Showing papers in "Pattern Recognition Letters in 2012"

TL;DR: The proposed CrackTree method is evaluated on a collection of 206 real pavement images and the experimental results show that the proposed method achieves a better performance than several existing methods.

TL;DR: This paper investigates gender recognition on real-life faces using the recently built database, the Labeled Faces in the Wild (LFW), and local Binary Patterns (LBP) is employed to describe faces, and Adaboost is used to select the discriminative LBP features.

TL;DR: A new method for detecting concept drift which uses an exponentially weighted moving average (EWMA) chart to monitor the misclassification rate of an streaming classifier and allows the rate of false positive detections to be controlled and kept constant over time.

TL;DR: For a multi-writer scenario on the IAM off-line database as well as for two single writer scenarios on historical data sets, it is shown that the proposed learning-based system outperforms a standard template matching method.

TL;DR: The proposed feature set describes the shape of a signature in terms of spatial distribution of black pixels around a candidate pixel (on the signature) and provides a measure of texture through the correlation among signature pixels in the neighborhood of that candidate pixel.

TL;DR: The present technique is based on an exhaustive screening taking into account all combinations of signal features extracted from the recorded acoustic emission signals, and can be used as an automated evaluation of the number of natural clusters and their partitions without previous knowledge about the cluster structure ofoustic emission signals.

TL;DR: A novel shape descriptor for matching and recognizing 2D object silhouettes that is not only invariant to geometric transformations such as translation, rotation and scaling but also insensitive to nonlinear deformations due to noise and occlusion is proposed.

TL;DR: The re-identification performance of HPE is augmented by applying it as human part descriptor, defining a structured feature called asymmetry-based HPE (AHPE), which provides optimal performances against low resolution, occlusions, pose and illumination variations, defining state-of-the-art results on all the considered datasets.

TL;DR: This paper introduces a new and robust approach for finger-vein ROI localization, and then proposes a new scheme for effectively improving the visibility of finger-VEin imageries.

TL;DR: These methods use low-complexity relevance and redundancy criteria, applicable to supervised, semi-supervised, and unsupervised learning, being able to act as pre-processors for computationally intensive methods to focus their attention on smaller subsets of promising features.

TL;DR: Experimental results show that the proposed approach has a high capability in fingerprint-vein based personal recognition as well as multimodal feature-level fusion.

TL;DR: This paper proposes an innovative and robust directional coding technique to encode the palm vein features in bit string representation, called VeinCode, which offers speedy template matching and enables more effective template storage and retrieval.

TL;DR: Results show that the cylindrical color spaces outperform other color spaces, the absence of the illuminance component decreases performance, the selection of an appropriate skin color modeling approach is important and that the tree based classifiers are well suited to pixel based skin detection.

TL;DR: Results from a rigorous empirical comparison with a subjective evaluation show that the proposed VISON technique produces video summaries with high quality relative to the state-of-the-art solutions and in a computational time that makes it suitable for online usage.

TL;DR: It is shown that physical support relationships between objects can provide useful contextual information for both object recognition and out-of-context detection.

TL;DR: This work proposes two complementary approaches to account for the spatial layout in an image-independent manner (as is the case of the SP) while the second one adapts to the image content which does not incur an increase of the image signature dimensionality.

TL;DR: A revised valley-emphasis thresholding method is presented, which weighs the objective function of the Otsu method with the valley point of the histogram for defect detection and provides better segmentation results than that of valley- emphasis method and Otsi method.

TL;DR: An automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym, and applies a novel approach for human action recognition by describing human actions using motion and shape features.

TL;DR: A new Random Forest induction algorithm called Dynamic Random Forest (DRF) which is based on an adaptative tree induction procedure which shows a significant improvement in terms of accuracy compared to the standard static RF induction algorithm.

TL;DR: A simplified form for the von Neumann entropy of a graph that can be computed in terms of node degree statistics is developed and the resulting complexity is compared with Estrada's heterogeneity index which measures the heterogeneity of the node degree across a graph.

TL;DR: The proposed noise tolerant extension of LBP operators to extract statistical and structural image features for efficient texture analysis uses a circular majority voting filter and suitable rotation-invariant labeling scheme to obtain more regular uniform and non-uniform patterns that have better discrimination ability and more robustness against noise.

TL;DR: Experimental results show that the proposed approach to efficiently remove background noise by detecting and modifying noisy pixels in an image cannot only efficiently suppress high-density impulse noise, but also can well preserve the detailed information of an image.

TL;DR: A novel fusion of different recognition approaches is proposed and described how it can contribute to more reliable noncooperative iris recognition by compensating for degraded images captured in less constrained acquisition setups and protocols under visible wavelengths and varying lighting conditions.

TL;DR: A novel approach to grade prostate malignancy using digitized histopathological specimens of the prostate tissue and a hierarchical (binary) classification scheme which utilizes the two methods and obtains 85.6% accuracy in classifying an input tissue pattern into one of the three classes.

TL;DR: The method significantly outperforms all other algorithms submitted to the Noisy Iris Challenge Evaluation-Part II (NICE), an open contest in noisy iris image matching.

TL;DR: This paper combines a set of the most robust morphological and perspiration-based measures for liveness detection and analyzed how the performance of the algorithm changes when the material employed for the spoof attack is not available during the training of the system.

TL;DR: A comprehensive survey of shadow detection methods, organised in a novel taxonomy based on object/environment dependency and implementation domain is presented, and a comparative evaluation of representative algorithms, based on quantitative and qualitative metrics is presented.

TL;DR: A re-identification method that takes into account the appearance of people, the spatial location of cameras and potential paths a person can choose to follow is proposed, modeled with a set of areas of interest (landmarks) that constrain the propagation of people trajectories in non-observed regions between the field-of-view of cameras.

TL;DR: The aim of this paper is to use a heterogeneous ensemble of multi-label learners to simultaneously tackle both the sample imbalance and label correlation problems and validate the advocated approach experimentally and demonstrate that it yields significant performance gains when compared with state-of-the art multi- label methods.

TL;DR: Two new graph kernels applied to regression and classification problems are presented, one based on the notion of edit distance while the other based on subtrees enumeration.