A Study on Various Methods of Gender Identification Based on Fingerprints

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

532

A Study on Various Methods of Gender Identification Based on

Fingerprints

Ms. Ritu Kaur

, Mrs. Susmita Ghosh Mazumdar

, Mr. Devanand Bhonsle

1

M.tech Student, RCET Bhilai (C.G)

2_{Reader, ETC Department, RCET Bhilai (C.G)} 3_{Sr.Asst. Professor, EEE Department, SSCET Bhilai (C.G)}

[email protected] [email protected]

[email protected]

ABSTRACT- Within today’s environment of increased importance of security and organization, identification and authentication methods have developed into a key technology. Fingerprints are one of the most mature biometric technologies and are considered legitimate proofs of evidence in courts of law all over the world. This study highlights the various ridge related methods like fingerprint ridge count, ridge density, ridge thickness to valley thickness ration, ridge width and fingerprint patterns used for gender identification. Also, this study proposes, a frequency domain analysis of fingerprint instead of traditional ridge related analysis, an efficient technique that can be used for partitioning large biometric database during identification.

Keywords: fingerprints, fingerprint ridges and valleys, frequency domain analysis, gender identification.

I. INTRODUCTION

As authentication based systems are growing in demand, personal identification has become an absolute necessity. Personal identification has wide applications in security systems, video surveillance, reducing search space for huge database. A person can be identified by number of features such as face, height, body, shape, gait, voice etc. Sex is among the most important information that discriminates between individuals. As a practical example, if we can recognize suspect’s sex, it can both restrict its search between enrolled suspects to decrease decision time and increase its recognition performance.

Fingerprinting remains the best to establish personal identification and tracking criminals. Few researchers addressed the use of fingerprint for gender identification which will be more helpful in short listing the suspects. Gender recognition is an interesting problem that can be used to boost the performance of several important applications such as face recognition and video surveillance. Gender classification can be utilized as an indexing technique to reduce the search space for automatic and manual recognition techniques. Further, other areas such as human computer interaction also have many interesting applications ranging from automatically identifying gender of individuals to image search over the internet.

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

533

Fingerprints have some important characteristics that make them invaluable evidence in crime scene investigations:

i. A fingerprint is unique to a particular individual,

and no two fingerprints possess exactly the same set of characteristics.

ii. Fingerprints do not change over the course of

person’s lifetime (even after superficial injury to the fingers).

iii. Fingerprint patterns can be classified, and those

classifications then used to narrow the range of suspects.

Anil K. Jain, Sarat C. Dass, and Karthik Nandakumar [8], in July 2004, formulated a mathematical framework based on the Bayesian decision theory for integrating the soft biometric information with the output of the primary biometric system. They demonstrated that the utilization of ancillary user information like gender, height, and ethnicity can improve the performance of the traditional biometric systems like fingerprint. Although these soft biometric characteristics are not as permanent and reliable as the traditional biometric identifiers like fingerprint, they provide some information about the identity of the user that leads to higher accuracy in establishing the user identity. Experiments conducted on a database of 263 users show that the recognition performance of a fingerprint system can be improved significantly (5%) by using additional user information like gender, ethnicity, and height.

II. RELATED WORK TO DETECT GENDER USING

FINGERPRINTS

Studies so far carried out in sex determination used the inked fingerprints and their findings are based on the spatial domain analysis of ridges. Generally ridge related parameters such as fingerprint ridge count, ridge density, ridge thickness to valley thickness ration, ridge width and fingerprint patterns and pattern types were used for gender determination.

Nithin MD, Manjunatha B, Preethi DS, Balaraj BM [1] in 2011 presented a study with a goal to determine the gender based on finger ridge count within a well-defined area. Rolled fingerprints were taken from 550 subjects (275 men and 275 women) belonging to South Indian population all within the age range of 18-65 years. Results showed that women have a significantly higher ridge count than men. Application of Baye's theorem suggests that a fingerprint

possessing ridge density <13 ridges/25 mm2 is most likely

to be of male origin. Likewise, a fingerprint having ridge

count >14 ridges/25 mm2 are most likely to be of female

origin.

Murlidhar Reddy Sangam, Karumanchi Krupadanam, Kolla Anasuya [2], in 2011, presented a study that revealed that there is significant sex and bimanual differences in the distribution of the finger print pattern. Their study was undertaken to observe the distribution of finger print pattern in males and females, and to observe the bilateral asymmetry in the region of Andhra Pradesh. Whorls were of high frequency on thumb, index and ring fingers in males. But females presented high frequency of loops on all fingers expect ring finger. There is a significant bimanual difference. Whorls are more common in right hands. Arches and radial loops are more on left index finger. The study revealed that there were significant sex and bimanual differences in the distribution of the finger print pattern.

