toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Juan Ramon Terven Salinas; Joaquin Salas; Bogdan Raducanu edit   pdf
url  doi
openurl 
  Title New Opportunities for Computer Vision-Based Assistive Technology Systems for the Visually Impaired Type Journal Article
  Year 2014 Publication Computer Abbreviated Journal COMP  
  Volume 47 Issue 4 Pages 52-58  
  Keywords  
  Abstract Computing advances and increased smartphone use gives technology system designers greater flexibility in exploiting computer vision to support visually impaired users. Understanding these users' needs will certainly provide insight for the development of improved usability of computing devices.  
  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 0018-9162 ISBN Medium (down)  
  Area Expedition Conference  
  Notes OR;MV Approved no  
  Call Number Admin @ si @ TSR2014a Serial 2317  
Permanent link to this record
 

 
Author Dimosthenis Karatzas; Faisal Shafait; Seiichi Uchida; Masakazu Iwamura; Lluis Gomez; Sergi Robles; Joan Mas; David Fernandez; Jon Almazan; Lluis Pere de las Heras edit   pdf
doi  openurl
  Title ICDAR 2013 Robust Reading Competition Type Conference Article
  Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 1484-1493  
  Keywords  
  Abstract This report presents the final results of the ICDAR 2013 Robust Reading Competition. The competition is structured in three Challenges addressing text extraction in different application domains, namely born-digital images, real scene images and real-scene videos. The Challenges are organised around specific tasks covering text localisation, text segmentation and word recognition. The competition took place in the first quarter of 2013, and received a total of 42 submissions over the different tasks offered. This report describes the datasets and ground truth specification, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.  
  Address Washington; USA; August 2013  
  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 1520-5363 ISBN Medium (down)  
  Area Expedition Conference ICDAR  
  Notes DAG; 600.056 Approved no  
  Call Number Admin @ si @ KSU2013 Serial 2318  
Permanent link to this record
 

 
Author Lluis Gomez edit   pdf
openurl 
  Title Perceptual Organization for Text Extraction in Natural Scenes Type Report
  Year 2012 Publication CVC Technical Report Abbreviated Journal  
  Volume 173 Issue Pages  
  Keywords  
  Abstract  
  Address Bellaterra  
  Corporate Author Thesis Master's 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 (down)  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ Gom2012 Serial 2309  
Permanent link to this record
 

 
Author Lluis Gomez; Dimosthenis Karatzas edit   pdf
doi  openurl
  Title Multi-script Text Extraction from Natural Scenes Type Conference Article
  Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 467-471  
  Keywords  
  Abstract Scene text extraction methodologies are usually based in classification of individual regions or patches, using a priori knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organisation through which text emerges as a perceptually significant group of atomic objects. Therefore humans are able to detect text even in languages and scripts never seen before. In this paper, we argue that the text extraction problem could be posed as the detection of meaningful groups of regions. We present a method built around a perceptual organisation framework that exploits collaboration of proximity and similarity laws to create text-group hypotheses. Experiments demonstrate that our algorithm is competitive with state of the art approaches on a standard dataset covering text in variable orientations and two languages.  
  Address Washington; USA; August 2013  
  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 1520-5363 ISBN Medium (down)  
  Area Expedition Conference ICDAR  
  Notes DAG; 600.056; 601.158; 601.197 Approved no  
  Call Number Admin @ si @ GoK2013 Serial 2310  
Permanent link to this record
 

 
Author Adriana Romero; Carlo Gatta edit   pdf
doi  isbn
openurl 
  Title Do We Really Need All These Neurons? Type Conference Article
  Year 2013 Publication 6th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal  
  Volume 7887 Issue Pages 460--467  
  Keywords Retricted Boltzmann Machine; hidden units; unsupervised learning; classification  
  Abstract Restricted Boltzmann Machines (RBMs) are generative neural networks that have received much attention recently. In particular, choosing the appropriate number of hidden units is important as it might hinder their representative power. According to the literature, RBM require numerous hidden units to approximate any distribution properly. In this paper, we present an experiment to determine whether such amount of hidden units is required in a classification context. We then propose an incremental algorithm that trains RBM reusing the previously trained parameters using a trade-off measure to determine the appropriate number of hidden units. Results on the MNIST and OCR letters databases show that using a number of hidden units, which is one order of magnitude smaller than the literature estimate, suffices to achieve similar performance. Moreover, the proposed algorithm allows to estimate the required number of hidden units without the need of training many RBM from scratch.  
  Address Madeira; Portugal; June 2013  
  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 978-3-642-38627-5 Medium (down)  
  Area Expedition Conference IbPRIA  
  Notes MILAB; 600.046 Approved no  
  Call Number Admin @ si @ RoG2013 Serial 2311  
Permanent link to this record
 

 
Author Fadi Dornaika; Alireza Bosaghzadeh; Bogdan Raducanu edit   pdf
doi  isbn
openurl 
  Title Efficient Graph Construction for Label Propagation based Multi-observation Face Recognition Type Conference Article
  Year 2013 Publication Human Behavior Understanding 4th International Workshop Abbreviated Journal  
  Volume 8212 Issue Pages 124-135  
  Keywords  
  Abstract Workshop on Human Behavior Understanding
Human-machine interaction is a hot topic nowadays in the communities of multimedia and computer vision. 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. Recently, graph-based label propagation for multi-observation face recognition was proposed. However, the associated graphs were constructed in an ad-hoc manner (e.g., using the KNN graph) that cannot adapt optimally to the data. In this paper, we propose a novel approach for efficient and adaptive graph construction that can be used for multi-observation face recognition as well as for other recognition problems. Experimental results performed on Honda video face database, show a distinct advantage of the proposed method over the standard graph construction methods.
 
