View Item 
  •   e_Buah Home
  • INVESTIGACIÓN
  • Tesis Doctorales UAH
  • Tesis Doctorales UAH
  • View Item
  • INVESTIGACIÓN
  • Tesis Doctorales UAH
  • Tesis Doctorales UAH
  • View Item
  • Biblioteca
    • English
    • español
JavaScript is disabled for your browser. Some features of this site may not work without it.

Visual vocabularies for category-level object recognition

Show full item record
RefworksUtilizar EndNote Import
Authors
López Sastre, Roberto JavierUniversity of Alcalá Author
Identifiers
Permanent link (URI): http://hdl.handle.net/10017/8716
Director
Maldonado Bascón, SaturninoUniversity of Alcalá Author
Date
2010
Affiliation
Universidad de Alcalá. Departamento de Teoría de la Señal y Comunicaciones
Keywords
Proceso de imágenes
Reconocimiento de formas
Bases de datos
Señales, Teoría de (Telecomunicación)
Document type
info:eu-repo/semantics/doctoralThesis
Version
info:eu-repo/semantics/acceptedVersion
Access rights
info:eu-repo/semantics/openAccess
Share
 
Abstract
This thesis focuses on the study of visual vocabularies for category-level object recognition. Specifically, we state novel approaches for building visual codebooks. Our aim is not just to obtain more discriminative and more compact visual codebooks, but to bridge the gap between visual features and semantic concepts. A novel approach for obtaining class representative visual words is presented. It is based on a maximisation procedure, i. e. the Cluster Precision Maximisation (CPM), of a novel cluster precision criterion, and on an adaptive threshold refinement scheme for agglomerative clustering algorithms based on correlation clustering techniques. The objective is to increase the vocabulary compactness while at the same time improve the recognition rate and further increase the representativeness of the visual words. Moreover, we describe a novel clustering aggregation based approach for building efficient and semantic visual vocabularies. It consist of a novel framework for incorporating neighboring appearances of local descriptors into the vocabulary construction, and a rigorous approach for adding meaningful spatial coherency among the local features into the visual codebooks. We also propose an efficient high-dimensional data clustering algorithm, the Fast Reciprocal Nearest Neighbours (Fast-RNN). Our approach, which is a speeded up version of the standard RNN algorithm, is based on the projection search paradigm. Finally, we release a new database of images called Image Collection of Annotated Real-world Objects (ICARO), which is especially designed for evaluating category-level object recognition systems. An exhaustive comparison of ICARO with other well-known datasets used within the same context is carried out. We also propose a benchmark for both object classification and detection.
Files in this item
FilesSizeFormat
View
thesis-camera-ready.pdf22.86MbPDF
FilesSizeFormat
View
thesis-camera-ready.pdf22.86MbPDF
Collections
  • Tesis Doctorales UAH [1742]
  • TSENCOM - Tesis [43]

Contact Us | Send Feedback | About DSpace
¡CSS Válido!@mire NV
¡CSS Válido!@mire NV
 

 

Browse

All of e_BuahCommunities y CollectionsIssue DateAuthorsTitlesSubjectsIn this CollectionIssue DateAuthorsTitlesSubjects

My Account

My e_BuahCreate account

Help

What is e-Buah?Guide e_BuahGuide autoarchiveFAQContact us

Statistics

View Usage Statistics

Information

Open Science. Open accessOpen access PolicyPublishing permissionsCopyrightResearch datae-cienciaDatos RepositoryPlan de Gestión de Datos

Los contenidos se difunden en


Contact Us | Send Feedback | About DSpace
¡CSS Válido!@mire NV
¡CSS Válido!@mire NV