Showing papers in "Pattern Recognition Letters in 2013"

TL;DR: This paper reviews the recent development of relevant technologies from the perspectives of computer vision and pattern recognition, and discusses how to face emerging challenges of intelligent multi-camera video surveillance.

TL;DR: This work introduces a versatile human activity dataset recorded in a sensor-rich environment and expects this benchmarking database will motivate other researchers to replicate and outperform the presented results, thus contributing to further advances in the state-of-the-art of activity recognition methods.

TL;DR: This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it, and describes the software libraries that can acquire it from a sensor.

TL;DR: The experimental results demonstrate that the proposed feature selection method improves the classification performance to a great extent and has proved to be a useful method in selecting features for multi-label classification problems.

TL;DR: A novel scene text detection approach using graph model built upon Maximally Stable Extremal Regions (MSERs) to incorporate various information sources into one framework that outperforms state-of-the-art methods both in recall and precision.

TL;DR: A new approach by integrating wavelet entropy based spider web plots and probabilistic neural network is proposed for the classification of MRI brain images, which provides a general solution to the pattern classification problems.

TL;DR: This study proposes a novel approach, Multi-output LS-SVR (MLS-Svr), in multi-output setting, inspired by the multi-task learning methods, and extensive experimental results validate the effectiveness of the proposed approach.

TL;DR: A human action recognition method is presented in which pose representation is based on the contour points of the human silhouette and actions are learned by making use of sequences of multi-view key poses, achieving state-of-the-art success rates without compromising the speed of the recognition process.

TL;DR: The main theoretical and computational properties of the measures under study are highlighted, while the relationships between them are investigated and useful conclusions are drawn regarding the accuracy and confidence of the recognition results.

TL;DR: This work proposes a novel image fusion scheme for combining two or multiple images with different focus points to generate an all-in-focus image that is consistently superior to the other existing state-of-the-art fusion methods in terms of visual and quantitative evaluations.

TL;DR: A novel framework that can recognize facial expressions very efficiently and with high accuracy even for very low resolution facial images is presented, which exceeds state-of-the-art methods for expression recognition on low resolution images.

TL;DR: The experimental results show that CFKNNC can classify much more accurately than CKNNC and various improvements to CKnnC such as the nearest feature line (NFL) classifier, the nearest features space (NFS) classifiers, nearest neighbor line classifier (NNLC) and center-based nearest neighbor classifier(CBNNC).

TL;DR: The proposed fusion strategy integrates conventional inpainting with the recently developed non-local filtering scheme to improve depth maps and shows a good balance between depth and color information guarantees an accurate inPainting result.

TL;DR: A new probabilistic model for supervised learning with multiple annotators where the reliability of the different annotators is treated as a latent variable is proposed and able to achieve state of the art performance, while reducing the number of model parameters, thus avoiding a potential overfitting.

TL;DR: A novel collaborative neighbor representation method for multi-class classification based on l"2-minimization approach with the assumption of locally linear embedding (LLE) that achieves competitive classification accuracy via optimal neighbor representation having discriminative learning power.

TL;DR: The proposed RCD framework had better average ranks in data sets with abrupt and gradual concept drifts compared to both the single classifiers and the ensemble approaches that use the same base learner.

TL;DR: The experimental results show that the proposed algorithm for fuzzy segmentation of MRI data has better performance on image segmentation than conventional FCM based algorithms.

TL;DR: Two novel distance measures are proposed, normalized between 0 and 1, and based on normalized cross-correlation for image matching, based on the fact that for natural images there is a high correlation between spatially close pixels.

TL;DR: A set of trainable keypoint detectors using COSFIRE filters to automatically detect vascular bifurcations in segmented retinal images are used and are versatile key point detectors as they can be configured with any given local contour pattern and are subsequently able to detect the same and similar patterns.

TL;DR: This paper conducts extensive experiments to compare different person-specific models for facial expression and action unit (AU) recognition, and shows that transfer learning significantly improves the recognition performance with a small amount of training data.

TL;DR: A novel computer-aided diagnosis tool for the diagnosis of the Alzheimer's disease (AD) using structural Magnetic Resonance Images (MRIs) using information learnt from the tissue distribution of Gray Matter and White Matter in the brain, which is previously obtained by an unsupervised segmentation method.

TL;DR: If additional information, such as the class assignments of other objects, is taken into account when making a classification, then the area under the curve is a coherent measure, although in those circumstances it makes an assumption which is seldom if ever appropriate.

TL;DR: A new font and size identification method for ultra-low resolution Arabic word images using a stochastic approach and is about 23% better than the global multi-font system in terms of word recognition rate on the Arabic Printed Text Image database.

TL;DR: The objective is to recognize the writer of a handwritten text in one script from the samples of the same writer in another script and hence validate the hypothesis that writing style of an individual remains constant across different scripts.

TL;DR: A multi-spectrum based saliency detection algorithm that incorporates near-infrared clues into the detection framework and results indicate that the proposed algorithm outperforms the others.

TL;DR: A new adaptive morphological method for the automatic detection of the optic disk in digital color eye fundus images is presented and was able to detect the optic disks center and the rim in DRIVE and DIARETDB1 databases.

TL;DR: This paper presents a new ensemble pruning method which highly reduces the complexity of ensemble methods and performs better than complete bagging in terms of classification accuracy and is a very fast algorithm.

TL;DR: Experimental evidence shows this method achieves better accuracy for registering visible and long wavelength infrared images/videos as compared to state-of-the-art approaches.

TL;DR: It is proven that the proposed sensor fusion technique, coupled with the random forests classifier, is effective for multiple view human action recognition.

TL;DR: This paper proposes a method for individual tree species classification of five different species based on the analysis of the 3D geometric texture of the bark based on a combination of the Complex Wavelet Transforms and the Contourlet Transform.