Abstract
This paper presents an upright frontal face recognition system, aimed to recognize faces on machine readable travel documents (MRTD). The system is able to handle large image databases with high processing speed and low detection and identification errors. In order to achieve high accuracy eyes are detected in the most probable regions, which narrows search area and therefore reduces computation time. Recognition is performed with the use of eigenface approach. The paper introduces eigenface basis ranking measure, which is helpful in challenging task of creating the basis for recognition purposes. To speed up identification process we split the database into males and females using high - performance AdaBoost classifier. At the end of the paper the results of the tests in speed and accuracy are given.
Highlights
During two last decades the technologies of face detection and recognition have attracted considerable research interest. These technologies are used in biometric systems, border control systems, video surveillance, human-computer interface, access control systems, face expression recognition, content based image retrieval
Our system works with Machine Readable Travel Documents (MRTD)
machine readable travel documents (MRTD) portraits must conform the quality requirements contained in Doc 9303
Summary
During two last decades the technologies of face detection and recognition have attracted considerable research interest. Methods to detect faces can be divided into four main groups: knowledge-based methods, feature invariant approaches, template matching methods and appearance-based methods [1]. Nowadays the appearance-based methods gained most popularity due to their hit rate and speed [1] These methods don’t use a priori knowledge in the data that is present on the image. Later Viola and Jones present a much faster detector than any of their contemporaries [6] They use rectangular features instead of using pixels directly. In [11] AdaBoost classifier is applied to features proposed by Viola and Jones in [6] to detect faces. We have chosen the approach proposed by Baluja and Rowley in [12] for simplicity and efficiency: gender can be classified with the comparison of a small number of pixels in the image. The authors have run various experiments to prove that their approach outgoes competitors in performance and accuracy
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
