Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	91–105 of 170 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >> [11–12]

List View

Citations

Details

	Records
	Author	Sergio Escalera; Oriol Pujol; Petia Radeva
	Title	On the Decoding Process in Ternary Error-Correcting Output Codes			Type	Journal Article
	Year	2010	Publication	IEEE on Pattern Analysis and Machine Intelligence	Abbreviated Journal	TPAMI
	Volume	32	Issue	1	Pages	120–134
	Keywords
	Abstract	A common way to model multiclass classification problems is to design a set of binary classifiers and to combine them. Error-correcting output codes (ECOC) represent a successful framework to deal with these type of problems. Recent works in the ECOC framework showed significant performance improvements by means of new problem-dependent designs based on the ternary ECOC framework. The ternary framework contains a larger set of binary problems because of the use of a ldquodo not carerdquo symbol that allows us to ignore some classes by a given classifier. However, there are no proper studies that analyze the effect of the new symbol at the decoding step. In this paper, we present a taxonomy that embeds all binary and ternary ECOC decoding strategies into four groups. We show that the zero symbol introduces two kinds of biases that require redefinition of the decoding design. A new type of decoding measure is proposed, and two novel decoding strategies are defined. We evaluate the state-of-the-art coding and decoding strategies over a set of UCI machine learning repository data sets and into a real traffic sign categorization problem. The experimental results show that, following the new decoding strategies, the performance of the ECOC design is significantly improved.
	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	0162-8828	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;HUPBA			Approved	no
	Call Number	BCNPCL @ bcnpcl @ EPR2010b			Serial	1277
Permanent link to this record



	Author	Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez
	Title	An Iterative Multiresolution Scheme for SFM with Missing Data: single and multiple object scenes			Type	Journal Article
	Year	2010	Publication	Image and Vision Computing	Abbreviated Journal	IMAVIS
	Volume	28	Issue	1	Pages	164-176
	Keywords
	Abstract	Most of the techniques proposed for tackling the Structure from Motion problem (SFM) cannot deal with high percentages of missing data in the matrix of trajectories. Furthermore, an additional problem should be faced up when working with multiple object scenes: the rank of the matrix of trajectories should be estimated. This paper presents an iterative multiresolution scheme for SFM with missing data to be used in both the single and multiple object cases. The proposed scheme aims at recovering missing entries in the original input matrix. The objective is to improve the results by applying a factorization technique to the partially or totally filled in matrix instead of to the original input one. Experimental results obtained with synthetic and real data sequences, containing single and multiple objects, are presented to show the viability of the proposed 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	0262-8856	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	ADAS @ adas @ JSL2010			Serial	1278
Permanent link to this record



	Author	Bogdan Raducanu; Jordi Vitria; Ales Leonardis
	Title	Online pattern recognition and machine learning techniques for computer-vision: Theory and applications			Type	Journal Article
	Year	2010	Publication	Image and Vision Computing	Abbreviated Journal	IMAVIS
	Volume	28	Issue	7	Pages	1063–1064
	Keywords
	Abstract	(Editorial for the Special Issue on Online pattern recognition and machine learning techniques) In real life, visual learning is supposed to be a continuous process. This paradigm has found its way also in artificial vision systems. There is an increasing trend in pattern recognition represented by online learning approaches, which aims at continuously updating the data representation when new information arrives. Starting with a minimal dataset, the initial knowledge is expanded by incorporating incoming instances, which may have not been previously available or foreseen at the system’s design stage. An interesting characteristic of this strategy is that the train and test phases take place simultaneously. Given the increasing interest in this subject, the aim of this special issue is to be a landmark event in the development of online learning techniques and their applications with the hope that it will capture the interest of a wider audience and will attract even more researchers. We received 19 contributions, of which 9 have been accepted for publication, after having been subjected to usual peer review process.
	Address
	Corporate Author				Thesis
	Publisher	Elsevier	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0262-8856	ISBN		Medium
	Area		Expedition		Conference
	Notes	OR;MV			Approved	no
	Call Number	BCNPCL @ bcnpcl @ RVL2010			Serial	1280
Permanent link to this record



