Search

During the last two decades, satisfactory results have been obtained for face identification techniques based on frontal pose. However, face identification from uncontrolled pose remains a challenging open problem in biometric recognition. Recently, pose invariant techniques that exploit either 3D scans or 2D images of the same face to generate the corresponding 3D model have emerged. Even if they tolerate pose variability and lead to high identification scores, they have the drawback to be computationally intensive and/or require the cooperation of the individual to be identified. Hence, they are not appropriate for the interesting real-time application of video surveillance. In this paper, we propose a profile face identification method based on correspondence mapping of 2D frontal face images. Kernel canonical correlation analysis (KCCA) is used to learn changeover from the profile pose to the frontal one. To show the effectiveness of our approach, tests are performed on FERET database according to a protocol referred to as leave one out-like protocol (LOOLP). These tests demonstrate that it leads to enhanced scores comparatively to other 2D-based methods proposed in the literature. [ABSTRACT FROM AUTHOR]

Usually in the context of integrated control and real-time scheduling, quality of control improvement is mainly based on the dynamic measurement process and the system task scheduling parameters (i.e., sampling period, execution time). In this paper, a new feedback controller based on delay prediction is proposed to overcome the degradation of quality for multi-controller systems due to scheduling delays. A statistical analysis is performed to highlight the correlation between scheduling artifacts (delays and jitters) and quality of the control. It is stated that the input–output latency has a significant influence on the quality of control. Hence, it is proposed to reduce control impairments by using a prediction of the response time to update the output. A case study consisting of the control of three servo-motors is used to practically illustrate our statement. The consistency and effectiveness of the improvement are checked through the case of the control of three inverted pendulums. [ABSTRACT FROM AUTHOR]