ministry of Health, Malaysia (ref: NMRR-14-1623-18717) and from the University of Nottingham Malaysia Campus (ref: IYL170414). Iman Yi Liao would like to thank the National Institute of Forensic Medicine (NIFM), Hospital Kuala Lumpur, for providing the PMCT data, and is grateful to Dr. Ahmad Hafizam Hasmi (NIFM) and Ms. Khoo Lay See (NIFM) for their assistance in coordinating the data preparation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Arigbabu, O.A., Liao, I.Y., Abdullah, N., Noor, M.H.M. (2018). Novel Group Variable Selection for Salient Skull Region Selection and Sex Determination. In: Ren, J., et al. Advances in Brain Inspired Cognitive Systems. BICS 2018. Lecture Notes in Computer Science(), vol 10989. Springer, Cham. https://doi.org/10.1007/978-3-030-00563-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-00563-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00562-7
Online ISBN: 978-3-030-00563-4
eBook Packages: Computer ScienceComputer Science (R0)