|   | 
Details
   web
Records
Author Oualid M. Benkarim; Petia Radeva; Laura Igual
Title (down) Label Consistent Multiclass Discriminative Dictionary Learning for MRI Segmentation Type Conference Article
Year 2014 Publication 8th Conference on Articulated Motion and Deformable Objects Abbreviated Journal
Volume 8563 Issue Pages 138-147
Keywords MRI segmentation; sparse representation; discriminative dic- tionary learning; multiclass classi cation
Abstract The automatic segmentation of multiple subcortical structures in brain Magnetic Resonance Images (MRI) still remains a challenging task. In this paper, we address this problem using sparse representation and discriminative dictionary learning, which have shown promising results in compression, image denoising and recently in MRI segmentation. Particularly, we use multiclass dictionaries learned from a set of brain atlases to simultaneously segment multiple subcortical structures.
We also impose dictionary atoms to be specialized in one given class using label consistent K-SVD, which can alleviate the bias produced by unbalanced libraries, present when dealing with small structures. The proposed method is compared with other state of the art approaches for the segmentation of the Basal Ganglia of 35 subjects of a public dataset.
The promising results of the segmentation method show the eciency of the multiclass discriminative dictionary learning algorithms in MRI segmentation problems.
Address Palma de Mallorca; July 2014
Corporate Author Thesis
Publisher Springer International Publishing 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 978-3-319-08848-8 Medium
Area Expedition Conference AMDO
Notes MILAB; OR Approved no
Call Number Admin @ si @ BRI2014 Serial 2494
Permanent link to this record
 

 
Author Volkmar Frinken; Andreas Fischer; Markus Baumgartner; Horst Bunke
Title (down) Keyword spotting for self-training of BLSTM NN based handwriting recognition systems Type Journal Article
Year 2014 Publication Pattern Recognition Abbreviated Journal PR
Volume 47 Issue 3 Pages 1073-1082
Keywords Document retrieval; Keyword spotting; Handwriting recognition; Neural networks; Semi-supervised learning
Abstract The automatic transcription of unconstrained continuous handwritten text requires well trained recognition systems. The semi-supervised paradigm introduces the concept of not only using labeled data but also unlabeled data in the learning process. Unlabeled data can be gathered at little or not cost. Hence it has the potential to reduce the need for labeling training data, a tedious and costly process. Given a weak initial recognizer trained on labeled data, self-training can be used to recognize unlabeled data and add words that were recognized with high confidence to the training set for re-training. This process is not trivial and requires great care as far as selecting the elements that are to be added to the training set is concerned. In this paper, we propose to use a bidirectional long short-term memory neural network handwritten recognition system for keyword spotting in order to select new elements. A set of experiments shows the high potential of self-training for bootstrapping handwriting recognition systems, both for modern and historical handwritings, and demonstrate the benefits of using keyword spotting over previously published self-training schemes.
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 DAG; 600.077; 602.101 Approved no
Call Number Admin @ si @ FFB2014 Serial 2297
Permanent link to this record
 

 
Author Frederic Sampedro; Sergio Escalera; Anna Puig
Title (down) Iterative Multiclass Multiscale Stacked Sequential Learning: definition and application to medical volume segmentation Type Journal Article
Year 2014 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 46 Issue Pages 1-10
Keywords Machine learning; Sequential learning; Multi-class problems; Contextual learning; Medical volume segmentation
Abstract In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel contextual information of the structures of interest in order to improve its segmentation performance results. Without any feature set or learning algorithm prior assumption, the proposed scheme directly seeks to learn the contextual properties of a region from the predicted classifications of previous classifiers within an iterative scheme. Performance results regarding segmentation accuracy in three two-class and multi-class medical volume datasets show a significant improvement with respect to state of the art alternatives. Due to its easiness of implementation and its independence of feature space and learning algorithm, the presented machine learning framework could be taken into consideration as a first choice in complex volume segmentation scenarios.
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 HuPBA;MILAB Approved no
Call Number Admin @ si @ SEP2014 Serial 2550
Permanent link to this record
 

