Large scale visual search

Leiden Repository

Large scale visual search

Type: Doctoral Thesis
Title: Large scale visual search
Author: Wu, S.
Issue Date: 2016-12-22
Keywords: Salient point method
Convolutional neural network
Large scale visual search
Abstract: With the ever-growing amount of image data on the web, much attention has been devoted to large scale image search. It is one of the most challenging problems in computer vision for several reasons. First, it must address various appearance transformations such as changes in perspective, rotation and scale existing in the huge amount of image data. Second, it needs to minimize memory requirements and computational cost when generating image representations. Finally, it needs to construct an efficient index space and a suitable similarity measure to reduce the response time to the users. This thesis aims to provide robust image representations that are less sensitive to above mentioned appearance transformations and are suitable for large scale image retrieval. Although this thesis makes a substantial number of contributions to large scale image retrieval, we also presented additional challenges and future research based on the contributions in this thesis.
Promotor: Supervisor: J.N. Kok Co-Supervisor: M.S. Lew
Faculty: Faculty of Science
University: Leiden
Uri: urn:isbn:9789463321174

Files in this item

Description Size View
application/pdf Full text 1.334Mb View/Open
application/pdf Cover 2.183Mb View/Open
application/pdf Title page_Contents 254.7Kb View/Open
application/pdf Chapter 1 237.0Kb View/Open
application/pdf Chapter 2 8.914Mb View/Open Full text at publisher site
application/pdf Chapter 3 3.306Mb View/Open Full text at publisher site
application/pdf Chapter 4 944.1Kb View/Open
application/pdf Chapter 5 536.8Kb View/Open
application/pdf Chapter 6 163.3Kb View/Open
application/pdf Bibliography 183.2Kb View/Open
application/pdf Summary 145.9Kb View/Open
application/pdf Summary_Dutch 146.3Kb View/Open
application/pdf Acknowledgements_CV 146.2Kb View/Open

This item appears in the following Collection(s)