Showing papers in "Pattern Recognition Letters in 2018"

TL;DR: The recent advance of deep learning based sensor-based activity recognition is surveyed from three aspects: sensor modality, deep model, and application and detailed insights on existing work are presented and grand challenges for future research are proposed.

TL;DR: A comprehensive survey of recent Convolutional Neural Network (CNN) based approaches that have demonstrated significant improvements over earlier methods that rely largely on hand-crafted representations is provided.

TL;DR: A trainable Convolutional Neural Network is proposed for weakly illuminated image enhancement, namely LightenNet, which takes a weakly illumination image as input and outputs its illumination map that is subsequently used to obtain the enhanced image based on Retinex model.

TL;DR: An easy-to-use measure of video spatial complexity was devised and correlated with the classification performance of the CAE, and a method for aggregating high-level spatial and temporal features with the input frames was proposed and implemented.

TL;DR: Two robust encoder-decoder type neural networks that generate multi-scale feature encodings in different ways and can be trained end-to-end using only a few training samples are proposed.

TL;DR: The proposed hybrid model consists of Convolution layers followed by Recurrent Neural Network (RNN) which the combined model extracts the relations within facial images and by using the recurrent network the temporal dependencies which exist in the images can be considered during the classification.

TL;DR: A novel technique based on the idea of best features selection is introduced in this article for an offline verification system that is based on three accuracy measures as FAR, FRR and AER.

TL;DR: Results show that the proposed approach of combining multiple cues by means of decision level fusion is competitive with other state of the art methods.

TL;DR: This work introduces a new approach for the finger vein authentication using the CNN and supervised discrete hashing and offers significantly reduced template size as compared with those over the other finger vein images matching methods available in the literature to date.

TL;DR: A feature selection method named manifold-based constraint Laplacian score (MCLS) is presented, which is used to transform logical label space to Euclidean label space, and the similarity between samples is constrained by the corresponding numerical labels.

TL;DR: A Machine Learning model using Convolutional Neural Networks is put forward to not only detect the distracted driver but also identify the cause of his distraction by analyzing the images obtained using the camera module installed inside the vehicle.

TL;DR: This proposal describes a CNN architecture which is able to infer the noise pattern of mobile camera sensors (also known as camera fingerprint) with the aim at detecting and identifying not only the mobile device used to capture an image, but also from which embedded camera the image was captured.

TL;DR: This paper proposes the first method in the literature able to extract the coordinates of the pores from touch-based, touchless, and latent fingerprint images, and uses specifically designed and trained Convolutional Neural Networks to estimate and refine the centroid of each pore.

TL;DR: This paper presents an active contour model using local pre-fitting energy for fast image segmentation and shows that the proposed model is robust to initialization, which allows the initial level set function to be a small constant function.

TL;DR: The main purpose of this review is to systematically explore the ideas behind current multiple data source mining methods and to consolidate recent research results in this field.

TL;DR: A novel feature selection method named Composition of Feature Relevancy (CFR) is proposed, which outperforms five other competing methods in terms of average classification accuracy and highest classification accuracy.

TL;DR: This paper uses a real world dataset, and describes an end-to-end solution from the practitioners perspective, by focusing on the following crucial aspects: unbalancedness, data processing and cost metric evaluation.

TL;DR: Results confirm that better classification is made when the model is constructed with the optimization of kappa instead of logarithmic loss.

TL;DR: The imputePSF method extends PSF by characterizing repeating patterns of existing observations to provide a more precise estimate of missing values compared to more conventional methods, such as replacement with means or last observation carried forward.

TL;DR: This work presents a simple, robust and fast method to the perspective-n-point (PnP) problem for determining the position and orientation of a calibrated camera from known reference points that only needs to solve a seventh-order and a fourth-order univariate polynomial.

TL;DR: This paper presents a randomized hierarchical alternating least squares (HALS) algorithm to compute the NMF by deriving a smaller matrix from the nonnegative input data, so that a more efficient nonnegative decomposition can be computed.

TL;DR: A Bag of Expression (BoE) framework, based on the bag of words method, for recognizing human action in simple and realistic scenarios, which outperforms existing Bag of Words based approaches, when evaluated using the same performance evaluation methods.

TL;DR: The proposed algorithm uses a two-layer stacked sparse autoencoder to learn deep features from geodesic moments by training the hidden layers individually in an unsupervised fashion, followed by a softmax classifier.

TL;DR: Qualitative and quantitative results reveal that the proposed VPM for point cloud segmentation can outperform representative segmentation algorithms, i.e., point- and voxel-based region growing, difference of normal based clustering, and LCCP.

TL;DR: This technique of detection of K-complex with a well-known pattern present in sleep EEG is a fuzzy neural based software solution in the field of biomedical signal processing.

TL;DR: Extensive experiments on texture classification shows the proposed Ldzp descriptor achieves state-of-the-art performance in terms of average classification accuracy when applied to the large and well-known benchmark Outex database and is equally powerful for human face recognition.

TL;DR: Improved block based joint EIRDH algorithm is employed in this paper which embedded n secret bits per block by dividing blocks of same size into n sub-blocks and optimizing visual quality and enhanced embedding rate are acquired.

TL;DR: Results are compared with existing methods for 22 classification problems, showing that HE-ELM is able to achieve significant improvement in terms of classification accuracy, with a reduced risk of overfitting the training data.

TL;DR: A distance is proposed that combines Minkowski and Chebyshev distances and can be seen as an intermediary distance that not only achieves efficient run times in neighbourhood iteration tasks in Z 2, but also obtains good accuracies when coupled with the k-Nearest Neighbours (k-NN) classifier.

TL;DR: A new clustering method that can not only discover clusters of arbitrary shapes and automatically remove noise and outliers, but also it can find clusters with different densities and those with internal density variation.