  Address Barcelona  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-319-02713-5 Medium (down)  
  Area Expedition Conference HBU  
  Notes OR;MV Approved no  
  Call Number Admin @ si @ DBR2013 Serial 2315  
Permanent link to this record
 

 
Author Bogdan Raducanu; Fadi Dornaika edit   pdf
doi  openurl
  Title Embedding new observations via sparse-coding for non-linear manifold learning Type Journal Article
  Year 2014 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 47 Issue 1 Pages 480-492  
  Keywords  
  Abstract Non-linear dimensionality reduction techniques are affected by two critical aspects: (i) the design of the adjacency graphs, and (ii) the embedding of new test data-the out-of-sample problem. For the first aspect, the proposed solutions, in general, were heuristically driven. For the second aspect, the difficulty resides in finding an accurate mapping that transfers unseen data samples into an existing manifold. Past works addressing these two aspects were heavily parametric in the sense that the optimal performance is only achieved for a suitable parameter choice that should be known in advance. In this paper, we demonstrate that the sparse representation theory not only serves for automatic graph construction as shown in recent works, but also represents an accurate alternative for out-of-sample embedding. Considering for a case study the Laplacian Eigenmaps, we applied our method to the face recognition problem. To evaluate the effectiveness of the proposed out-of-sample embedding, experiments are conducted using the K-nearest neighbor (KNN) and Kernel Support Vector Machines (KSVM) classifiers on six public face datasets. The experimental results show that the proposed model is able to achieve high categorization effectiveness as well as high consistency with non-linear embeddings/manifolds obtained in batch modes.  
  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 (down)  
  Area Expedition Conference  
  Notes OR;MV Approved no  
  Call Number Admin @ si @ RaD2013b Serial 2316  
Permanent link to this record
 

 
Author Albert Gordo; Florent Perronnin; Ernest Valveny edit   pdf
url  doi
openurl 
  Title Large-scale document image retrieval and classification with runlength histograms and binary embeddings Type Journal Article
  Year 2013 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 46 Issue 7 Pages 1898-1905  
  Keywords visual document descriptor; compression; large-scale; retrieval; classification  
  Abstract We present a new document image descriptor based on multi-scale runlength
histograms. This descriptor does not rely on layout analysis and can be
computed efficiently. We show how this descriptor can achieve state-of-theart
results on two very different public datasets in classification and retrieval
tasks. Moreover, we show how we can compress and binarize these descriptors
to make them suitable for large-scale applications. We can achieve state-ofthe-
art results in classification using binary descriptors of as few as 16 to 64
bits.
 
  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 0031-3203 ISBN Medium (down)  
  Area Expedition Conference  
  Notes DAG; 600.042; 600.045; 605.203 Approved no  
  Call Number Admin @ si @ GPV2013 Serial 2306  
Permanent link to this record
 

 
Author Albert Gordo; Alicia Fornes; Ernest Valveny edit   pdf
doi  openurl
  Title Writer identification in handwritten musical scores with bags of notes Type Journal Article
  Year 2013 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 46 Issue 5 Pages 1337-1345  
  Keywords  
  Abstract Writer Identification is an important task for the automatic processing of documents. However, the identification of the writer in graphical documents is still challenging. In this work, we adapt the Bag of Visual Words framework to the task of writer identification in handwritten musical scores. A vanilla implementation of this method already performs comparably to the state-of-the-art. Furthermore, we analyze the effect of two improvements of the representation: a Bhattacharyya embedding, which improves the results at virtually no extra cost, and a Fisher Vector representation that very significantly improves the results at the cost of a more complex and costly representation. Experimental evaluation shows results more than 20 points above the state-of-the-art in a new, challenging 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 0031-3203 ISBN Medium (down)  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ GFV2013 Serial 2307  
Permanent link to this record
 

