Forensic Gender Discrimination in Malaysian Population Using Machine Learning Methods

Lee, Loong Chuen; Adam, Muhammad Yusuf; Sanih, Siti Norfaraan Abd; Bohari, Nur Izzati

doi:10.1109/3ict51146.2020.9311988

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penelitian klasifikasi gender berbasis sidik jari dapat dilakukan secara manual maupun berbasis pengolahan citra dengan komputer. Penelitian secara manual dengan kaca pembesar diantaranya yang dilakukan oleh Singh [8], Lee, dkk., [9], Taduran dkk., [10], dan Redomero, dkk., [11].…”

Section: Gambar 1 Klas Sidik Jariunclassified

Penentuan Fitur Gender Pemilik Sidik Jari Berbasis Ketebalan Ridge

Suwarno

2022

SINTaKS

View full text Add to dashboard Cite

Sidik jari merupakan salah satu bentuk biometrik yangdigunakan sebagai sarana verifikasi maupun identifikasi. Sidikjari banyak digunakan untuk mengidentifikasi pelaku kejahatan,korban bencana alam maupun korban kecelakaan yang sulitdikenali. Penelitian yang dilaporkan pada tulisan ini bertujuanuntuk menentukan ciri sidik jari yang dapat digunakan sebagaipembeda gender pemiliknya. Apabila gender pemilik sidik jarisudah dapat diestimasi, maka proses identifikasi selanjutnya akanlebih tararah. Pendekatan yang digunakan pada penelitian iniadalah menghitung ketebalan alur (ridge) dari sidik jari.Ketebalan ridge dihitung dengan memanfaatkan pengolahan citrasecara digital. Pada bagian-bagian tertentu dari sidik jari dibacanilai-nilai piksel yang membentuk garis lurus setebal satu pikseldengan panjang 32 piksel. Dari piksel-piksel tersebut dihitungbanyaknya piksel hitam yang saling berdekatan yang merupakanpotongan melintang dari suatu ridge. Sampel sidik jari diambildari dataset NIST (National Institute of Standarts and Technology)sebanyak 100 sidik jari pria dan 100 sidik jari wanita. Dataset inisudah diberi label apakah sidik jari wanita atau sidik jari pria.Berdasarkan hasil penelitian ini ditemukan bahwa secara umumsidik jari wanita memiliki ketebalan ridge yang lebih kecildibandingkan dengan ridge pada sidik jari pria. Secara statistiksidik jari wanita memiliki ketebalan ridge dengan nilai mean ofmeans sebesar 2.7698 dan median of medians sebesar 2.0000.Sedangkan sidik jari pria memiliki ketebalan ridge dengan nilaimean of means sebesar 3.0287 dan median of medians sebesar2.5000. Berdasarkan nilai-nilai tersebut metode ini menghasilkanketepatan maksimal 65% untuk sidik jari wanita dan 60% untuksidik jari pria.

show abstract

Section: Gambar 1 Klas Sidik Jariunclassified

Penentuan Fitur Gender Pemilik Sidik Jari Berbasis Ketebalan Ridge

Suwarno

2022

SINTaKS

View full text Add to dashboard Cite

show abstract

“…This is the first work attempted on evaluating ethnic difference among Malaysian based ridge count of fingerprint using machine learning method. The sexual dimorphism of the fingerprint data has been demonstrated using descriptive statistics [26][27][28]. Moreover, it is also of particular interest to evaluate relative performance of NB and decision tree (i.e.…”

mentioning

confidence: 99%

Forensic Fingerprint Analysis using Self-Organizing Maps, Classification and Regression Trees and Naïve Bayes Methods

Lee¹,

Bohari²,

Sanih³

et al. 2022

IJCDS

View full text Add to dashboard Cite

Fingerprint is one type of physical evidence frequently encountered at a crime scene. It is useful in revealing identity of the culprit. However, poor quality latent fingerprint collected from a crime scene seldom makes an identification reliable. In practice, the identification is accomplished by matching a known print to an unknown print according to the types and locations of their minutiae features. When it is infeasible to conduct an identification, forensic scientist can attempt to predict the sex of donor of the latent fingerprint in order to narrow down the scope of searching of the suspect. In the context of forensic science, sexual dimorphism in ridge count has been studied for a few decades ago. Meanwhile, gender classification based on fingerprint images have been regularly reported in the field of computer science. Viewed from a practical perspective, image of a latent print collected from a real crime scene can be low in quality or even incomplete. Hence, this study has not considered image of fingerprint as input data but the number of diagonal ridge counted manually within a well-defined region, i.e. 25 centimeter squared. Firstly, the fingerprint data was explored using self-organizing maps method with respect to sexual dimorphism and ethnic difference. Next, Naïve Bayes (NB) and Classification and Regression Trees (CART) algorithms were, respectively, used to construct predictive model for discriminating gender based on the fingerprint data. A multitude of prediction models were constructed by considering tendigit, five-digit and one-digit samples, respectively, to predict gender by three races, i.e. Chinese, Indians and Malays; and the combined sub-population. Each of the models was validated using bootstrapping without replacement approach. Results showed that the single-digit samples produced accuracy rate slightly lower than that obtained using five-or ten-digit samples. Comparing to the global predictive model, ethnicity-specific models of Indian and Malay subjects showed slight improvement in external accuracy rate. Moreover, by considering all five digits of a particular hand as input data, NB tends to outperform CART. However, both NB and CART are comparable to each other when one-digit sample was considered as input data. In conclusion, SOM is useful for exploring sexual dimorphism of fingerprint data and NB outperforms CART in modelling of the fingerprint data.

show abstract

Forensic Gender Discrimination in Malaysian Population Using Machine Learning Methods

Cited by 2 publications

References 8 publications

Penentuan Fitur Gender Pemilik Sidik Jari Berbasis Ketebalan Ridge

Penentuan Fitur Gender Pemilik Sidik Jari Berbasis Ketebalan Ridge

Forensic Fingerprint Analysis using Self-Organizing Maps, Classification and Regression Trees and Naïve Bayes Methods

Contact Info

Product

Resources

About