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

534

Dr. Sudesh Gungadin MBBS, MD [4] in 2007 conducted a study with an aim to establish a relationship between sex and fingerprint ridge density. The fingerprints were taken from 500 subjects (250 males and 250 females) in the age group of 18-60 years. After taking fingerprints, the ridges were counted in the upper portion of the radial border of each print for all ten fingers and mean value was calculated. The results have shown that a finger print ridge

of < 13 ridges/25 mm2 is more likely of male origin and

finger print ridge of > 14 ridges/25 mm2 is more likely of

female origin. It has been successful to support the hypothesis that women tend to have a statistically significant greater ridge density than men.

Ahmed Badawi, Mohamed Mahfouz, Rimon Tadross, Richard Jantz [5] proposed a Gender classification from fingerprints, which is an important step in forensic anthropology in order to identify the gender of a criminal and minimize the list of suspects search. A dataset of 10-fingerprint images for 2200 persons of different ages and gender (1100 males and 1100 females) was analyzed. Features extracted were; ridge count, ridge thickness to valley thickness ratio (RTVTR), white lines count, and ridge count asymmetry, and pattern type concordance. Fuzzy- C Means (FCM), Linear Discriminant Analysis (LDA), and Neural Network (NN) were used for the classification using the most dominant features. They obtained results of 80.39%, 86.5%, and 88.5% using FCM, LDA, and NN, respectively.

Dr. A.Bharadwaja, Dr.P.K.Saraswat, Dr.S.K.Aggarwal, Dr.P.Banerji, and Dr.S.Bharadwaja [6] in 2004 presented a study that reveals that there is an association between distribution of finger print (dermatoglyphic) pattern and blood groups. Their study was carried out on 300 students of different ABA blood groups of Medical College, Ajmer with two objectives, viz. (a) To study distribution of finger print pattern among the subjects having different ABO and Rh blood group and (b) Correlate any relation between their characters and blood groups. Male: female ratio was 2.4:1. Majority of the subjects (38.33%) in the study were

of blood group A followed by blood group B, A and AB of whom 95.67% were Rh-positive.

Acree, M. [7] in 1999 presented a study whose aim is to determine if women have significantly higher ridge density, hence finer epidermal ridge detail, than men by counting ridges that occur within a well defined space. If significant gender differences do exist then the likelihood of inferring gender from given ridge densities will be explored. Their study focused on 400 randomly picked ten-print cards representing 400 subjects. The demographic composition of this sample population represents 100 Caucasian males, 100 African American males, 100 Caucasian females and 100 African American females all within the age range of 18-67. Results show that women tend to have a significantly higher ridge density than men and that this trend is upheld in subjects of both Caucasian and African American descent (F = 81.96, P < 0.001). Application of Bayes' theorem suggests that a given fingerprint possessing

a ridge density of 11 ridges/25 mm2 or less is most likely to

be of male origin. Likewise a fingerprint having a ridge

density of 12 ridges/25 mm2 or greater is most likely to be

of female origin, regardless of race.

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

535

Frequency domain is a term used to describe the domain for analysis of mathematical functions or signals with respect to frequency, rather than time. A time-domain graph shows how a signal changes over time, whereas, a frequency-domain graph shows how much of the signal lies within each given frequency band over a range of frequencies. A given function or signal can be converted between the time and frequency domains with a pair of mathematical operators called a transform. The inverse Fourier transform converts the frequency domain function back to a time function. There are a number of different mathematical transforms which are used to analyse time functions and are referred to as "frequency domain" methods. These are the most common transforms, and the fields in which they are used:

 Fourier series – repetitive signals, oscillating

systems

 Fourier transform – non-repetitive signals,

transients

 Laplace transform – electronic circuits and control

systems

 Wavelet transform – digital image processing,

signal compression

 Z transform – discrete signals, digital signal

processing

IV. PROPOSED METHOD FOR GENDER IDENTIFICATION

Spatial and frequency domain approaches are two different approaches in image processing. Generally ridge related parameters such as fingerprint ridge count, ridge density, ridge thickness to valley thickness ration, ridge width and fingerprint patterns and pattern types were used for gender determination. All the methods proposed above are based on the fingerprint ridges and has given insight about the ridge parameters mentioned about but fails to give accurate method of measuring the parameters. In this paper, instead of traditional ridge related analysis, an attempt has been made to analyse the fingerprints in frequency domain and then based upon certain rules gender is identified.

Most of the spatial domain approaches involve more computations, whereas frequency domain approaches are more flexible and involve less computation.

A. Algorithm level Design

The algorithm level design of the proposed gender identification system is shown in fig-2:

Fig-2: Algorithm for the proposed Gender identification system

Fingerprints of an individual have been used as one of the vital parts of identification in both civil and criminal cases because of their unique properties of absolute identity. It is crucially important to explore new ways for biometric identification in the hopes of speeding up processes. The results of such improvements have far-reaching consequences for faster and better access control, as well as an enhanced utility of fingerprints in forensics.

