Hybrid Biometric Based Person Identification Using Machine Learning

Abstract

When compared to the more traditional methods of authentication, biometric systems offer a much higher level of protection for a wide range of uses (like pin, passwords etc.). Various sectors of modern society can find use for biometric systems. Among these are authentication for computers, attendance tracking for businesses, financial transactions, safeguarding private information, securing access to buildings, and ensuring the safety of travellers at airports. Identifying and verifying individuals via their unique physical and behavioural characteristics is the primary function of the biometric system. Importance of biometric systems in modern society is analysed in this paper. Single-trait biometric user recognition is currently used, but it does not offer sufficient security for critical programmes. Multimodal biometric systems are used to get around these issues. Physical and behavioural characteristics, like fingerprints and DNA, signatures and fingerprints, etc., are all part of a multimodal biometric system's arsenal for authenticating users. In addition to the hard biometric features already mentioned (skin colour, age, height, hair colour, eye colour, gender, etc.), the use of a person's soft biometric traits is becoming increasingly common. While soft biometrics can be used to boost the efficiency of biometric systems that focus on other characteristics, they are not without their own set of drawbacks, such as a lack of permanence and distinctive behaviour. User authentication, security, and performance are all boosted by the work presented in this paper using Machine learning (F-SVM -Fuzzy-Support Vector Machine) model.

Digital Criminal Biometric Archives (DICA) and Public Facial Recognition System (FRS) for Nigerian criminal investigation using HAAR cascades classifier technique

“…Faces are scanned, looking for the stage-appropriate Haar traits. AdaBoost's machine learning technique is used to create both the features' weights and sizes as well as the features themselves [28], [29]. The learning method produces constants called weights.…”

“…Since information about known criminals is inputted and saved in the database, the DICA system is essentially an input/process/output (IPO) system. Human faces are first recognised in suspect images using Intel's Haarcascades_frontalface_default.xml algorithm, which is based on the Haar-like features suggested by [28] in the OpenCV library. The eyes, nose, and mouth are calculated as distinct face characteristics known as feature extraction, which are then recorded in the database as facial encodings.…”