Pàgina inicial > Resultats de la cerca: Visión por computadora
  Consells de cerca
Cerca avançada
Cerca col·leccions:
Ordena'ls per: Mostrar els resultats: Format de visualizació:
Resultats globals: 11 registres trobats en 0.04 segons.
Articles, 8 registres trobats
Documents de recerca, 3 registres trobats
Articles 8 registres trobats  
1.
8 p, 1.1 MB Separating Rigid Motion for Continuous Shape Evolution / Overgaard, Niels Chr. (Malmo University (Suècia)) ; Solem, Jan Erik (Malmo University (Suècia))
A method is proposed for the construction of descent directions for the minimization of energy functionals defined for plane curves. The method is potentially useful in a number of image analysis problems, such as image registration and shape warping, where the standard gradient descent curve evolutions are not always feasible. [...]
2007 - 10.5565/rev/elcvia.144
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 6 n. 2 (2007) p. 1-8  
Registre complet - Creative Commons
2.
17 p, 263.4 KB Genetic Programming for Object Detection : a Two-Phase Approach with an Improved Fitness Function / Zhang, Mengjie (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science) ; Bhowan, Urvesh (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science) ; Ny, Bunna (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science)
This paper describes two innovations that improve the efficiency and effectiveness of a genetic programming approach to object detection problems. The approach uses genetic programming to construct object detection programs that are applied, in a moving window fashion, to the large images to locate the objects of interest. [...]
2007 - 10.5565/rev/elcvia.135
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 6 n. 1 (2007) p. 27-43  
Registre complet - Creative Commons
3.
12 p, 527.1 KB Ear Biometrics Based on Geometrical Feature Extraction / Choraś, Micha (University of Technology and Agriculture (Polònia). Institute of Telecommunication)
Biometrics identification methods proved to be very efficient, more natural and easy for users than traditional methods of human identification. In fact, only biometrics methods truly identify humans, not keys and cards they posses or passwords they should remember. [...]
2005 - 10.5565/rev/elcvia.108
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 5 n. 3 (2005) p. 84-95  
Registre complet - Creative Commons
4.
11 p, 231.8 KB Complex articulated object tracking / Comport, Andrew (IRISA - INRIA (Rennes, França)) ; Marchand, Éric (IRISA - INRIA (Rennes, França)) ; Chaumette, Francois (IRISA - INRIA (Rennes, França))
In this paper new results are presented for tracking complex multi-body objects. The theoretical framework is based on robotics techniques and uses an a-priori model of the object including a general mechanical link description. [...]
2005 - 10.5565/rev/elcvia.103
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 5 n. 3 (2005) p. 21-31  
Registre complet - Creative Commons
5.
11 p, 440.7 KB Frequent Graph Discovery : application to Line Drawing Document Images / Barbu, Eugen (Université de Rouen. Laboratoire PSI) ; Heroux, Pierre (Université de Rouen. Laboratoire PSI) ; Adam, Sebastien (Université de Rouen. Laboratoire PSI) ; Trupin, Eric (Université de Rouen. Laboratoire PSI)
In this paper a sequence of steps is applied to a graph representation of line drawings using concepts from data mining. This process finds frequent subgraphs and then association rules between these subgraphs. [...]
2005 - 10.5565/rev/elcvia.95
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 5 n. 2 (2005) p. 47-57  
Registre complet - Creative Commons
6.
12 p, 198.3 KB Potential Fields as an External Force and Algorithmic Improvements in Deformable Models / Caro Lindo, Andrés (Universidad de Extremadura. Departamento de Informática) ; García Rodríguez, Pablo (Universidad de Extremadura. Departamento de Informática) ; Cernadas García, Eva (Universidade de Vigo. Departamento de Informática) ; Antequera Rojas, Teresa (Universidad de Extremadura. Departamento de Producción Animal y Ciencias de los Alimentos) ; Durán Martín-Merás, María Luisa (Universidad de Extremadura. Departamento de Informática)
Deformable Models are extensively used as a Pattern Recognition technique. They are curves defined within an image domain that can be moved under the influence of internal and external forces. Some trade-offs of standard deformable models algorithms are the selection of image energy function (external force), the location of initial snake and the attraction of contour points to local energy minima when the snake is being deformed. [...]
2003 - 10.5565/rev/elcvia.64
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 2 n. 1 (2003) p. 25-36  
Registre complet - Creative Commons
7.
11 p, 2.5 MB An Appearance-Based Method for Parametric Video Registration / Orriols, Xavier (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Binefa i Valls, Xavier (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Barceló Dachs, Lluis (Centre de Visió per Computador (Bellaterra, Catalunya))
In this paper we address the problem of multi frame video registration using the combination of an appearance-based technique and a parametric model of the transformations. This technique uses an image that is selected as reference frame, and therefore, estimates the transformation that occurred to each frame in the sequence respect to this absolute referenced one. [...]