 
Author David Fernandez; Simone Marinai; Josep Llados; Alicia Fornes edit   pdf
doi  isbn
openurl 
  Title Contextual Word Spotting in Historical Manuscripts using Markov Logic Networks Type Conference Article
  Year 2013 Publication 2nd International Workshop on Historical Document Imaging and Processing Abbreviated Journal  
  Volume Issue Pages 36-43  
  Keywords  
  Abstract Natural languages can often be modelled by suitable grammars whose knowledge can improve the word spotting results. The implicit contextual information is even more useful when dealing with information that is intrinsically described as one collection of records. In this paper, we present one approach to word spotting which uses the contextual information of records to improve the results. The method relies on Markov Logic Networks to probabilistically model the relational organization of handwritten records. The performance has been evaluated on the Barcelona Marriages Dataset that contains structured handwritten records that summarize marriage information.  
  Address washington; USA; August 2013  
  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 978-1-4503-2115-0 Medium (down)  
  Area Expedition Conference HIP  
  Notes DAG; 600.056; 600.045; 600.061; 602.006 Approved no  
  Call Number Admin @ si @ FML2013 Serial 2308  
Permanent link to this record
 

 
Author A. M. Here; B. C. Lopez; Debora Gil; J. J. Camarero; Jordi Martinez-Vilalta edit   pdf
url  openurl
  Title A new software to analyse wood anatomical features in conifer species Type Conference Article
  Year 2013 Publication International Symposium on Wood Structure in Plant Biology and Ecology Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract International Symposium on Wood Structure in Plant Biology and Ecology  
  Address Naples; Italy; March 2013  
  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 (down)  
  Area Expedition Conference WSE  
  Notes IAM Approved no  
  Call Number Admin @ si @ HLG2013 Serial 2303  
Permanent link to this record
 

 
Author Enric Marti; Ferran Poveda; Antoni Gurgui; Jaume Rocarias; Debora Gil edit   pdf
openurl 
  Title Una propuesta de seguimiento, tutorías on line y evaluación en la metodología de Aprendizaje Basado en Proyectos Type Miscellaneous
  Year 2013 Publication IV Congreso Internacional UNIVEST Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Poster  
  Address Girona  
  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 (down)  
  Area Expedition Conference UNIVEST  
  Notes IAM Approved no  
  Call Number Admin @ si @ MPG2013a Serial 2304  
Permanent link to this record
 

 
Author Debora Gil; Agnes Borras; Sergio Vera; Miguel Angel Gonzalez Ballester edit   pdf
doi  isbn
openurl 
  Title A Validation Benchmark for Assessment of Medial Surface Quality for Medical Applications Type Conference Article
  Year 2013 Publication 9th International Conference on Computer Vision Systems Abbreviated Journal  
  Volume 7963 Issue Pages 334-343  
  Keywords Medial Surfaces; Shape Representation; Medical Applications; Performance Evaluation  
  Abstract Confident use of medial surfaces in medical decision support systems requires evaluating their quality for detecting pathological deformations and describing anatomical volumes. Validation in the medical imaging field is a challenging task mainly due to the difficulties for getting consensual ground truth. In this paper we propose a validation benchmark for assessing medial surfaces in the context of medical applications. Our benchmark includes a home-made database of synthetic medial surfaces and volumes and specific scores for evaluating surface accuracy, its stability against volume deformations and its capabilities for accurate reconstruction of anatomical volumes.  
  Address Sant Petersburg; Russia; July 2013  
  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 978-3-642-39401-0 Medium (down)  
  Area Expedition Conference ICVS  
  Notes IAM; 600.044; 600.060 Approved no  
  Call Number Admin @ si @ GBV2013 Serial 2300  
Permanent link to this record
 

 
Author Sergio Vera; Miguel Angel Gonzalez Ballester; Debora Gil edit   pdf
openurl 
  Title Volumetric Anatomical Parameterization and Meshing for Inter-patient Liver Coordinate System Deffinition Type Conference Article
  Year 2013 Publication 16th International Conference on Medical Image Computing and Computer Assisted Intervention Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Nagoya; Japan; September 2013  
  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 (down)  
  Area Expedition Conference MICCAI  
  Notes IAM Approved no  
  Call Number Admin @ si @ VGG2013 Serial 2301  
Permanent link to this record
 

 
Author Carles Sanchez; Jorge Bernal; Debora Gil; F. Javier Sanchez edit   pdf
doi  isbn
openurl 
  Title On-line lumen centre detection in gastrointestinal and respiratory endoscopy Type Conference Article
  Year 2013 Publication Second International Workshop Clinical Image-Based Procedures Abbreviated Journal  
  Volume 8361 Issue Pages 31-38  
  Keywords Lumen centre detection; Bronchoscopy; Colonoscopy  
  Abstract We present in this paper a novel lumen centre detection for gastrointestinal and respiratory endoscopic images. The proposed method is based on the appearance and geometry of the lumen, which we defined as the darkest image region which centre is a hub of image gradients. Experimental results validated on the first public annotated gastro-respiratory database prove the reliability of the method for a wide range of images (with precision over 95 %).  
  Address Nagoya; Japan; September 2013  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor Erdt, Marius and Linguraru, Marius George and Oyarzun Laura, Cristina and Shekhar, Raj and Wesarg, Stefan and González Ballester, Miguel Angel and Drechsler, Klaus  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-319-05665-4 Medium (down)  
  Area 800 Expedition Conference CLIP  
  Notes MV; IAM; 600.047; 600.044; 600.060 Approved no  
  Call Number Admin @ si @ SBG2013 Serial 2302  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: