Image search with LSH and shape context
No Thumbnail Available
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Partial-duplicate image search is a problem of searching the query image cropped from the same original image from a large database. Kd-tree have a good performance to address this problem when data dimension is low, but not good enough for high dimension. In our paper, we present locality sensitive hashing for image search, it is a randomized algorithms, which does not guarantee an exact answer but instead provides a high probability guarantee that it will return the correct answer or one close to it. With locality sensitive hashing we create 10 good hash table to save computation time and increased accuracy. We also generate bounding box to localize the query in dataset image. By using mean distance we make matched pair image scale invariant. We also captures the distribution of the remaining points relative to reference point to reduce the noise points. Finally, we magnify the bounding box relative to query with only 2 points.
Table of Contents
DOI
PubMed ID
Degree
M.S.
Thesis Department
Rights
Access to files is limited to the University of Missouri--Columbia.