2003 - 10.5565/rev/elcvia.62
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 2 n. 1 (2003) p. 1-11  
Registre complet - Creative Commons
8.
7 p, 26.7 KB Presentation of ELCVIA / Bunke, Horst (University of Bern. Institut für Informatik und Angewandte Mathematik) ; Villanueva Pipaón, Juan José (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
This paper wants to be a presentation of the e-journal Electronic Letters on Computer Vision and Image Analysis (ELCVIA). ELCVIA is a new electronic journal whose aim is to provide a forum where Computer Vision and Image Analysis researchers can discuss about methods, applications and experiences in this field. [...]
2002 - 10.5565/rev/elcvia.201
ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 0 n. 0 (2002) p. 1-7  
Registre complet - Creative Commons

Documents de recerca 3 registres trobats  
1.
9 p, 2.4 MB HIST4XAC : una eina d'anàlisi de documents pel manteniment del patrimoni històric / Molina Rodríguez, Adrià ; Ramos Terrades, Oriol, dir. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Universitat Autònoma de Barcelona. Escola d'Enginyeria
Heritage Intelligent Support Tool for Xarxa d'Arxius Comarcals (HIST4XAC) és una eina web per visualització explorativa, "data profiler", que intenta proveïr una col·lecció de serveis i utilitats basades en aprenentatge profund i visió per computador a arxivers i científics de l'àmbit social. [...]
La Herramienta de soporte inteligente para la Red de Archivos Comarcales (HIST4XAC) es una herramienta web de visualización y exploración "data profiler" que intenta proporcionar un conjunto de servicios y utilidades basadas en el aprendizaje profundo y la visión por ordenador a los archiveros y científicos del ámbito social. [...]
The Heritage Intelligent Support Tool for the Comarcal Archives Network (HIST4XAC) is a web visualization tool, data profiler, that aims to provide a collection of services and utilities based on deep learning and computer vision to archivists and social scientists. [...]
2022
Enginyeria de Dades [1394]  
Registre complet - Creative Commons
2.
150 p, 5.7 MB Robust Handwritten Text Recognition in Scarce Labeling Scenarios : Disentanglement, Adaptation and Generation / Kang, Lei ; Fornes Bisquerra, Alicia, dir. ; Rossinyol, Marçal, dir. ; Villegas Santamaría, Mauricio, dir. ; Lladós, Josep, dir.
Els documents escrits a mà no només es conserven en arxius històrics, sinó que també s'utilitzen àmpliament en documents administratius, com ara xecs o formularis. Amb l'auge de de l'anomenat aprenentatge profund (Deep Learning), s'ha aconseguit un bon rendiment en conjunts de dades específics per al reconeixement de text manuscrit. [...]
Los documentos manuscritos no solo se conservan en archivos históricos, sino que también se usan ampliamente en documentos administrativos como cheques y reclamaciones. Con el auge de las redes neuronales profundas, muchas técnicas del estado del arte han obtenido un buen rendimiento en conjuntos de datos específicos para el reconocimiento de texto manuscrito (HTR). [...]
Handwritten documents are not only preserved in historical archives but also widely used in administrative documents such as cheques and claims. With the rise of the deep learning era, many state-of-the-art approaches have achieved good performance on specific datasets for Handwritten Text Recognition (HTR). [...]
2020  
Registre complet - Creative Commons
3.
143 p, 11.7 MB Visual Saliency for Object Recognition, and Object Recognition for Visual Saliency / Figueroa Flores, Carola ; Weijer, Joost van de, dir. ; Raducanu, Bogdan, dir.
Per als humans, el reconeixement d'objectes és un procés gairebé instantani, precís i extremadament adaptable. A més, tenim la capacitat innata d'aprendre classes d'objectes nous a partir d'uns pocs exemples. [...]
El reconocimiento de objetos para los seres humanos es un proceso instantáneo, preciso y extremadamente adaptable. Además, tenemos la capacidad innata de aprender nuevas categorias de objetos a partir de unos pocos ejemplos. [...]
For humans, the recognition of objects is an almost instantaneous, precise and extremely adaptable process. Furthermore, we have the innate capability to learn new object classes from only few examples. [...]
2021  
Registre complet - Creative Commons

Us interessa rebre alertes sobre nous resultats d'aquesta cerca?
Definiu una alerta personal via correu electrònic o subscribiu-vos al canal RSS.
Dipòsit Digital de Documents de la UAB :: Cerca :: Lliura :: Personalitza :: Ajuda
Powered by Invenio v1.1.6
Mantingut per ddd.bib@uab.cat  :: Metadades subjectes a:
Col·laborem