Machine Learning in Forensic Anthropology: Sex Classification of Fingerprints

Abstract

A Fingerprint plays an important role in identifying an individual in forensic and criminal investigations. Fingerprint ridge density is considered one of the most important features for sex classification. The present study intends to classify sex using fingerprint ridge density through a machine learning model, i.e., Random Forest. A total of 2040 fingerprints of 204 participants (102 males and 102 females) were collected from the north Indian population using a standard methodology. Ridge density in the three topological areas of fingerprints, i.e., radial, ulnar, and proximal areas, was assessed. Taking all the areas into consideration, the data of fingerprint ridge density was used to train the Random forest algorithm. The training and testing of the model data were taken in a ratio of 70:30, respectively (training dataset = 1428; testing dataset = 612). Random forest provided an accuracy of 81.53% in sex classification using fingerprint ridge density. The paper discusses the evaluation report of the accuracy of the parameters of the Random forest in detail. The study concludes that the machine learning models, such as Random forest can be utilized for sex classification from fingerprint ridge density. The study proposes its direct application in forensic examinations, especially when there is no clue about the perpetrator, and the sex of the perpetrator can be predicted from fingerprints recovered from the crime scene using the present customized model.

Keywords

Machine learning / Fingerprint ridge density / Sex classification / Random forest / Forensic implications / Forensic anthropology

References

[1] Shekhar M, Patgiri R, Trivedi AK, Dhar P . A Critical Study of Biometrics and Their Fusion. In Proceedings of the 2023 International Conference on Intelligent Systems Advanced Computing and Communication (ISACC), Silchar, India, 3-4 February 2023; pp. 1-7. doi: 10.1109/ISACC56298.2023.10083801.

[2] Neumann C, Champod C, Solis RP, Egli N, Anthonioz A, Griffiths AB . Computation of likelihood ratios in fingerprint identification for configurations of any number of minutiæ. J. Forensic Sci. 2006, 521, 54-64. doi: 10.1111/j.1556-4029.2006.00327.x.

[3] Garg R, Singh RG, Singh A, Singh MP . Fingerprint Recognition using Convolution Neural Network with Inversion and Augmented Techniques. Syst. Soft Comput. 2024, 6, 200106. doi: 10.1016/j.sasc.2024.200106.

[4] Gungadin S. Sex Determination from Fingerprint Ridge Density. Internet J. Med. Update 2007, 2, 4-7.

[5] Redomero EG, Quirós JA, Rivaldería N, Alonso MC . Topological variability of fingerprint ridge density in a Sub-Saharan population sample for application in personal identification. J. Forensic Sci. 2013, 583, 592-600. doi: 101111/1556-402912092.

[6] Redomero EG, Alonso C, Romero E, Galera V . Variability of fingerprint ridge density in a sample of Spanish Caucasians and its application to sex determination. Forensic Sci. Int. 2008, 1801, 17-22. doi: 10.1016/j.forsciint.2008.06.014.

[7] Acree MA . Is there a gender difference in fingerprint ridge density? Forensic Sci. Int. 1999, 1021, 35-44. doi: 10.1016/S0379-0738(99)00037-7.

[8] Krishan K, Kanchan T, Ngangom C . A study of sex differences in fingerprint ridge density in a North Indian young adult population. J. Forensic Leg. Med. 2013, 204, 217-222. doi: 10.1016/j.jflm.2012.09.008.

[9] Nayak VC, Rastogi P, Kanchan T, Yoganarasimha K, Kumar GP, Menezes RG . Sex differences from fingerprint ridge density in Chinese and Malaysian population. Forensic Sci. Int. 2010, 197, 67-69. doi: 10.1016/j.forsciint.2009.12.055.

[10] Nithin MD, Manjunatha B, Preethi DS, Balaraj B . Gender differentiation by finger ridge count among South Indian population. J. Forensic Leg. Med. 2011, 182, 79-81. doi: 10.1016/j.jflm.2011.01.006.

[11] Eshak GA, Zaher JF, Hasan EI, Ewis AAEA . Sex identification from fingertip features in Egyptian population. J. Forensic Leg. Med. 2012, 201, 46-50. doi: 10.1016/j.jflm.2012.04.038.

[12] Kanchan T, Krishan K, Aparna K, Shyamsunder S . Footprint ridge density: A new attribute for sexual dimorphism. HOMO 2012, 636, 468-480. doi: 10.1016/j.jchb.2012.09.004.

[13] Ali FI, Ahmed AA . Sexual and topological variability in palmprint ridge density in a sample of Sudanese population. Forensic Sci. Int. Rep. 2020, 2, 100151. doi: 10.1016/j.fsir.2020.100151.

[14] Verma M, Agarwal S . Fingerprint Based Male-Female Classification. In Proceedings of the International Workshop on Computational Intelligence in Security for Information Systems CISIS’08; Corchado E, Zunino R, Gastaldo P, Herrero Á, Eds.; Advances in Soft Computing; Springer: Berlin/Heidelberg, Germany, 2009; Volume 53. doi: 10.1007/978-3-540-88181-0_32.

[15] Wang JF, Lin CL, Chang YH, Nagurka M, Yen CW, Yeh C . Gender Determination using Fingertip Features. Internet J. Med. Update 2008, 3, 22-28. doi: 10.4314/ijmu.v3i2.39838.

[16] Narayanan A, Sajith K . Gender Detection and Classification from Fingerprints Using Pixel Count. In Proceedings of the 3rd International Conference on Systems, Energy and Environment (ICSEE), Kannur, India, 12-13 July 2019; pp. 1-5. doi: 10.2139/ssrn.3444032.

[17] Athiraja A, Arunkumar G, Nandhakumar R . Automatic Latent Fingerprint Segmentation based on Orientation and Frequency Features. Int. J. Electr. Eng. Technol. 2019, 10, 77-87.

[18] Tiwari M, Mishra A . Different classifier approaches used for fingerprint classification. Ann. Comput. Sci. Inf. Syst. 2022, 33, 249-253. doi: 10.15439/2022R13.

[19] Berriche L. Comparative Study of Fingerprint-Based Gender Identification. Secur. Commun. Netw. 2022, 1626953. doi: 10.1155/2022/1626953.

[20] Cummins HH, Midlo C . Fingerprints Palms and Soles: An Introduction to Dermatoglyphics; Dover Publication: New York, NY, USA, 1961.

[21] Çorbacıoğlu ŞK, Aksel G . Receiver operating characteristic curve analysis in diagnostic accuracy studies: A guide to interpreting the area under the curve value. Turk. J. Emerg. Med. 2023, 234, 195-198. doi: 10.4103/tjem.tjem_182_23.

[22] Pisharody AS, Pargaonkar S, Kulkarni VY . Fingerprint classification and building a gender prediction model using random forest algorithm. Int. J. Knowl. Eng. Data Min. 2015, 3, 286. doi: 10.1504/IJKEDM.2015.074080.

[23] Jasem FM, Ahmed IT, Hammad BT . A comprehensive method for fingerprint classification based on GABOR filters and machine learning. Int. J. Saf. Secur. Eng. 2024, 14, 1775-1782. doi: 10.18280/ijsse.140612.

[24] Sharma S, Krishan K, Rani D, Mukhra M . Is fingerprint ridge density influenced by hand dimensions? Acta Biomed. 2022, 93, e2022315. doi: 10.23750/abm.v93i6.13548.