This paper presents a novel illumination normalization approach for face recognition under varying lighting conditions. In the proposed approach, a discrete cosine transform (DCT) is employed to compensate for illumination variations in the logarithm domain. Since illumination variations mainly lie in the low-frequency band, an appropriate number of DCT coefficients are truncated to minimize variations under different lighting conditions. Experimental results on the Yale B database and CMU PIE database show that the proposed approach improves the performance significantly for the face images with large illumination variations. Moreover, the advantage of our approach is that it does not require any modeling steps and can be easily implemented in a real-time face recognition system.

In this paper, an efficient method for high-speed face recognition based on the discrete cosine transform (DCT), the Fisher's linear discriminant (FLD) and radial basis function (RBF) neural networks is presented. First, the dimensionality of the original face image is reduced by using the DCT and the large area illumination variations are alleviated by discarding the first few low-frequency DCT coefficients. Next, the truncated DCT coefficient vectors are clustered using the proposed clustering algorithm. This process makes the subsequent FLD more efficient. After implementing the FLD, the most discriminating and invariant facial features are maintained and the training samples are clustered well. As a consequence, further parameter estimation for the RBF neural networks is fulfilled easily which facilitates fast training in the RBF neural networks. Simulation results show that the proposed system achieves excellent performance with high training and recognition speed, high recognition rate as well as very good illumination robustness.

No abstract

No abstract

No abstract

Abstract-This paper focuses on energy-efficient packet transmission with individual packet delay constraints. The optimal offline scheduler (vis-à-vis total transmission energy), assuming information of all packet arrivals before scheduling, was developed by Zafer, et al. (2005) and Chen et al. (2006). This paper shows that when packet inter-arrival times are identically and independently distributed (i.i.d.), the resulting optimal transmission durations of packets m and M − m + 1, m ∈ [1, · · · , M ], M ≥ 1, are identically distributed. This symmetry property leads to a simple and exact solution of the average packet delay under the optimal offline schedule. Two heuristic online scheduling algorithms, which assume no future arrival information, are then studied. These online schedulers are compared with the optimal offline scheduler in terms of delay and energy performance via analysis and simulations. While both online schedulers are inherently inferior, one online scheduler is shown to achieve a comparable energy performance to the optimal offline scheduler in a wide range of scenarios.

This study examined the distribution pattern of Aggregatibacter actinomycetemcomitans serotypes in the subgingival plaque of subjects residing in the United States. A. actinomycetemcomitans was identified in 256 subgingival plaque samples from 161 subjects. For 190 of the 256 samples, the total cultivable bacteria and selected periodontal pathogenic species were determined. A. actinomycetemcomitans isolates were confirmed by a16S rDNA-based PCR analysis, genotyped by arbitrarily-primed PCR, and serotyped by PCR analysis of serotype-specific gene clusters. A total of 82 distinct A. actinomycetemcomitans strains were identified. The serotype distribution pattern of the strains was 21 (25.6%) serotype a, 12 (14.6%) b, 41 (50%) c, 6 (7.3%) e, 1 (1.2%) f, and 1 (1.2%) non-typeable. For 14 subjects where multiple colonies of A. actinomycetemcomitans were identified, 11 subjects (78.6%) were each infected by a single serotype, while the remaining three subjects (21.3%) were each infected by two serotypes of A. actinomycetemcomitans. There was an inverse relationship between the level of cultivable A. actinomycetemcomitans and Porphyromonas gingivalis. Within subgingival plaque of study cohort A. actinomycetemcomitans serotype c was the dominant serotype and comprised 50% of all strains, followed by (in order of detection frequency) serotypes a and b. Serotypes d, e, and f strains were either not detected or less frequently found. Serotype distribution patterns of subgingival A. actinomycetemcomitans may vary among subjects of different race orethnicity.

No abstract