Biometrics is the measurement and statistical analysis of individuals’

Biometrics is the measurement and statistical analysis of individuals’ physiological and behavioral features. A wide variety of systems requires reliable personal recognition schemes to either confirm or determine the identity of an individual requesting their services. Multi-biometrics are mandatory in the current context of large international biometric databases and to accommodate new emerging security demands. There are some distinctive and measurable features used to distinguish individuals known as Biometric identifiers. These identifiers include, but are not limited to fingerprint, face recognition and digital signature. In this report two biometric characteristics are used i.e. Face recognition and digital signature. Multi-biometric systems tend to integrate multiple identifiers to increase recognition accuracy. This is due to each biometric has its strengths and weaknesses. Face recognition and digital signature are still a challenge in many applications especially in surveillance and security systems.  The main goal of this report is to analyze different techniques of identifiers integration applied in the multi-biometric personal identification system.  This technical report proposes to use features extract using Histograms of Oriented Gradients (HOG) for face recognition and digital signature. By the end of our project, we will produce reliable multi-biometric system able to identify individuals accurately and in real-time. Such system will be helpful, for example, in access control to secured areas or electronic systems, or time and attendance management, and other applications. Finally, the multi-modal biometric technique may achieve good results with all security systems for digital signature and face recognition. The current initial results show that the HOG feature descriptor significantly performs target matching at an average of 100% accuracy ratio for face recognition together with digital signature. It outperforms existing feature sets with accuracy of % 84.25 for face only and 97.42% for digital signature only.


I'm Dianna!

Would you like to get a custom essay? How about receiving a customized one?

Check it out