Home << 1 2 3 4 5 6 7 8 9 10 >> [11–14]
List View
 | 
Citations
 | 
Details
   web
Records
Author Antonio Hernandez; Nadezhda Zlateva; Alexander Marinov; Miguel Reyes; Petia Radeva; Dimo Dimov; Sergio Escalera
Title Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps Type Conference Article
Year 2012 Publication 25th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages (down) 726-732
Keywords
Abstract We present a generic framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs in depth maps. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α-β swap Graph-cuts algorithm. Moreover, depth of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
Address Portland; Oregon; June 2013
Corporate Author Thesis
Publisher IEEE Xplore Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1063-6919 ISBN 978-1-4673-1226-4 Medium
Area Expedition Conference CVPR
Notes MILAB;HuPBA Approved no
Call Number Admin @ si @ HZM2012b Serial 2046
Permanent link to this record
 
 
Author Volkmar Frinken; Francisco Zamora; Salvador España; Maria Jose Castro; Andreas Fischer; Horst Bunke
Title Long-Short Term Memory Neural Networks Language Modeling for Handwriting Recognition Type Conference Article
Year 2012 Publication 21st International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages (down) 701-704
Keywords
Abstract Unconstrained handwritten text recognition systems maximize the combination of two separate probability scores. The first one is the observation probability that indicates how well the returned word sequence matches the input image. The second score is the probability that reflects how likely a word sequence is according to a language model. Current state-of-the-art recognition systems use statistical language models in form of bigram word probabilities. This paper proposes to model the target language by means of a recurrent neural network with long-short term memory cells. Because the network is recurrent, the considered context is not limited to a fixed size especially as the memory cells are designed to deal with long-term dependencies. In a set of experiments conducted on the IAM off-line database we show the superiority of the proposed language model over statistical n-gram models.
Address Tsukuba Science City, Japan
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1051-4651 ISBN 978-1-4673-2216-4 Medium
Area Expedition Conference ICPR
Notes DAG Approved no
Call Number Admin @ si @ FZE2012 Serial 2052
Permanent link to this record
 
 
Author Arjan Gijsenij; R. Lu; Theo Gevers; De Xu
Title Color Constancy for Multiple Light Source Type Journal Article
Year 2012 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 21 Issue 2 Pages (down) 697-707
Keywords
Abstract Impact factor 2010: 2.92
Impact factor 2011/2012?: 3.32
Color constancy algorithms are generally based on the simplifying assumption that the spectral distribution of a light source is uniform across scenes. However, in reality, this assumption is often violated due to the presence of multiple light sources. In this paper, we will address more realistic scenarios where the uniform light-source assumption is too restrictive. First, a methodology is proposed to extend existing algorithms by applying color constancy locally to image patches, rather than globally to the entire image. After local (patch-based) illuminant estimation, these estimates are combined into more robust estimations, and a local correction is applied based on a modified diagonal model. Quantitative and qualitative experiments on spectral and real images show that the proposed methodology reduces the influence of two light sources simultaneously present in one scene. If the chromatic difference between these two illuminants is more than 1° , the proposed framework outperforms algorithms based on the uniform light-source assumption (with error-reduction up to approximately 30%). Otherwise, when the chromatic difference is less than 1° and the scene can be considered to contain one (approximately) uniform light source, the performance of the proposed method framework is similar to global color constancy methods.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1057-7149 ISBN Medium
Area Expedition Conference
Notes ALTRES;ISE Approved no
Call Number Admin @ si @ GLG2012a Serial 1852
Permanent link to this record
 
 
Author Marina Alberti; Simone Balocco; Xavier Carrillo; Josepa Mauri; Petia Radeva
Title Automatic Non-Rigid Temporal Alignment of IVUS Sequences Type Conference Article
Year 2012 Publication 15th International Conference on Medical Image Computing and Computer Assisted Intervention Abbreviated Journal
Volume 1 Issue Pages (down) 642-650
Keywords
Abstract Clinical studies on atherosclerosis regression/progression performed by Intravascular Ultrasound analysis require the alignment of pullbacks of the same patient before and after clinical interventions. In this paper, a methodology for the automatic alignment of IVUS sequences based on the Dynamic Time Warping technique is proposed. The method is adapted to the specific IVUS alignment task by applying the non-rigid alignment technique to multidimensional morphological signals, and by introducing a sliding window approach together with a regularization term. To show the effectiveness of our method, an extensive validation is performed both on synthetic data and in-vivo IVUS sequences. The proposed method is robust to stent deployment and post dilation surgery and reaches an alignment error of approximately 0.7 mm for in-vivo data, which is comparable to the inter-observer variability.
Address Nice, France
Corporate Author Thesis
Publisher Springer-Verlag Berlin, Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-3-642-33414-6 Medium
Area Expedition Conference MICCAI
Notes MILAB Approved no
Call Number Admin @ si @ ABC2012 Serial 2168
Permanent link to this record
 