 
Author Michal Drozdzal; Jordi Vitria; Santiago Segui; Carolina Malagelada; Fernando Azpiroz; Petia Radeva
Title (down) Intestinal event segmentation for endoluminal video analysis Type Conference Article
Year 2014 Publication 21st IEEE International Conference on Image Processing Abbreviated Journal
Volume Issue Pages 3592 - 3596
Keywords
Abstract
Address Paris; Francia; October 2014
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 ICIP
Notes MILAB; OR;MV Approved no
Call Number Admin @ si @ DVS2014 Serial 2565
Permanent link to this record
 

 
Author Anjan Dutta
Title (down) Inexact Subgraph Matching Applied to Symbol Spotting in Graphical Documents Type Book Whole
Year 2014 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract There is a resurgence in the use of structural approaches in the usual object recognition and retrieval problem. Graph theory, in particular, graph matching plays a relevant role in that. Specifically, the detection of an object (or a part of that) in an image in terms of structural features can be formulated as a subgraph matching. Subgraph matching is a challenging task. Specially due to the presence of outliers most of the graph matching algorithms do not perform well in subgraph matching scenario. Also exact subgraph isomorphism has proven to be an NP-complete problem. So naturally, in graph matching community, there are lot of efforts addressing the problem of subgraph matching within suboptimal bound. Most of them work with approximate algorithms that try to get an inexact solution in estimated way. In addition, usual recognition must cope with distortion. Inexact graph matching consists in finding the best isomorphism under a similarity measure. Theoretically this thesis proposes algorithms for solving subgraph matching in an approximate and inexact way.
We consider the symbol spotting problem on graphical documents or line drawings from application point of view. This is a well known problem in the graphics recognition community. It can be further applied for indexing and classification of documents based on their contents. The structural nature of this kind of documents easily motivates one for giving a graph based representation. So the symbol spotting problem on graphical documents can be considered as a subgraph matching problem. The main challenges in this application domain is the noise and distortions that might come during the usage, digitalization and raster to vector conversion of those documents. Apart from that computer vision nowadays is not any more confined within a limited number of images. So dealing a huge number of images with graph based method is a further challenge.
In this thesis, on one hand, we have worked on efficient and robust graph representation to cope with the noise and distortions coming from documents. On the other hand, we have worked on different graph based methods and framework to solve the subgraph matching problem in a better approximated way, which can also deal with considerable number of images. Firstly, we propose a symbol spotting method by hashing serialized subgraphs. Graph serialization allows to create factorized substructures such as graph paths, which can be organized in hash tables depending on the structural similarities of the serialized subgraphs. The involvement of hashing techniques helps to reduce the search space substantially and speeds up the spotting procedure. Secondly, we introduce contextual similarities based on the walk based propagation on tensor product graph. These contextual similarities involve higher order information and more reliable than pairwise similarities. We use these higher order similarities to formulate subgraph matching as a node and edge selection problem in the tensor product graph. Thirdly, we propose near convex grouping to form near convex region adjacency graph which eliminates the limitations of traditional region adjacency graph representation for graphic recognition. Fourthly, we propose a hierarchical graph representation by simplifying/correcting the structural errors to create a hierarchical graph of the base graph. Later these hierarchical graph structures are matched with some graph matching methods. Apart from that, in this thesis we have provided an overall experimental comparison of all the methods and some of the state-of-the-art methods. Furthermore, some dataset models have also been proposed.
Address
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Josep Llados;Umapada Pal
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-940902-4-0 Medium
Area Expedition Conference
Notes DAG; 600.077 Approved no
Call Number Admin @ si @ Dut2014 Serial 2465
Permanent link to this record
 