	Author	Fernando Vilariño; Panagiota Spyridonos; Fosca De Iorio; Jordi Vitria; Fernando Azpiroz; Petia Radeva
	Title	Intestinal Motility Assessment With Video Capsule Endoscopy: Automatic Annotation of Phasic Intestinal Contractions			Type	Journal Article
	Year	2010	Publication	IEEE Transactions on Medical Imaging	Abbreviated Journal	TMI
	Volume	29	Issue	2	Pages	246-259
	Keywords
	Abstract	Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions shown in a video provided by an ingestible capsule with a wireless micro-camera. The manual labeling of all the motility events requires large amount of time for offline screening in search of findings with low prevalence, which turns this procedure currently unpractical. In this paper, we propose a machine learning system to automatically detect the phasic intestinal contractions in video capsule endoscopy, driving a useful but not feasible clinical routine into a feasible clinical procedure. Our proposal is based on a sequential design which involves the analysis of textural, color, and blob features together with SVM classifiers. Our approach tackles the reduction of the imbalance rate of data and allows the inclusion of domain knowledge as new stages in the cascade. We present a detailed analysis, both in a quantitative and a qualitative way, by providing several measures of performance and the assessment study of interobserver variability. Our system performs at 70% of sensitivity for individual detection, whilst obtaining equivalent patterns to those of the experts for density of contractions.
	Address
	Corporate Author	IEEE			Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0278-0062	ISBN		Medium
	Area	800	Expedition		Conference
	Notes	MILAB;MV;OR;SIAI			Approved	no
	Call Number	BCNPCL @ bcnpcl @ VSD2010; IAM @ iam @ VSI2010			Serial	1281
Permanent link to this record



	Author	Sergio Escalera; Oriol Pujol; Petia Radeva; Jordi Vitria; Maria Teresa Anguera
	Title	Automatic Detection of Dominance and Expected Interest			Type	Journal Article
	Year	2010	Publication	EURASIP Journal on Advances in Signal Processing	Abbreviated Journal	EURASIPJ
	Volume		Issue		Pages	12
	Keywords
	Abstract	Article ID 491819 Social Signal Processing is an emergent area of research that focuses on the analysis of social constructs. Dominance and interest are two of these social constructs. Dominance refers to the level of influence a person has in a conversation. Interest, when referred in terms of group interactions, can be defined as the degree of engagement that the members of a group collectively display during their interaction. In this paper, we argue that only using behavioral motion information, we are able to predict the interest of observers when looking at face-to-face interactions as well as the dominant people. First, we propose a simple set of movement-based features from body, face, and mouth activity in order to define a higher set of interaction indicators. The considered indicators are manually annotated by observers. Based on the opinions obtained, we define an automatic binary dominance detection problem and a multiclass interest quantification problem. Error-Correcting Output Codes framework is used to learn to rank the perceived observer's interest in face-to-face interactions meanwhile Adaboost is used to solve the dominant detection problem. The automatic system shows good correlation between the automatic categorization results and the manual ranking made by the observers in both dominance and interest detection problems.
	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	1110-8657	ISBN		Medium
	Area		Expedition		Conference
	Notes	OR;MILAB;HUPBA;MV			Approved	no
	Call Number	BCNPCL @ bcnpcl @ EPR2010d			Serial	1283
Permanent link to this record



	Author	O. Fors; J. Nuñez; Xavier Otazu; A. Prades; Robert D. Cardinal
	Title	Improving the Ability of Image Sensors to Detect Faint Stars and Moving Objects Using Image Deconvolution Techniques			Type	Journal Article
	Year	2010	Publication	Sensors	Abbreviated Journal	SENS
	Volume	10	Issue	3	Pages	1743–1752
	Keywords	image processing; image deconvolution; faint stars; space debris; wavelet transform
	Abstract	Abstract: In this paper we show how the techniques of image deconvolution can increase the ability of image sensors as, for example, CCD imagers, to detect faint stars or faint orbital objects (small satellites and space debris). In the case of faint stars, we show that this benefit is equivalent to double the quantum efficiency of the used image sensor or to increase the effective telescope aperture by more than 30% without decreasing the astrometric precision or introducing artificial bias. In the case of orbital objects, the deconvolution technique can double the signal-to-noise ratio of the image, which helps to discover and control dangerous objects as space debris or lost satellites. The benefits obtained using CCD detectors can be extrapolated to any kind of image sensors.
	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	CIC			Approved	no
	Call Number	CAT @ cat @ FNO2010			Serial	1285
Permanent link to this record