 
Author Naila Murray; Sandra Skaff; Luca Marchesotti; Florent Perronnin
Title Towards automatic and flexible concept transfer Type Journal Article
Year 2012 Publication Computers and Graphics Abbreviated Journal CG
Volume 36 Issue 6 Pages (down) 622–634
Keywords
Abstract This paper introduces a novel approach to automatic, yet flexible, image concepttransfer; examples of concepts are “romantic”, “earthy”, and “luscious”. The presented method modifies the color content of an input image given only a concept specified by a user in natural language, thereby requiring minimal user input. This method is particularly useful for users who are aware of the message they wish to convey in the transferred image while being unsure of the color combination needed to achieve the corresponding transfer. Our framework is flexible for two reasons. First, the user may select one of two modalities to map input image chromaticities to target concept chromaticities depending on the level of photo-realism required. Second, the user may adjust the intensity level of the concepttransfer to his/her liking with a single parameter. The proposed method uses a convex clustering algorithm, with a novel pruning mechanism, to automatically set the complexity of models of chromatic content. Results show that our approach yields transferred images which effectively represent concepts as confirmed by a user study.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0097-8493 ISBN Medium
Area Expedition Conference
Notes CIC Approved no
Call Number Admin @ si @ MSM2012 Serial 2002
Permanent link to this record
 
 
Author Volkmar Frinken; Alicia Fornes; Josep Llados; Jean-Marc Ogier
Title Bidirectional Language Model for Handwriting Recognition Type Conference Article
Year 2012 Publication Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop Abbreviated Journal
Volume 7626 Issue Pages (down) 611-619
Keywords
Abstract In order to improve the results of automatically recognized handwritten text, information about the language is commonly included in the recognition process. A common approach is to represent a text line as a sequence. It is processed in one direction and the language information via n-grams is directly included in the decoding. This approach, however, only uses context on one side to estimate a word’s probability. Therefore, we propose a bidirectional recognition in this paper, using distinct forward and a backward language models. By combining decoding hypotheses from both directions, we achieve a significant increase in recognition accuracy for the off-line writer independent handwriting recognition task. Both language models are of the same type and can be estimated on the same corpus. Hence, the increase in recognition accuracy comes without any additional need for training data or language modeling complexity.
Address Japan
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-34165-6 Medium
Area Expedition Conference SSPR&SPR
Notes DAG Approved no
Call Number Admin @ si @ FFL2012 Serial 2057
Permanent link to this record
 
 
Author Jose Carlos Rubio; Joan Serrat; Antonio Lopez; Daniel Ponsa
Title Multiple target tracking for intelligent headlights control Type Journal Article
Year 2012 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS
Volume 13 Issue 2 Pages (down) 594-605
Keywords Intelligent Headlights
Abstract Intelligent vehicle lighting systems aim at automatically regulating the headlights' beam to illuminate as much of the road ahead as possible while avoiding dazzling other drivers. A key component of such a system is computer vision software that is able to distinguish blobs due to vehicles' headlights and rear lights from those due to road lamps and reflective elements such as poles and traffic signs. In a previous work, we have devised a set of specialized supervised classifiers to make such decisions based on blob features related to its intensity and shape. Despite the overall good performance, there remain challenging that have yet to be solved: notably, faint and tiny blobs corresponding to quite distant vehicles. In fact, for such distant blobs, classification decisions can be taken after observing them during a few frames. Hence, incorporating tracking could improve the overall lighting system performance by enforcing the temporal consistency of the classifier decision. Accordingly, this paper focuses on the problem of constructing blob tracks, which is actually one of multiple-target tracking (MTT), but under two special conditions: We have to deal with frequent occlusions, as well as blob splits and merges. We approach it in a novel way by formulating the problem as a maximum a posteriori inference on a Markov random field. The qualitative (in video form) and quantitative evaluation of our new MTT method shows good tracking results. In addition, we will also see that the classification performance of the problematic blobs improves due to the proposed MTT algorithm.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1524-9050 ISBN Medium
Area Expedition Conference
Notes ADAS Approved no
Call Number Admin @ si @ RLP2012; ADAS @ adas @ rsl2012g Serial 1877
Permanent link to this record
 
