東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Methods for faster feature matching ...

Treen, Geoffrey.

FindBook

Google Book

Amazon

博客來

Methods for faster feature matching using the scale-invariant feature transform.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Methods for faster feature matching using the scale-invariant feature transform./
作者:	Treen, Geoffrey.
面頁冊數:	76 p.
附註:	Source: Masters Abstracts International, Volume: 48-06, page: 3728.
Contained By:	Masters Abstracts International48-06.
標題:	Engineering, Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR63824
ISBN:	9780494638248

Methods for faster feature matching using the scale-invariant feature transform.
Treen, Geoffrey.

Methods for faster feature matching using the scale-invariant feature transform. - 76 p.

Source: Masters Abstracts International, Volume: 48-06, page: 3728.

Thesis (M.A.Sc.)--Carleton University (Canada), 2010.

A set of modular algorithms for efficiently finding SIFT correspondences in images or image archives is presented. The basic algorithm, called SIFT-HHM, exploits properties of the SIFT descriptor vector to find shortcuts to the most likely matches in two feature sets. SIFT-HHM converges approximately 15 times faster than a linear search, and, respectively, four and five times faster than PCA-SIFT and SURF at near-equivalent precision-recall performance.

ISBN: 9780494638248Subjects--Topical Terms:

1018454
Engineering, Robotics.

Methods for faster feature matching using the scale-invariant feature transform.
LDR:01851nam 2200277 4500 001 1401691
005 20111017084431.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9780494638248
035 $a (UMI)AAIMR63824
035 $a AAIMR63824
040 $a UMI $c UMI
100 1 $a Treen, Geoffrey. $3 1680842
245 1 0 $a Methods for faster feature matching using the scale-invariant feature transform.
300 $a 76 p.
500 $a Source: Masters Abstracts International, Volume: 48-06, page: 3728.
502 $a Thesis (M.A.Sc.)--Carleton University (Canada), 2010.
520 $a A set of modular algorithms for efficiently finding SIFT correspondences in images or image archives is presented. The basic algorithm, called SIFT-HHM, exploits properties of the SIFT descriptor vector to find shortcuts to the most likely matches in two feature sets. SIFT-HHM converges approximately 15 times faster than a linear search, and, respectively, four and five times faster than PCA-SIFT and SURF at near-equivalent precision-recall performance.
520 $a A PCA-based binning algorithm that can be combined with SIFT-HHM is presented to address the content-based image retrieval problem. Our experiments show this combined approach to be preferable over current tree-based methods for a number of reasons. Most significantly, it will converge approximately three times faster than the current state ofthe art. Secondly, database build times are less than 10% of those for constructing a k-means tree. Finally, we note simplicity of storage, scalability, and suitability to distributed processing as incidental benefits.
590 $a School code: 0040.
650 4 $a Engineering, Robotics. $3 1018454
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0771
690 $a 0800
690 $a 0984
710 2 $a Carleton University (Canada). $3 1018407
773 0 $t Masters Abstracts International $g 48-06.
790 $a 0040
791 $a M.A.Sc.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR63824