	Author	Sergio Escalera; Oriol Pujol; Petia Radeva
	Title	Error-Correcting Output Codes Library			Type	Journal Article
	Year	2010	Publication	Journal of Machine Learning Research	Abbreviated Journal	JMLR
	Volume	11	Issue		Pages	661-664
	Keywords
	Abstract	(Feb):661−664 In this paper, we present an open source Error-Correcting Output Codes (ECOC) library. The ECOC framework is a powerful tool to deal with multi-class categorization problems. This library contains both state-of-the-art coding (one-versus-one, one-versus-all, dense random, sparse random, DECOC, forest-ECOC, and ECOC-ONE) and decoding designs (hamming, euclidean, inverse hamming, laplacian, β-density, attenuated, loss-based, probabilistic kernel-based, and loss-weighted) with the parameters defined by the authors, as well as the option to include your own coding, decoding, and base classifier.
	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	1532-4435	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;HUPBA			Approved	no
	Call Number	BCNPCL @ bcnpcl @ EPR2010c			Serial	1286
Permanent link to this record



	Author	David Rotger; Petia Radeva; N. Bruining
	Title	Automatic Detection of Bioabsorbable Coronary Stents in IVUS Images using a Cascade of Classifiers			Type	Journal Article
	Year	2010	Publication	IEEE Transactions on Information Technology in Biomedicine	Abbreviated Journal	TITB
	Volume	14	Issue	2	Pages	535 – 537
	Keywords
	Abstract	Bioabsorbable drug-eluting coronary stents present a very promising improvement to the common metallic ones solving some of the most important problems of stent implantation: the late restenosis. These stents made of poly-L-lactic acid cause a very subtle acoustic shadow (compared to the metallic ones) making difficult the automatic detection and measurements in images. In this paper, we propose a novel approach based on a cascade of GentleBoost classifiers to detect the stent struts using structural features to code the information of the different subregions of the struts. A stochastic gradient descent method is applied to optimize the overall performance of the detector. Validation results of struts detection are very encouraging with an average F-measure of 81%.
	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	MILAB			Approved	no
	Call Number	BCNPCL @ bcnpcl @ RRB2010			Serial	1287
Permanent link to this record



	Author	Alicia Fornes; Josep Llados; Gemma Sanchez; Dimosthenis Karatzas
	Title	Rotation Invariant Hand-Drawn Symbol Recognition based on a Dynamic Time Warping Model			Type	Journal Article
	Year	2010	Publication	International Journal on Document Analysis and Recognition	Abbreviated Journal	IJDAR
	Volume	13	Issue	3	Pages	229–241
	Keywords
	Abstract	One of the major difficulties of handwriting symbol recognition is the high variability among symbols because of the different writer styles. In this paper, we introduce a robust approach for describing and recognizing hand-drawn symbols tolerant to these writer style differences. This method, which is invariant to scale and rotation, is based on the dynamic time warping (DTW) algorithm. The symbols are described by vector sequences, a variation of the DTW distance is used for computing the matching distance, and K-Nearest Neighbor is used to classify them. Our approach has been evaluated in two benchmarking scenarios consisting of hand-drawn symbols. Compared with state-of-the-art methods for symbol recognition, our method shows higher tolerance to the irregular deformations induced by hand-drawn strokes.
	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	1433-2833	ISBN		Medium
	Area		Expedition		Conference
	Notes	DAG; IF 2009: 1,213			Approved	no
	Call Number	DAG @ dag @ FLS2010a			Serial	1288
Permanent link to this record