 
Author Jiaolong Xu; Sebastian Ramos; David Vazquez; Antonio Lopez
Title (down) Incremental Domain Adaptation of Deformable Part-based Models Type Conference Article
Year 2014 Publication 25th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords Pedestrian Detection; Part-based models; Domain Adaptation
Abstract Nowadays, classifiers play a core role in many computer vision tasks. The underlying assumption for learning classifiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classifiers. However, in practice, there are different reasons that can break this constancy assumption. Accordingly, reusing existing classifiers by adapting them from the previous training environment (source domain) to the new testing one (target domain)
is an approach with increasing acceptance in the computer vision community. In this paper we focus on the domain adaptation of deformable part-based models (DPMs) for object detection. In particular, we focus on a relatively unexplored scenario, i.e. incremental domain adaptation for object detection assuming weak-labeling. Therefore, our algorithm is ready to improve existing source-oriented DPM-based detectors as soon as a little amount of labeled target-domain training data is available, and keeps improving as more of such data arrives in a continuous fashion. For achieving this, we follow a multiple
instance learning (MIL) paradigm that operates in an incremental per-image basis. As proof of concept, we address the challenging scenario of adapting a DPM-based pedestrian detector trained with synthetic pedestrians to operate in real-world scenarios. The obtained results show that our incremental adaptive models obtain equally good accuracy results as the batch learned models, while being more flexible for handling continuously arriving target-domain data.
Address Nottingham; uk; September 2014
Corporate Author Thesis
Publisher BMVA Press Place of Publication Editor Valstar, Michel and French, Andrew and Pridmore, Tony
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference BMVC
Notes ADAS; 600.057; 600.054; 600.076 Approved no
Call Number XRV2014c; ADAS @ adas @ xrv2014c Serial 2455
Permanent link to this record
 

 
Author Joan M. Nuñez; Jorge Bernal; Miquel Ferrer; Fernando Vilariño
Title (down) Impact of Keypoint Detection on Graph-based Characterization of Blood Vessels in Colonoscopy Videos Type Conference Article
Year 2014 Publication CARE workshop Abbreviated Journal
Volume Issue Pages
Keywords Colonoscopy; Graph Matching; Biometrics; Vessel; Intersection
Abstract We explore the potential of the use of blood vessels as anatomical landmarks for developing image registration methods in colonoscopy images. An unequivocal representation of blood vessels could be used to guide follow-up methods to track lesions over different interventions. We propose a graph-based representation to characterize network structures, such as blood vessels, based on the use of intersections and endpoints. We present a study consisting of the assessment of the minimal performance a keypoint detector should achieve so that the structure can still be recognized. Experimental results prove that, even by achieving a loss of 35% of the keypoints, the descriptive power of the associated graphs to the vessel pattern is still high enough to recognize blood vessels.
Address Boston; USA; September 2014
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 CARE
Notes MV; DAG; 600.060; 600.047; 600.077;SIAI Approved no
Call Number Admin @ si @ NBF2014 Serial 2504
Permanent link to this record
 

 
Author Klaus Broelemann; Anjan Dutta; Xiaoyi Jiang; Josep Llados
Title (down) Hierarchical Plausibility-Graphs for Symbol Spotting in Graphical Documents Type Book Chapter
Year 2014 Publication Graphics Recognition. Current Trends and Challenges Abbreviated Journal
Volume 8746 Issue Pages 25-37
Keywords
Abstract Graph representation of graphical documents often suffers from noise such as spurious nodes and edges, and their discontinuity. In general these errors occur during the low-level image processing viz. binarization, skeletonization, vectorization etc. Hierarchical graph representation is a nice and efficient way to solve this kind of problem by hierarchically merging node-node and node-edge depending on the distance. But the creation of hierarchical graph representing the graphical information often uses hard thresholds on the distance to create the hierarchical nodes (next state) of the lower nodes (or states) of a graph. As a result, the representation often loses useful information. This paper introduces plausibilities to the nodes of hierarchical graph as a function of distance and proposes a modified algorithm for matching subgraphs of the hierarchical graphs. The plausibility-annotated nodes help to improve the performance of the matching algorithm on two hierarchical structures. To show the potential of this approach, we conduct an experiment with the SESYD dataset.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor Bart Lamiroy; Jean-Marc Ogier
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-662-44853-3 Medium
Area Expedition Conference
Notes DAG; 600.045; 600.056; 600.061; 600.077 Approved no
Call Number Admin @ si @ BDJ2014 Serial 2699
Permanent link to this record
 