B. System level Design

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

536

A fingerprint based gender identification system constitutes of digital images of fingerprint as its input which is then transformed into frequency domain, compared with the predetermined thresholds and finally, gender is declared. The fig-3 shows the block diagram of the proposed gender identification system by frequency domain analysis of fingerprints. The fingerprint image from the database can be applied as input to the system and then we have to obtain the fundamental frequency of various transforms and use them for gender classification. Threshold setting can be done manually by analysing the sample data. The above proposed method can be implemented using MATLAB.

V.

A

Once a person is identified as male or female, then any suitable biometric trait can be used for further classification. Identification of gender can also provide an important clue in various security and surveillance based applications.

Fingerprint patterns are genotypically determined and remain unchanged from birth till death. Fingerprints collected at a crime scene can be used to identify suspects, victims and other persons who touched the surface, fingerprint scans can be used to validate electronic registration, cashless catering and library access especially in schools and colleges.

VI. CONCLUSION

Fingerprint evidence is undoubtedly the most reliable and acceptable evidence till date in the court of law. Due to the immense potential of fingerprints as an effective method of identification an attempt has been made in the present work to analyse their correlation with gender of an individual. The traditional methods uses ridge related parameters to detect gender and not much work has been done to detect gender using frequency domain analysis. Hence, an attempt has been made by proposing a method that utilizes frequency domain analysis of the fingerprints.

In future, more work can be done in frequency domain to find different parameters and different transforms that can be applied in gender identification which will more accurate and suitable for all types of applications. This research can be further extended by enhancing the classifier using neural network and fuzzy logic tool box.

Gender identification can help effectively reduce the search time by limiting the subsequent searching stage to either male database or female database. Once a person is identified as male or female, then any suitable biometric trait can be used for further classification. Identification of gender can also provide an important clue in various security and surveillance based applications.

REFERENCES

[1] Nithin MD, Manjunatha B, Preethi DS, Balaraj BM “Gender differentiation by finger ridge count among South India Population” J FORENSIC LEG MED.2011FEB;18(2):79-81.EPUB 2011JAN 23 [2] Murlidhar Reddy Sangam, Karumanchi Krupadanam, Kolla Anasuya

“A Study of Finger Prints: Bilateral Asymmetry and Sex Difference in the Region of Andhra Pradesh” Journal of Clinical and Diagnostic Research. 2011 June, Vol-5(3): 597-600

[3] Ramanjit Kaur, Rakesh K. Garg “Determination Of Gender

Differences From Fingerprint Ridge Density In Two Northern Indian Populations” Problems of Forensic Sciences 2011, vol. LXXXV, 5– 10 © by the Institute of Forensic Research

[4] Dr. Sudesh Gungadin MBBS, MD "Sex Determination from Fingerprint Ridge Density" Internet Journal of Medical Update, Vol. 2, No. 2, Jul-Dec 2007.

[5] A. Badawi, M. Mahfouz, R. Tadross, and R. Jantz “Fingerprint-based

International Journal of Emerging Technology and Advanced Engineering

Website: www.ijetae.com (

ISSN 2250-2459

, Volume 2, Issue 4, April 2012)

537

[6] Dr. A.Bharadwaja, Dr.P.K.Saraswat, Dr.S.K.Aggarwal, Dr.P.Banerji, and Dr.S.Bharadwaja, "Pattern of finger prints in different ABO blood groups." Journal of Indian Academy of forensic medicine, vol 26(1), pp 6-9, March 2004.

[7] Acree, M. “Is there a gender difference in fingerprint ridge density?”

Forensic Science International 1999 May; 102 (1): 35-44.

[8] Anil K. Jain, Sarat C. Dass, and Karthik Nandakumar “Soft Biometric

Traits for Personal Recognition Systems” Proceedings of International Conference on Biometric Authentication, LNCS 3072, pp. 731-738, Hong Kong, July 2004

[9] Dr. Prateek Rastogi, Ms. Keerthi R Pillai “A study of fingerprints in relation to gender and blood group” J Indian Acad Forensic Med, 32(1), pp-11-14 ISSN 0971-097

[10] Monika Bhardwaj, Rajiv Joshi, Neelam Kamra and Rajni Chowdhary

“A Study on Fingerprint Loop-Ridge Count in Relation to Gender” J Life Sci, 3(2): 163-164 (2011)

[11] Michael D. Frick, Shimon K. Modi, Stephen J. Elliott, Ph.D., and Eric P. Kukula, Member IEEE “Impact of Gender on Fingerprint

Recognition Systems” 5th International Conference on Information Technology and Applications ICITA 2008 ISBN: 978-0-9803267-2-7 [12] Emilio Mordini And Sonia Massari “Body, Biometrics and Identity”

Bioethics ISSN 0269-9702 (print); 1467-8519 (online), Volume 22 Number 9 2008 p-p 488–498

AUTHORS

Ms. Ritu Kaur is currently pursuing Masters Degree program in Digital Electronics in Chhattisgarh Swami Vivekananda Technical University, India.

Mrs. Susmita Ghosh Mazumdar is currently working as a Reader in Rungta College of Engineering and Technology, in Chhattisgarh Swami Vivekananda Technical University, India.