	Author	Mathieu Nicolas Delalandre; Ernest Valveny; Tony Pridmore; Dimosthenis Karatzas
	Title	Generation of Synthetic Documents for Performance Evaluation of Symbol Recognition & Spotting Systems			Type	Journal Article
	Year	2010	Publication	International Journal on Document Analysis and Recognition	Abbreviated Journal	IJDAR
	Volume	13	Issue	3	Pages	187-207
	Keywords
	Abstract	This paper deals with the topic of performance evaluation of symbol recognition & spotting systems. We propose here a new approach to the generation of synthetic graphics documents containing non-isolated symbols in a real context. This approach is based on the definition of a set of constraints that permit us to place the symbols on a pre-defined background according to the properties of a particular domain (architecture, electronics, engineering, etc.). In this way, we can obtain a large amount of images resembling real documents by simply defining the set of constraints and providing a few pre-defined backgrounds. As documents are synthetically generated, the groundtruth (the location and the label of every symbol) becomes automatically available. We have applied this approach to the generation of a large database of architectural drawings and electronic diagrams, which shows the flexibility of the system. Performance evaluation experiments of a symbol localization system show that our approach permits to generate documents with different features that are reflected in variation of localization results.
	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	1433-2833	ISBN		Medium
	Area		Expedition		Conference
	Notes	DAG			Approved	no
	Call Number	DAG @ dag @ DVP2010			Serial	1289
Permanent link to this record



	Author	Jose Antonio Rodriguez; Florent Perronnin; Gemma Sanchez; Josep Llados
	Title	Unsupervised writer adaptation of whole-word HMMs with application to word-spotting			Type	Journal Article
	Year	2010	Publication	Pattern Recognition Letters	Abbreviated Journal	PRL
	Volume	31	Issue	8	Pages	742–749
	Keywords	Word-spotting; Handwriting recognition; Writer adaptation; Hidden Markov model; Document analysis
	Abstract	In this paper we propose a novel approach for writer adaptation in a handwritten word-spotting task. The method exploits the fact that the semi-continuous hidden Markov model separates the word model parameters into (i) a codebook of shapes and (ii) a set of word-specific parameters. Our main contribution is to employ this property to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best of our knowledge, this is the first work dealing with adaptation for word-spotting. The preliminary version of this paper obtained an IBM Best Student Paper Award at the 19th International Conference on Pattern Recognition.
	Address
	Corporate Author				Thesis
	Publisher	Elsevier	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	DAG			Approved	no
	Call Number	DAG @ dag @ RPS2010			Serial	1290
Permanent link to this record



	Author	Marçal Rusiñol; Josep Llados
	Title	Symbol Spotting in Digital Libraries:Focused Retrieval over Graphic-rich Document Collections			Type	Book Whole
	Year	2010	Publication	Symbol Spotting in Digital Libraries:Focused Retrieval over Graphic-rich Document Collections	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	Focused Retrieval , Graphical Pattern Indexation,Graphics Recognition ,Pattern Recognition , Performance Evaluation , Symbol Description ,Symbol Spotting
	Abstract	The specific problem of symbol recognition in graphical documents requires additional techniques to those developed for character recognition. The most well-known obstacle is the so-called Sayre paradox: Correct recognition requires good segmentation, yet improvement in segmentation is achieved using information provided by the recognition process. This dilemma can be avoided by techniques that identify sets of regions containing useful information. Such symbol-spotting methods allow the detection of symbols in maps or technical drawings without having to fully segment or fully recognize the entire content. This unique text/reference provides a complete, integrated and large-scale solution to the challenge of designing a robust symbol-spotting method for collections of graphic-rich documents. The book examines a number of features and descriptors, from basic photometric descriptors commonly used in computer vision techniques to those specific to graphical shapes, presenting a methodology which can be used in a wide variety of applications. Additionally, readers are supplied with an insight into the problem of performance evaluation of spotting methods. Some very basic knowledge of pattern recognition, document image analysis and graphics recognition is assumed.
	Address
	Corporate Author				Thesis
	Publisher	Springer	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-1-84996-208-7	Medium
	Area		Expedition		Conference
	Notes	DAG			Approved	no
	Call Number	DAG @ dag @ RuL2010a			Serial	1292
Permanent link to this record



