Showing papers in "Pattern Recognition in 2010"

TL;DR: The experimental results on representative databases show that the proposed LBPV operator and global matching scheme can achieve significant improvement, sometimes more than 10% in terms of classification accuracy, over traditional locally rotation invariant LBP method.

TL;DR: An up-to-date review and a new classification of the existingShape reconstruction using coded structured light techniques and their potentials are presented.

TL;DR: A new unsupervised DR method called sparsity preserving projections (SPP), which aims to preserve the sparse reconstructive relationship of the data, which is achieved by minimizing a L1 regularization-related objective function.

TL;DR: A new region-based active contour model that embeds the image local information by introducing the local image fitting (LIF) energy to extract the localimage information is proposed and is able to segment images with intensity inhomogeneities.

TL;DR: Experimental results on benchmark test images demonstrate that the LPG-PCA method achieves very competitive denoising performance, especially in image fine structure preservation, compared with state-of-the-art Denoising algorithms.

TL;DR: Generally, a CAD system consists of four stages: preprocessing, segmentation, feature extraction and selection, and classification, and their advantages and disadvantages are discussed.

TL;DR: The integration of the spatial information from the watershed segmentation in the hyperspectral image classifier improves the classification accuracies and provides classification maps with more homogeneous regions, compared to pixel-wise classification and previously proposed spectral-spatial classification techniques.

TL;DR: Comparisons with the well-known Chan-Vese (CV) model and recent popular local binary fitting (LBF) model show that the proposed LCV model can segment images with few iteration times and be less sensitive to the location of initial contour and the selection of governing parameters.

TL;DR: This work presents a hybrid algorithm, SAGA, that combines the ability to avoid being trapped in a local minimum of simulated annealing with the very high rate of convergence of the crossover operator of genetic algorithms, the strong local search ability of greedy algorithms and the high computational efficiency of generalized regression neural networks.

TL;DR: Bayesian decision making (BDM) results in the highest correct classification rate with relatively small computational cost, and a performance comparison of the classification techniques is provided in terms of their correct differentiation rates, confusion matrices, and computational cost.

TL;DR: The proposed method automatically merges the regions that are initially segmented by mean shift segmentation, and then effectively extracts the object contour by labeling all the non-marker regions as either background or object.

TL;DR: Good performance of the application for infrared dim small target detection is obtained, which could be ascribed to the proper selection of structuring elements based on the properties and three types of multi-scale operations are discussed in detail.

TL;DR: It is suggested that the performance from the Haar wavelet and Log-Gabor filter based phase encoding is the most promising among all the four approaches considered in this work and the combination of these two matchers is most promising, both in terms of performance and the computational complexity.

TL;DR: This paper presents a new biometric authentication system using finger-knuckle-print (FKP) imaging, which achieves much higher recognition rate and it works in real time and has great potentials for commercial applications.

TL;DR: Experiments show that the proposed method without residue compensation generates higher-quality images and costs less computational time than some recent face image super-resolution (hallucination) techniques.

TL;DR: A comparative evaluation of four popular interactive segmentation algorithms using the well-known Jaccard index for measuring object accuracy and a new fuzzy metric, proposed in this paper, designed for measuring boundary accuracy, demonstrates the effectiveness of the suggested measures.

TL;DR: An efficient road sign recognition system is built, based on a conventional nearest neighbour classifier and a simple temporal integration scheme, which demonstrates a competitive performance in the experiments involving real traffic video.

TL;DR: A hybrid learning model based on the triangle area based nearest neighbors (TANN) in order to detect attacks more effectively and provide higher accuracy and detection rates and the lower false alarm rate than three baseline models based on support vector machines, k-NN, and the hybrid centroid-based classification model by combining k-means and k-nn.

TL;DR: This paper presents a new approach to the computer aided diagnosis (CAD) of diabetic retinopathy (DR) based on multi-scale correlation filtering (MSCF) and dynamic thresholding and concludes the method to be effective and efficient.

TL;DR: The results demonstrate that it is much more efficient than representative image feature descriptors, such as the edge orientation auto-correlogram and the texton co-occurrence matrix and has good discrimination power of color, texture and shape features.

TL;DR: Comparison between experimental results on sum rule-based fusion and SVM- based fusion reveals that the latter could attain better performance than the former, provided that the kernel and its parameters have been carefully selected.

TL;DR: This paper proposes a convex energy-based framework to jointly perform feature selection and SVM parameter learning for linear and non-linear kernels.

TL;DR: Experiments show that the proposed algorithm improves reconstruction quality over existing state-of-the-art super-resolution algorithms, both visually, and using a quantitative peak signal-to-noise ratio assessment.

TL;DR: Experimental results show the presented method outperforms existing methods, in both visual effect and objective evaluation criteria, and some practical applications are given further.

TL;DR: An effective method for automatic writer recognition from unconstrained handwritten text images based on the presence of redundant patterns in the writing and its visual attributes is proposed, which exhibits promising results on writer identification and verification.

TL;DR: A supervised feature selection approach, which is based on metric applied on continuous and discrete data representations, builds a dissimilarity space using information theoretic measures, in particular conditional mutual information between features with respect to a relevant variable that represents the class labels.

TL;DR: A novel clustering technique called enhanced soft subspace clustering (ESSC) is proposed by employing both within-cluster and between-class information and it is demonstrated that the accuracy of the proposed ESSC algorithm outperforms most existing state-of-the-art soft sub space clustering algorithms.

TL;DR: This framework is able to improve the binarization results and to restore weak connections and strokes, especially in the case of degraded historical documents, thanks to localized nature of the framework on the spatial domain.

TL;DR: The proposed DBN-based hand gesture model and the design of a gesture network model are believed to have a strong potential for successful applications to other related problems such as sign language recognition although it is a bit more complicated requiring analysis of hand shapes.

TL;DR: A new graphometric feature set that considers the curvature of the most important segments, perceptually speaking, of the signature by using Bezier curves and then extracting features from these curves to improve the reliability of the classification.