The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The important issue in multi-class classification on support vector machines is the decision rule, which determines whether an input pattern belongs to a predicted class. To enhance the accuracy of multi-class classification, this study proposes a multi-weighted majority voting algorithm of support vector machine (SVM), and applies it to overcome complex facial security application. The proposed algorithm...
The challenge of facial biometrics is the decision rule of how to determine whether the claimant is the genuine user. It is an important issue that the decision rule affects the accuracy of performance. Therefore, the study proposes a breadth-first-based decision algorithm for facial biometrics. The proposed algorithm searches different graph paths to obtain a verified decision to accept or reject...
The issue of ownership of digital watermark is addressed in this paper. An audio watermarking scheme is presented where the biometric pattern of iris is used to generate the watermark that has a stamp of ownership. The watermark is embedded in the high-energy regions selectively in wavelet domain that makes the embedding process robust against signal processing attacks. The watermark extraction process...
As security is a major concern in present times, reliable authentication systems are in great demand. A biometric trait like the vascular pattern on the back of the hand of a person is unique and secure. A biometric system working on this principle often fails to authenticate a person either because of the varying hand posture or due to an injury altering the vein pattern. In this paper we propose...
Biometric authentication provides a high security and reliable approach to be used in security access system. However, this authentication method has not been widely implemented in a resource-constrained embedded system. In this project, we investigate a method of personal authentication based on infrared vein pattern in the back of the hand, targeted for embedded system which is implemented in Altera...
To provide personal services in a ubiquitous environment, it is necessary to identify users without giving a psychological pressure to them. This paper proposes a configuration of the sensor network used to identify a user based on his or her sole pressure distribution on a sensor mat that uses a hetero-core optical fiber. Specifically, it presents a filtering algorithm used to determine the pressure...
The individual privacy linking to the widespread use of personal information appears to be a new phenomenon for networked society. In a conventional biometrics enabled authentication system, the privacy remains a controversial topic. Biometric characteristics are indisputable and unique to an individual hence the compromise of the biometric template is permanent. Cancelable biometrics was introduced...
This paper presents a long distance person identification system based on height measurement and face recognition using web-camera without zoom-in/zoom-out. In this system, face detection determines if a target person entering the monitoring area or not. We use calibrated camera technique to compensate distortion images. Human height is then measured by the ratio with a reference point. The measured...
This paper presents a projection model to fuse the scores of a visual face verification system and an infrared face verification system. Essentially, the model consists of an arbitrarily number of linear projection vectors with randomly permuted elements. An equal error rate formulation is next adopted to learn the linear coefficients for projection. The learned model is consequently used for prediction...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.