 
Author Josep Llados; Marçal Rusiñol
Title (down) Graphics Recognition Techniques Type Book Chapter
Year 2014 Publication Handbook of Document Image Processing and Recognition Abbreviated Journal
Volume D Issue Pages 489-521
Keywords Dimension recognition; Graphics recognition; Graphic-rich documents; Polygonal approximation; Raster-to-vector conversion; Texture-based primitive extraction; Text-graphics separation
Abstract This chapter describes the most relevant approaches for the analysis of graphical documents. The graphics recognition pipeline can be splitted into three tasks. The low level or lexical task extracts the basic units composing the document. The syntactic level is focused on the structure, i.e., how graphical entities are constructed, and involves the location and classification of the symbols present in the document. The third level is a functional or semantic level, i.e., it models what the graphical symbols do and what they mean in the context where they appear. This chapter covers the lexical level, while the next two chapters are devoted to the syntactic and semantic level, respectively. The main problems reviewed in this chapter are raster-to-vector conversion (vectorization algorithms) and the separation of text and graphics components. The research and industrial communities have provided standard methods achieving reasonable performance levels. Hence, graphics recognition techniques can be considered to be in a mature state from a scientific point of view. Additionally this chapter provides insights on some related problems, namely, the extraction and recognition of dimensions in engineering drawings, and the recognition of hatched and tiled patterns. Both problems are usually associated, even integrated, in the vectorization process.
Address
Corporate Author Thesis
Publisher Springer London Place of Publication Editor D. Doermann; K. Tombre
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-0-85729-858-4 Medium
Area Expedition Conference
Notes DAG; 600.077 Approved no
Call Number Admin @ si @ LlR2014 Serial 2380
Permanent link to this record
 

 
Author Mohammad Ali Bagheri; Qigang Gao; Sergio Escalera
Title (down) Generic Subclass Ensemble: A Novel Approach to Ensemble Classification Type Conference Article
Year 2014 Publication 22nd International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 1254 - 1259
Keywords
Abstract Multiple classifier systems, also known as classifier ensembles, have received great attention in recent years because of their improved classification accuracy in different applications. In this paper, we propose a new general approach to ensemble classification, named generic subclass ensemble, in which each base classifier is trained with data belonging to a subset of classes, and thus discriminates among a subset of target categories. The ensemble classifiers are then fused using a combination rule. The proposed approach differs from existing methods that manipulate the target attribute, since in our approach individual classification problems are not restricted to two-class problems. We perform a series of experiments to evaluate the efficiency of the generic subclass approach on a set of benchmark datasets. Experimental results with multilayer perceptrons show that the proposed approach presents a viable alternative to the most commonly used ensemble classification approaches.
Address Stockholm; August 2014
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 Medium
Area Expedition Conference ICPR
Notes HuPBA;MILAB Approved no
Call Number Admin @ si @ BGE2014b Serial 2445
Permanent link to this record
 

 
Author Svebor Karaman; Giuseppe Lisanti; Andrew Bagdanov; Alberto del Bimbo
Title (down) From re-identification to identity inference: Labeling consistency by local similarity constraints Type Book Chapter
Year 2014 Publication Person Re-Identification Abbreviated Journal
Volume 2 Issue Pages 287-307
Keywords re-identification; Identity inference; Conditional random fields; Video surveillance
Abstract In this chapter, we introduce the problem of identity inference as a generalization of person re-identification. It is most appropriate to distinguish identity inference from re-identification in situations where a large number of observations must be identified without knowing a priori that groups of test images represent the same individual. The standard single- and multishot person re-identification common in the literature are special cases of our formulation. We present an approach to solving identity inference by modeling it as a labeling problem in a Conditional Random Field (CRF). The CRF model ensures that the final labeling gives similar labels to detections that are similar in feature space. Experimental results are given on the ETHZ, i-LIDS and CAVIAR datasets. Our approach yields state-of-the-art performance for multishot re-identification, and our results on the more general identity inference problem demonstrate that we are able to infer the identity of very many examples even with very few labeled images in the gallery.
Address
Corporate Author Thesis
Publisher Springer London Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2191-6586 ISBN 978-1-4471-6295-7 Medium
Area Expedition Conference
Notes LAMP; 600.079 Approved no
Call Number Admin @ si @KLB2014b Serial 2521
Permanent link to this record
 