 
Author Laura Igual; Joan Carles Soliva; Sergio Escalera; Roger Gimeno; Oscar Vilarroya; Petia Radeva
Title Automatic Brain Caudate Nuclei Segmentation and Classification in Diagnostic of Attention-Deficit/Hyperactivity Disorder Type Journal Article
Year 2012 Publication Computerized Medical Imaging and Graphics Abbreviated Journal CMIG
Volume 36 Issue 8 Pages (down) 591-600
Keywords Automatic caudate segmentation; Attention-Deficit/Hyperactivity Disorder; Diagnostic test; Machine learning; Decision stumps; Dissociated dipoles
Abstract We present a fully automatic diagnostic imaging test for Attention-Deficit/Hyperactivity Disorder diagnosis assistance based on previously found evidences of caudate nucleus volumetric abnormalities. The proposed method consists of different steps: a new automatic method for external and internal segmentation of caudate based on Machine Learning methodologies; the definition of a set of new volume relation features, 3D Dissociated Dipoles, used for caudate representation and classification. We separately validate the contributions using real data from a pediatric population and show precise internal caudate segmentation and discrimination power of the diagnostic test, showing significant performance improvements in comparison to other state-of-the-art methods.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes OR; HuPBA; MILAB Approved no
Call Number Admin @ si @ ISE2012 Serial 2143
Permanent link to this record
 
 
Author Jose Manuel Alvarez; Y. LeCun; Theo Gevers; Antonio Lopez
Title Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features Type Conference Article
Year 2012 Publication 12th European Conference on Computer Vision – Workshops and Demonstrations Abbreviated Journal
Volume 7584 Issue Pages (down) 586-595
Keywords road detection
Abstract Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process.
Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-33867-0 Medium
Area Expedition Conference ECCVW
Notes ADAS;ISE Approved no
Call Number Admin @ si @ ALG2012; ADAS @ adas Serial 2187
Permanent link to this record
 
 
Author Fadi Dornaika; A.Assoum; Bogdan Raducanu
Title Automatic Dimensionality Estimation for Manifold Learning through Optimal Feature Selection Type Conference Article
Year 2012 Publication Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop Abbreviated Journal
Volume 7626 Issue Pages (down) 575-583
Keywords
Abstract A very important aspect in manifold learning is represented by automatic estimation of the intrinsic dimensionality. Unfortunately, this problem has received few attention in the literature of manifold learning. In this paper, we argue that feature selection paradigm can be used to the problem of automatic dimensionality estimation. Besides this, it also leads to improved recognition rates. Our approach for optimal feature selection is based on a Genetic Algorithm. As a case study for manifold learning, we have considered Laplacian Eigenmaps (LE) and Locally Linear Embedding (LLE). The effectiveness of the proposed framework was tested on the face recognition problem. Extensive experiments carried out on ORL, UMIST, Yale, and Extended Yale face data sets confirmed our hypothesis.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-34165-6 Medium
Area Expedition Conference SSPR&SPR
Notes OR;MV Approved no
Call Number Admin @ si @ DAR2012 Serial 2174
Permanent link to this record
 
 
Author Bogdan Raducanu; Fadi Dornaika
Title Pose-Invariant Face Recognition in Videos for Human-Machine Interaction Type Conference Article
Year 2012 Publication 12th European Conference on Computer Vision Abbreviated Journal
Volume 7584 Issue Pages (down) 566.575
Keywords
Abstract Human-machine interaction is a hot topic nowadays in the communities of computer vision and robotics. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. This is mostly due to the difficulty of simultaneously handling variations in illumination, pose, and occlusions. In this paper, we propose a novel approach for robust pose-invariant face recognition for human-robot interaction based on the real-time fitting of a 3D deformable model to input images taken from video sequences. More concrete, our approach generates a rectified face image irrespective with the actual head-pose orientation. Experimental results performed on Honda video database, using several manifold learning techniques, show a distinct advantage of the proposed method over the standard 2D appearance-based snapshot approach.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-33867-0 Medium
Area Expedition Conference ECCVW
Notes OR;MV Approved no
Call Number Admin @ si @ RaD2012e Serial 2182
Permanent link to this record
 
