Biometrics of Asymmetrical Face

نویسنده

  • Leonid Kompanets
چکیده

Traditionally, in face authentication/identification methods the presumption concerning face/head symmetry is used, which is logical in terms of the next qualitative reduction of primary data to templates as well as not using the primary face images, for example, in advanced applications that concern creating techniques by means of which it is possible to reproduce the extraordinary complexity of skin, muscle, eye and hair movements that convey emotion, gesture, psychological state or in psycho-sociological applications. In the paper, new research direction called Biometrics of Asymmetrical Face is presented. Apart from the direct study of new biometric techniques types in traditional sense, the essential new problem in this direction is the ability of interpretation of untapped “subtle” primary face information in psychological constructs terms, for example, person’s cognition-psyche characteristics and integrated usage as biometrics in traditional understanding as well as psychological constructs. The new direction study is based on modern knowledge of face authentication/identification, functional brain asymmetry phenomena and ophthalmogeometry, knowledge of psychological testing of personnel types. This is an example of collective interpretation of physiological-behavioral biometrics and psychological constructs. The study is stimulated with modern interdisciplinary needs for human science development. In the paper, specifically, it is presented a new type of precise normalized model of a face called Czestochowa-face, in the sense suiting the specification of the problem of modern and prospect person’s authentication/identification techniques creation in biometrics. As soon as two new biometric techniques based on the Czestochowa-faces are created; the ophthalmogeometrical technique and the face asymmetry one will be partially researched. Also, attention has been drawn to interdisciplinary research context. The main developed original components of the techniques are the following: 1) A procedure of finding (discovering) a „truthful” vertical axis of a face. 2) A procedure of 2D normalization of a single frontal view of a face image using a unit called Muld. 3) A procedure of constructing a combine (two polar and one Cartesian) facial coordinate system based on the “truthful” vertical axis and a special virtual coordinate system for eyes area. 4) An algorithm of person’s ophthalmologic pattern visualization in the virtual coordinate system. 5) An algorithm of the synthesis of special facial pictures (left-left and right-right composites) for face asymmetry features evaluation. 6) An algorithm of the Czestochowa-face creation. 7) An algorithm of precise mapping and evaluating (the pseudo-information) similarity of a pair of compared facial elements or given element set in a holistic manner. 8) Some theses concerning the cognition-psyche and interdisciplinary interpretation of gained ophthalmogeometrical, face asymmetry and other information features. 9) (A procedure of special linear oversampling a part of a picture if the picture has low resolution.) Beside the first-hand usage, the new techniques may be employed in the areas of human-computer interaction, identification of cognition-psyche type of personality for personnel management, advanced education, and so on.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Fusing Face and Periocular biometrics using Canonical correlation analysis

This paper presents a novel face and periocular biometric fusion at feature level using canonical correlation analysis. Face recognition itself has limitations such as illumination, pose, expression, occlusion etc. Also, periocular biometrics has spectacles, head angle, hair and expression as its limitations. Unimodal biometrics cannot surmount all these limitations. The recognition accuracy ca...

متن کامل

Techniques and Recent Directions in Palmprint and Face Recognition

Face and palmprint are two biometric characteristics with the highest user-acceptance. This paper presents techniques used in palmprint and face recognition as well as techniques used in biometric fusion. Some recent research trends directions in palmprint and face recognitions are described, such as the face recognition in video and touchless hand biometrics. Keywords-biometrics; face recognit...

متن کامل

Bridging biometrics and forensics

This paper is a survey on biometrics and forensics, especially on the techniques and applications of face recognition in forensics. This paper describes the differences and connections between biometrics and forensics, and bridges each other by formulating the conditions when biometrics can be applied in forensics. Under these conditions, face recognition, as a non-intrusive and non-contact bio...

متن کامل

Fusion of Near Infrared Face and Iris Biometrics

In this paper, we present a method for fusing face and iris biometrics using single near infrared (NIR) image. Fusion of NIR face and iris modalities is a natural way of doing multi-model biometrics because they can be acquired in a single image. An NIR face image is taken using a high resolution NIR camera. Face and iris are segmented from the same NIR image. Face and iris features are then ex...

متن کامل

Biometrics and Face Recognition Techniques

Biometrics is a growing technology, which has been widely used in forensics, secured access and prison security. A biometric system is fundamentally a pattern recognition system that recognizes a person by determining the authentication by using his different biological features i.e. Fingerprint, retina-scan, iris scan, hand geometry, and face recognition are leading physiological biometrics an...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004