1,721,020 research outputs found
Fiducial point localization in color images of face foregrounds
No full textWe describe a method for the automatic identification of facial features (eyes, nose, mouth and chin) and the precise localization of their fiducial points (e.g. nose tip, mouth and eye corners) in color images of face foregrounds. The algorithm requires as input 2D color images, representing face foregrounds with homogeneous background; it is scale-independent, it deals with either frontal, rotated (up to 30°) or slightly tilted (up to 10°) faces, and it is robust to different facial expressions, requiring the mouth closed and the eyes opened, and no wearing glasses. The method proceeds with subsequent refinements: first, it identifies the sub images containing each feature, afterwards, it processes the single features separately by a blend of techniques which use both color and shape information. The system has been tested on three databases: the XM2VTS database, the University of Stirling database, and ours, for a total of 1650 images. The obtained results are described quantitatively and discussed
Robust Face Recognition Providing the Identity and its Reliability Degree Combining Sparse Representation and Multiple Features
Full text linkFor decades, face recognition (FR) has attracted a lot of attention, and several systems have been successfully developed to solve this problem. However, the issue deserves further research effort so as to reduce the still existing gap between the computer and human ability in solving it. Among the others, one of the human skills concerns his ability in naturally conferring a “degree of reliability” to the face identification he carried out. We believe that providing a FR system with this feature would be of great help in real application contexts, making more flexible and treatable the identification process. In this spirit, we propose a completely automatic FR system robust to possible adverse illuminations and facial expression variations that provides together with the identity the corresponding degree of reliability. The method promotes sparse coding of multi-feature representations with LDA projections for dimensionality reduction, and uses a multistage classifier. The method has been evaluated in the challenging condition of having few (3–5) images per subject in the gallery. Extended experiments on several challenging databases (frontal faces of Extended YaleB, BANCA, FRGC v2.0, and frontal faces of Multi-PIE) show that our method outperforms several state-of-the-art sparse coding FR systems, thus demonstrating its effectiveness and generalizability
High-rate compression of ECG signals by an accuracy-driven sparsity model relying on natural basis
Full text linkLong duration recordings of ECG signals require high compression ratios, in particular when storing on portable devices. Most of the ECG compression methods in literature are based on wavelet transform while only few of them rely on sparsity promotion models. In this paper we propose a novel ECG signal compression framework based on sparse representation using a set of ECG segments as natural basis. This approach exploits the signal regularity, i.e. the repetition of common patterns, in order to achieve high compression ratio (CR). We apply k-LiMapS as fine-tuned sparsity solver algorithm guaranteeing the required signal reconstruction quality PRDN (Normalized Percentage Root-mean-square Difference). Extensive experiments have been conducted on all the 48 records of MIT-BIH Arrhythmia Database and on some 24 hour records from the Long-Term ST Database. Direct comparisons of our method with several state-of-the-art ECG compression methods (namely ARLE, Rajoub's, SPIHT, TRE) prove its effectiveness. Our method achieves average performances that are two-three times higher than those obtained by the other assessed methods. In particular the compression ratio gap between our method and the others increases with growing PRDN
A face recognition system based on automatically determined facial fiducial points
No full textIn this paper, a completely automatic face recognition system is presented. The method works on color images: after having localized the face and the facial features, it determines 24 facial fiducial points, and characterizes them applying a bank of Gabor filters which extract the peculiar texture around them (jets). Recognition is realized measuring the similarity between the different jets. The system is inspired by the elastic bunch graph method, while it does no assumption on the scale, pose, and the background. Comparison with standard algorithms is presented and discussed
Face detection in color images of generic scenes
No full textIn this paper we describe a face detection algorithm, the key idea being to determine roughly the skin regions of a 2D color image and searching for eyes through them. The technique is based on a support vector machine trained to separate sub images representing eyes from others. The algorithm can be used in face image database management systems both as a first step of a person identification, and to discriminate the images on the basis of the number of faces in them
Local features and sparse representation for face recognition with partial occlusions
No full textIn this paper we present a new local-based face recognition system that combines weak classifiers to create a robust system able to recognize faces in presence of either occlusions or large expression variations. The method relies on sparse approximation using dictionaries built on local features. Experiments on the AR database show the effectiveness of our method, which achieves better performance than those obtained by the state-of-the-art l1 norm-based sparse representation classifier (SRC)
Precise eye and mouth localization
No full textThe literature on the topic has shown a strong correlation between the degree of precision of face localization and the face recognition performance. Hence, there is a need for precise facial feature detectors, as well as objective measures for their evaluation and comparison.
In this paper, we will present significant improvements to a previous method for precise eye center localization, by integrating a module for mouth localization. The technique is based on Support Vector Machines trained on optimally chosen Haar wavelet coefficients. The method has been tested on several public databases; the results are reported and compared according to a standard error measure. The tests show that the algorithm achieves high precision of localization
Sparse decomposition by iterating Lipschitzian-type mappings
No full textcombines nonconvex Lipschitzian-type mappings with canonical orthogonal projectors. The former are aimed at uniformly enhancing the sparsity level by shrinkage effects, the latter are used to project back onto the space of feasible solutions. The iterative process is driven by an increasing sequence of a scalar parameter that mainly contributes to approach the sparsest solutions. It is shown that the minima are locally asymptotically stable for a specific smooth . l0-norm. Furthermore, it is shown that the points yielded by this iterative strategy are related to the optimal solutions measured in terms of a suitable smooth . l1-norm. Numerical simulations on phase transition show that the performances of the proposed technique overcome those yielded by well known methods for sparse recovery
ECG compression retaining the best natural basis k-coefficients via sparse decomposition
No full textA novel and efficient signal compression algorithm aimed at finding the sparsest representation of electro-cardiogram (ECG) signals is presented and analyzed. The idea behind the method relies on basis elementsdrawn from the initial transitory of a signal itself, and the sparsity promotion process applied to its sub-sequent blocks grabbed by a sliding window. The saved coefficients rescaled in a convenient range, quantized and compressed by a lossless entropy-based algorithm. Experiments on signals extracted from the MIT-BIH Arrhythmia database show that the methodachieves in most of the cases very high performance
- …
