Lips Identification using Fuzzy Based Triangular Feature Set
Abstract
Biometric traits are now highly explored by researchers to identify a person. This paper presents a biometric identifier, namely lips for personal identification. A Fuzzy based on Triangle Feature Set is applied to the lips verification system. This method demonstrates that the minutiae template of an user may be used to reconstruct the lips image of Computer Education and Training Society (CETS) students and staff members. The performance of the method is also reported. This paper proposes the concept of fixed number of triangles in the lips. It improves the performance of the method.
Keywords
Download Options
Introduction
Biometrics refers to metrics related to human characteristics and traits. Biometrics authentication is used as a form of identification and access control. Biometric identifiers are the distinctive, measurable characteristics used to label and describe individuals. Biometric identifiers are often categorized by physiological characteristics and behavioral characteristics. A human body posses several physiological characteristics that can serve as biometric features. Also a human being develops several unique behavioral traits which can also serve as biometric features. The various physiological characteristics that are generally used are face, iris, fingerprints, palm prints, hand geometry and voice. Automated biometric systems by including data obtained during these processes vastly improve the accuracy of the system. A good biometric is characterized by use of a feature that is highly unique. The chance of any two people having the same characteristic will be minimal, stable so that the feature does not change over time. This can be easily captured in order to provide convenience to the user, and prevent misrepresentation of the feature. This section is devoted to the description of the most common traits that are presently used for biometric purpose.
Lip is the tactile sensory organ constituting the visible portion of the mouth. Since the lip data can be captured at a distance, it represents a passive biometric as it requires no active user participation. The lip biometric lies on the area of uniqueness and circumvention.
Conclusion
A novel method for lip matching is analyzed. The lips are represented by the fuzzy feature that is local triangle feature set. The similarity between the fuzzy features is used to character the similarity between lips. A fuzzy similarity measurement for two triangles and extend it to construct a similarity vector including the triangle-level similarity in two lips are introduced. Finally, the FFM method maps a similarity vector pair to a normalized quantity which quantifies the overall image to image similarity within the real interval [0, 1]. The algorithm has been experimented and evaluated with the lips of CETS students and staff members’ database. Experimental results confirm that the algorithm works well with the nonlinear distortions. Here we found 95.37% of accuracy in matching. The proposed concept of fixed area and fixed number of triangles in the lips improves the performance of the triangularization method. The proposed system reduces the complexity of the local triangularization method. It also improves the accuracy.