 
Author Marçal Rusiñol; Lluis Pere de las Heras; Oriol Ramos Terrades
Title (down) Flowchart Recognition for Non-Textual Information Retrieval in Patent Search Type Journal Article
Year 2014 Publication Information Retrieval Abbreviated Journal IR
Volume 17 Issue 5-6 Pages 545-562
Keywords Flowchart recognition; Patent documents; Text/graphics separation; Raster-to-vector conversion; Symbol recognition
Abstract Relatively little research has been done on the topic of patent image retrieval and in general in most of the approaches the retrieval is performed in terms of a similarity measure between the query image and the images in the corpus. However, systems aimed at overcoming the semantic gap between the visual description of patent images and their conveyed concepts would be very helpful for patent professionals. In this paper we present a flowchart recognition method aimed at achieving a structured representation of flowchart images that can be further queried semantically. The proposed method was submitted to the CLEF-IP 2012 flowchart recognition task. We report the obtained results on this dataset.
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 1386-4564 ISBN Medium
Area Expedition Conference
Notes DAG; 600.077 Approved no
Call Number Admin @ si @ RHR2013 Serial 2342
Permanent link to this record
 

 
Author Claudio Baecchi; Francesco Turchini; Lorenzo Seidenari; Andrew Bagdanov; Alberto del Bimbo
Title (down) Fisher vectors over random density forest for object recognition Type Conference Article
Year 2014 Publication 22nd International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 4328-4333
Keywords
Abstract
Address Stockholm; Sweden; August 2014
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 ICPR
Notes LAMP; 600.079 Approved no
Call Number Admin @ si @ BTS2014 Serial 2518
Permanent link to this record
 

 
Author P. Ricaurte ; C. Chilan; Cristhian A. Aguilera-Carrasco; Boris X. Vintimilla; Angel Sappa
Title (down) Feature Point Descriptors: Infrared and Visible Spectra Type Journal Article
Year 2014 Publication Sensors Abbreviated Journal SENS
Volume 14 Issue 2 Pages 3690-3701
Keywords
Abstract This manuscript evaluates the behavior of classical feature point descriptors when they are used in images from long-wave infrared spectral band and compare them with the results obtained in the visible spectrum. Robustness to changes in rotation, scaling, blur, and additive noise are analyzed using a state of the art framework. Experimental results using a cross-spectral outdoor image data set are presented and conclusions from these experiments are given.
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 ADAS;600.055; 600.076 Approved no
Call Number Admin @ si @ RCA2014a Serial 2474
Permanent link to this record
 

 
Author Hongxing Gao; Marçal Rusiñol; Dimosthenis Karatzas; Josep Llados
Title (down) Fast Structural Matching for Document Image Retrieval through Spatial Databases Type Conference Article
Year 2014 Publication Document Recognition and Retrieval XXI Abbreviated Journal
Volume 9021 Issue Pages
Keywords Document image retrieval; distance transform; MSER; spatial database
Abstract The structure of document images plays a signi cant role in document analysis thus considerable e orts have been made towards extracting and understanding document structure, usually in the form of layout analysis approaches. In this paper, we rst employ Distance Transform based MSER (DTMSER) to eciently extract stable document structural elements in terms of a dendrogram of key-regions. Then a fast structural matching method is proposed to query the structure of document (dendrogram) based on a spatial database which facilitates the formulation of advanced spatial queries. The experiments demonstrate a signi cant improvement in a document retrieval scenario when compared to the use of typical Bag of Words (BoW) and pyramidal BoW descriptors.
Address Amsterdam; September 2014
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 SPIE-DRR
Notes DAG; 600.056; 600.061; 600.077 Approved no
Call Number Admin @ si @ GRK2014a Serial 2496
Permanent link to this record