	Author	Miquel Ferrer; Ernest Valveny; F. Serratosa; K. Riesen; Horst Bunke
	Title	Generalized Median Graph Computation by Means of Graph Embedding in Vector Spaces			Type	Journal Article
	Year	2010	Publication	Pattern Recognition	Abbreviated Journal	PR
	Volume	43	Issue	4	Pages	1642–1655
	Keywords	Graph matching; Weighted mean of graphs; Median graph; Graph embedding; Vector spaces
	Abstract	The median graph has been presented as a useful tool to represent a set of graphs. Nevertheless its computation is very complex and the existing algorithms are restricted to use limited amount of data. In this paper we propose a new approach for the computation of the median graph based on graph embedding. Graphs are embedded into a vector space and the median is computed in the vector domain. We have designed a procedure based on the weighted mean of a pair of graphs to go from the vector domain back to the graph domain in order to obtain a final approximation of the median graph. Experiments on three different databases containing large graphs show that we succeed to compute good approximations of the median graph. We have also applied the median graph to perform some basic classification tasks achieving reasonable good results. These experiments on real data open the door to the application of the median graph to a number of more complex machine learning algorithms where a representative of a set of graphs is needed.
	Address
	Corporate Author				Thesis
	Publisher	Elsevier	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	DAG			Approved	no
	Call Number	DAG @ dag @ FVS2010			Serial	1294
Permanent link to this record



	Author	Antonio Lopez; Joan Serrat; Cristina Cañero; Felipe Lumbreras; T. Graf
	Title	Robust lane markings detection and road geometry computation			Type	Journal Article
	Year	2010	Publication	International Journal of Automotive Technology	Abbreviated Journal	IJAT
	Volume	11	Issue	3	Pages	395–407
	Keywords	lane markings
	Abstract	Detection of lane markings based on a camera sensor can be a low-cost solution to lane departure and curve-over-speed warnings. A number of methods and implementations have been reported in the literature. However, reliable detection is still an issue because of cast shadows, worn and occluded markings, variable ambient lighting conditions, for example. We focus on increasing detection reliability in two ways. First, we employed an image feature other than the commonly used edges: ridges, which we claim addresses this problem better. Second, we adapted RANSAC, a generic robust estimation method, to fit a parametric model of a pair of lane lines to the image features, based on both ridgeness and ridge orientation. In addition, the model was fitted for the left and right lane lines simultaneously to enforce a consistent result. Four measures of interest for driver assistance applications were directly computed from the fitted parametric model at each frame: lane width, lane curvature, and vehicle yaw angle and lateral offset with regard the lane medial axis. We qualitatively assessed our method in video sequences captured on several road types and under very different lighting conditions. We also quantitatively assessed it on synthetic but realistic video sequences for which road geometry and vehicle trajectory ground truth are known.
	Address
	Corporate Author				Thesis
	Publisher	The Korean Society of Automotive Engineers	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1229-9138	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	ADAS @ adas @ LSC2010			Serial	1300
Permanent link to this record



	Author	David Geronimo; Angel Sappa; Antonio Lopez
	Title	Stereo-based Candidate Generation for Pedestrian Protection Systems			Type	Book Chapter
	Year	2010	Publication	Binocular Vision: Development, Depth Perception and Disorders	Abbreviated Journal
	Volume		Issue	9	Pages	189–208
	Keywords	Pedestrian Detection
	Abstract	This chapter describes a stereo-based algorithm that provides candidate image windows to a latter 2D classification stage in an on-board pedestrian detection system. The proposed algorithm, which consists of three stages, is based on the use of both stereo imaging and scene prior knowledge (i.e., pedestrians are on the ground) to reduce the candidate searching space. First, a successful road surface fitting algorithm provides estimates on the relative ground-camera pose. This stage directs the search toward the road area thus avoiding irrelevant regions like the sky. Then, three different schemes are used to scan the estimated road surface with pedestrian-sized windows: (a) uniformly distributed through the road surface (3D); (b) uniformly distributed through the image (2D); (c) not uniformly distributed but according to a quadratic function (combined 2D-3D). Finally, the set of candidate windows is reduced by analyzing their 3D content. Experimental results of the proposed algorithm, together with statistics of searching space reduction are provided.
	Address
	Corporate Author				Thesis
	Publisher	NOVA Publishers	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	ADAS			Approved	no
	Call Number	ADAS @ adas @ GSL2010			Serial	1301
Permanent link to this record