 
Author Pierluigi Casale; Oriol Pujol; Petia Radeva
Title Personalization and User Verification in Wearable Systems using Biometric Walking Patterns Type Journal Article
Year 2012 Publication Personal and Ubiquitous Computing Abbreviated Journal PUC
Volume 16 Issue 5 Pages (down) 563-580
Keywords
Abstract In this article, a novel technique for user’s authentication and verification using gait as a biometric unobtrusive pattern is proposed. The method is based on a two stages pipeline. First, a general activity recognition classifier is personalized for an specific user using a small sample of her/his walking pattern. As a result, the system is much more selective with respect to the new walking pattern. A second stage verifies whether the user is an authorized one or not. This stage is defined as a one-class classification problem. In order to solve this problem, a four-layer architecture is built around the geometric concept of convex hull. This architecture allows to improve robustness to outliers, modeling non-convex shapes, and to take into account temporal coherence information. Two different scenarios are proposed as validation with two different wearable systems. First, a custom high-performance wearable system is built and used in a free environment. A second dataset is acquired from an Android-based commercial device in a ‘wild’ scenario with rough terrains, adversarial conditions, crowded places and obstacles. Results on both systems and datasets are very promising, reducing the verification error rates by an order of magnitude with respect to the state-of-the-art technologies.
Address
Corporate Author Thesis
Publisher Springer-Verlag Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1617-4909 ISBN Medium
Area Expedition Conference
Notes MILAB;HuPBA Approved no
Call Number Admin @ si @ CPR2012 Serial 1706
Permanent link to this record
 
 
Author Michael Holte; Bhaskar Chakraborty; Jordi Gonzalez; Thomas B. Moeslund
Title A Local 3D Motion Descriptor for Multi-View Human Action Recognition from 4D Spatio-Temporal Interest Points Type Journal Article
Year 2012 Publication IEEE Journal of Selected Topics in Signal Processing Abbreviated Journal J-STSP
Volume 6 Issue 5 Pages (down) 553-565
Keywords
Abstract In this paper, we address the problem of human action recognition in reconstructed 3-D data acquired by multi-camera systems. We contribute to this field by introducing a novel 3-D action recognition approach based on detection of 4-D (3-D space $+$ time) spatio-temporal interest points (STIPs) and local description of 3-D motion features. STIPs are detected in multi-view images and extended to 4-D using 3-D reconstructions of the actors and pixel-to-vertex correspondences of the multi-camera setup. Local 3-D motion descriptors, histogram of optical 3-D flow (HOF3D), are extracted from estimated 3-D optical flow in the neighborhood of each 4-D STIP and made view-invariant. The local HOF3D descriptors are divided using 3-D spatial pyramids to capture and improve the discrimination between arm- and leg-based actions. Based on these pyramids of HOF3D descriptors we build a bag-of-words (BoW) vocabulary of human actions, which is compressed and classified using agglomerative information bottleneck (AIB) and support vector machines (SVMs), respectively. Experiments on the publicly available i3DPost and IXMAS datasets show promising state-of-the-art results and validate the performance and view-invariance of the approach.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1932-4553 ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ HCG2012 Serial 1994
Permanent link to this record
 
 
Author Antonio Hernandez; Nadezhda Zlateva; Alexander Marinov; Miguel Reyes; Petia Radeva; Dimo Dimov; Sergio Escalera
Title Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization Type Journal Article
Year 2012 Publication Journal of Ambient Intelligence and Smart Environments Abbreviated Journal JAISE
Volume 4 Issue 6 Pages (down) 535-546
Keywords Multi-modal vision processing; Random Forest; Graph-cuts; multi-label segmentation; human body segmentation
Abstract We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1876-1364 ISBN Medium
Area Expedition Conference
Notes MILAB;HuPBA Approved no
Call Number Admin @ si @ HZM2012a Serial 2006
Permanent link to this record
 
 
Author Klaus Broelemann; Anjan Dutta; Xiaoyi Jiang; Josep Llados
Title Hierarchical graph representation for symbol spotting in graphical document images Type Conference Article
Year 2012 Publication Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop Abbreviated Journal
Volume 7626 Issue Pages (down) 529-538
Keywords
Abstract Symbol spotting can be defined as locating given query symbol in a large collection of graphical documents. In this paper we present a hierarchical graph representation for symbols. This representation allows graph matching methods to deal with low-level vectorization errors and, thus, to perform a robust symbol spotting. To show the potential of this approach, we conduct an experiment with the SESYD dataset.
Address Miyajima-Itsukushima, Hiroshima
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-34165-6 Medium
Area Expedition Conference SSPR&SPR
Notes DAG Approved no
Call Number Admin @ si @ BDJ2012 Serial 2126
Permanent link to this record