SMOWL is a biometric approach which employs automatic algorithm to verify or recognize the identity of a person based on his/her physiological characteristics. In general, a biometric identification system makes use of either physiological characteristics (such as a fingerprint, iris pattern, or face) or behavior patterns (such as hand-writing, voice, or key-stroke pattern) to identify a person. Because of human inherent protectiveness of his/her eyes, some people are reluctant to use eye identification systems. For this reason, SMOWL has chosen face recognition and its benefit of being a passive & non-intrusive system, to verify personal identity in a “natural” and friendly way.
Face recognition algorithms have two major parts: (1) face detection and normalization and (2) face identification. Algorithms that consist of both parts are referred to as fully automatic algorithms and those that consist of only the second part are called partially automatic algorithms. SMOWL is categorized as FULLY AUTOMATIC face recognition system which automatizes both detection and identification/verification tasks.
SMOWL face recognition process can be explained with a three-step procedure:
(1) Capture: a WebCam visual sensor gives SMOWL a “Biometric Signature” (image) of the individual.
(2) Characteristic extraction algorithm: a computer algorithm “normalizes” the biometric signature into a face representative feature vector. The normalization of the biometric signature gives us a “Normalized Signature” of the individual.
(3) Matching algorithm: a matcher compares the normalized signature with the set (or sub-set) of normalized signatures on the system's database and provides a "similarity score" that compares the individual's normalized signature with each signature in the database set (or sub-set).
Research & Challenges
Face recognition research still face challenge in some specific domains such as incident illumination changes, head pose or individual appearance (facial expression, hairstyle (include facial hair), cosmetics (including eyewear) and age).
SMOWL, supported by Vicomtech-Ik4 research center and its well-known background in this field, is actively working to reach the results achieved in fingerprint and iris matching systems, improving and updating its current automatic face recognition core.