In this paper, a local appearance based face recognition algorithm is proposed. In the proposed algorithm local information is extracted using block-based discrete cosine transform. Obtained local features are combined both at the feature level and at the decision level. The performance of the proposed algorithm is tested on the Yale and CMU PIE face databases, and the obtained results show significant improvement over the holistic approaches. 1.

This paper considers the problem of recognizing faces under varying illuminations. First, we investigate the statistics of the derivative of the irradiance images (log) of human face and find that the distribution is very sparse. Based on this observation, we propose an illumination insensitive similarity measure based on the min operator of the derivatives of two images. Our experiments on the CMU-PIE database have shown that the proposed method improves the performance of a face recognition system when the probes are collected under varying lighting conditions. 1.

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extractions. Simple, complex and end-stopped cells tuned to different spatial frequencies (scales) and/or orientations provide input for line, edge and keypoint detection. This yields a rich, multi-scale object representation that can be stored in memory in order to identify objects. The multi-scale, keypoint-based saliency maps for Focus-of-Attention can be explored to obtain face detection and normalization, after which face recognition can be achieved using the line/edge representation. In this paper, we focus only on face normalization, showing that multi-scale keypoints can be used to construct canonical representations of faces in memory. 1.

Abstract—When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database. Index Terms—Face recognition, optimization, regularized discriminant analysis (RDA), small sample-size problem. I.

Abstract. Face-to-face communications between humans involve emotions, which often are unconsciously conveyed by facial expressions and body gestures. Intelligent human-machine interfaces, for example in cognitive robotics, need to recognize emotions. This paper addresses facial expressions and their neural correlates on the basis of a model of the visual cortex: the multi-scale line and edge coding. The recognition model links the cortical representation with Paul Ekman’s Action Units which are related to the different facial muscles. The model applies a top-down categorization with trends and magnitudes of displacements of the mouth and eyebrows based on expected displacements relative to a neutral expression. The happy vs. not-happy categorization yielded a correct recognition rate of 91%, whereas final recognition of the six expressions happy, anger, disgust, fear, sadness and surprise resulted in a rate of 78%. 1

Abstract — Con objeto de analizar en qué medida puede ayudar el uso de imágenes adquiridas en el rango de ondas milimétricas (MMW) al reconocimiento biométrico de personas a distancia, se presenta un análisis experimental de tres escenarios con diferentes distancias de captura adecuadas para la adquisición de imágenes MMW. En concreto se realizan experimentos de reconocimiento facial a corta, media y larga distancia entre la cámara y el sujeto a identificar, siendo los escenarios de media y larga distancia los más adecuados para las capturas en MMW. Los tres escenarios consideran plantillas registradas en condiciones controladas, y para su estudio se usan datos del NIST Multiple Biometric Grand Challenge. Este enfoque permite: 1) aproximarnos al problema del reconocimiento biométrico de imágenes en MMW como complemento a biometrías tradicionales como es el reconocimiento facial, y 2) entender los factores de

Illumination variation is a challenging problem in face recognition research area. Same person can appear greatly different under varying lighting conditions. This paper consists of Face Recognition System which is invariant to illumination variations. Face recognition system which uses Linear Discriminant Analysis (LDA) as feature extractor have Small Sample Size (SSS). It consists of

Bu bildiride, ayrık kosinüs dönüşümü tabanlı yerel görünüme

Although it shows enormous potential as a feature extractor, 2D principal component analysis (2DPCA) produces numerous coefficients. Using a feature-selection algorithm based on a multiobjective genetic algorithm to analyze and discard irrelevant coefficients offers a solution that considerably reduces the number of coefficients, while also improving recognition rates. 1521-9615/11/$26.00 © 2011 IEEE Copublished by the IEEE CS and the AIP Face recognition and facial-expression recognition have been active research fields for several years. Potential application areas include access control, searching mug shots, screening, security monitoring and surveillance systems, human-computer interaction, emotion analysis, and automated tutoring systems. Both face and facial-expression recognition continue to attract researchers from image processing, pattern recognition, machine learning, and computer vision. 1 Several attempts have been made to improve the reliability of these recognition systems. One highly successful approach is eigenfaces, which Matthew Turk and Alex Pentland proposed in 19912 based on principal component analysis (PCA). Since then, researchers have been investigating PCA and using it as a basis for developing successful techniques for face and facial-expression recognition. 1

Sparse representation based face recognition is the most recent technique used, this technique first codes a testing sample as a sparse linear combination of all the training samples, and then classifies the testing sample by evaluating which class leads to the minimum representation error. The l1-norm sparsity improves the face recognition accuracy. While most of the research focus has been in increasing the face recognition accuracy, in this paper we analyze the time needed for face recognition under varying Facial expressions, Pose and Illumination. This analysis is done on various public data sets. GRIMACE and ATT data sets provide variations in Facial expressions, SUBJECT data set provides Pose variations and YALEB data set provides 64 illumination conditions. The average time taken is calculated for each of the data set.