In the literature, there are some studies which investigate if there is a relationship between fingerprint and gender or not. In these studies, this relationship is examined based on some vectorial parts of fingerprints. The main problem in these studies is the lack of data, depending on ethnical background and country, and there is not an exact finding of true classification results. It is known that fingerprints show difference in males and females, and it is explained that women's line details are thin whereas men's line details are thick. However, the statistical studies, which have been made to prove the relationship between fingerprint and gender, have not investigated if the hypothesis is true for all ethnical backgrounds. In this study, we have examined if gender inference can be made only through fingerprint feature vectors, which belong to Turkish subjects, by using our database consisting of Naive Bayes, kNN, Decision Tree and Support Vector Machine learning algorithms. By using Naive Bayes algorithm, the success of the gender classification is found as 95.3%. This ratio has not been obtained before for "gender inference from fingerprint" in the literature. Therefore, this study can be useful for criminal cases.

No abstract

No abstract

ÖZETLiteratürde, parmak izinin belirli bir bölgesi analiz edilerek cinsiyet sınıflandırma üzerine istatistiksel analiz çalışmaları mevcuttur. Bu çalışmalarda parmak izi tepe çizgisi sayılarının kullanıldığı belirlenmiştir. Çalışmalar kısıtlı veriyle yapılmıştır. Kullanılan veri ırka veya ülkeye bağımlıdır. İşlemler de el ile yapılmıştır. Bu çalışmada, literatürde ilk kez parmak izi ve cinsiyet arasındaki ilişkiyi belirlemek için yapay sinir ağları modelleri ile parmak izinin tüm öznitelik vektörlerini kullanarak zeki bir model tanımlanmıştır. Daha sonra elde edilen sonuçlar sunulmuştur. Ön analiz çalışmalarımızda, parmak izlerinin değişken miktarda kullanılabilir veri içerdiği gözlenmiştir. Bu çalışmada kullanılan veri miktarı bu değerler göz önünde bulundurularak belirlenmiştir. Yaptığımız testlerde geliştirilen zeki sistemin başarı oranı %72 olarak elde edilmiştir. Sonuçlar parmak izi ve cinsiyet arasındaki ilişkinin yüksek olduğunu göstermektedir.Anahtar Kelimeler: Parmak izi, cinsiyet, sınıflandırma, biyometri, zeki model, yapay sinir ağı. GENDER CLASSIFICATION BASED ON ANN WITH USING FINGERPRINT FEATURE VECTORS ABSTRACTThere are statistical analysis studies on gender classification by analyzing a particular area of fingerprint in literature. In these studies it has been determined that ridge counts of fingerprint were used. The studies was performed with limited data. The data used depend on race or country. Also the processes were performed manually. In this study for the first time in the literature, an intelligent model have been identified using all feature vectors of fingerprint with artificial neural network models for determining the relationship between gender and fingerprint. Then results that have been obtained are presented. In our preliminary analysis studies, it has been observed that fingerprints contain a changeable amount of usable data. The quantity of data used in this study is determined by considering this amounts. Success rate of the developed intelligent system is obtained 72% in our tests. The results show that the relationship between fingerprint and gender is high.