Graduate Thesis Or Dissertation
 

Fine-grained detection and localization of objects in images

Público Deposited

Contenido Descargable

Descargar PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/dv13zw987

Descriptions

Attribute NameValues
Creator
Abstract
  • Object recognition is a fundamental problem in computer vision. Recognition is required by many applications. This thesis presents a distance based approach to recognize objects. We are interested in objects that belong to very similar classes, where each class has large variations. This problem is called fine-grained object recognition. Given a set of training images our approach identifies a sparse number of image patches in the training set which cover the most parts of the target object in the test image. We use Hungarian algorithm to match the image patches, based on a linear combination of appearance and geometric image features. We also specify a voting scheme for each possible location of the target object in the test image. The location which is close to the training image center is more likely to be the object center in the test image. Our results on a set of the challenging benchmark datasets are promising. This suggests that our approach is suitable to effectively address fine-grained object recognition.
License
Resource Type
Fecha Disponible
Fecha de Emisión
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Subject
Declaración de derechos
Publisher
Peer Reviewed
Language
Replaces

Relaciones

Parents:

This work has no parents.

En Collection:

Elementos

Miniatura Título Fecha de subida Visibilidad Acciones
file details YaofeiFeng2013.pdf 2017-08-09 Público Descargar