Near-duplicate keyframe identification with interest point matching and pattern learning

This paper proposes a new approach for near-duplicate keyframe (NDK) identification by matching, filtering and learning of local interest points (LIPs) with PCA-SIFT descriptors. The issues in matching reliability, filtering efficiency and learning flexibility are novelly exploited to delve into the...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHAO, Wan-Lei, NGO, Chong-wah, TAN, Hung-Khoon, WU, Xiao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2007
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6334
https://ink.library.smu.edu.sg/context/sis_research/article/7337/viewcontent/Near_Duplicate_Keyframe_Identification_W.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7337
record_format dspace
spelling sg-smu-ink.sis_research-73372021-11-23T04:33:03Z Near-duplicate keyframe identification with interest point matching and pattern learning ZHAO, Wan-Lei NGO, Chong-wah TAN, Hung-Khoon WU, Xiao This paper proposes a new approach for near-duplicate keyframe (NDK) identification by matching, filtering and learning of local interest points (LIPs) with PCA-SIFT descriptors. The issues in matching reliability, filtering efficiency and learning flexibility are novelly exploited to delve into the potential of LIP-based retrieval and detection. In matching, we propose a one-to-one symmetric matching (OOS) algorithm which is found to be highly reliable for NDK identification, due to its capability in excluding false LIP matches compared with other matching strategies. For rapid filtering, we address two issues: speed efficiency and search effectiveness, to support OOS with a new index structure called LIP-IS. By exploring the properties of PCA-SIFT, the filtering capability and speed of LIP-IS are asymptotically estimated and compared to locality sensitive hashing (LSH). Owing to the robustness consideration, the matching of LIPs across keyframes forms vivid patterns that are utilized for discriminative learning and detection with support vector machines. Experimental results on TRECVID-2003 corpus show that our proposed approach outperforms other popular methods including the techniques with LSH in terms of retrieval and detection effectiveness. In addition, the proposed LIP-IS successfully speeds up OOS for more than ten times and possesses several avorable properties compared to LSH. 2007-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6334 info:doi/10.1109/TMM.2007.898928 https://ink.library.smu.edu.sg/context/sis_research/article/7337/viewcontent/Near_Duplicate_Keyframe_Identification_W.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University local interest point matching near-duplicate detection nearest neighbor search Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic local interest point matching
near-duplicate detection
nearest neighbor search
Graphics and Human Computer Interfaces
spellingShingle local interest point matching
near-duplicate detection
nearest neighbor search
Graphics and Human Computer Interfaces
ZHAO, Wan-Lei
NGO, Chong-wah
TAN, Hung-Khoon
WU, Xiao
Near-duplicate keyframe identification with interest point matching and pattern learning
description This paper proposes a new approach for near-duplicate keyframe (NDK) identification by matching, filtering and learning of local interest points (LIPs) with PCA-SIFT descriptors. The issues in matching reliability, filtering efficiency and learning flexibility are novelly exploited to delve into the potential of LIP-based retrieval and detection. In matching, we propose a one-to-one symmetric matching (OOS) algorithm which is found to be highly reliable for NDK identification, due to its capability in excluding false LIP matches compared with other matching strategies. For rapid filtering, we address two issues: speed efficiency and search effectiveness, to support OOS with a new index structure called LIP-IS. By exploring the properties of PCA-SIFT, the filtering capability and speed of LIP-IS are asymptotically estimated and compared to locality sensitive hashing (LSH). Owing to the robustness consideration, the matching of LIPs across keyframes forms vivid patterns that are utilized for discriminative learning and detection with support vector machines. Experimental results on TRECVID-2003 corpus show that our proposed approach outperforms other popular methods including the techniques with LSH in terms of retrieval and detection effectiveness. In addition, the proposed LIP-IS successfully speeds up OOS for more than ten times and possesses several avorable properties compared to LSH.
format text
author ZHAO, Wan-Lei
NGO, Chong-wah
TAN, Hung-Khoon
WU, Xiao
author_facet ZHAO, Wan-Lei
NGO, Chong-wah
TAN, Hung-Khoon
WU, Xiao
author_sort ZHAO, Wan-Lei
title Near-duplicate keyframe identification with interest point matching and pattern learning
title_short Near-duplicate keyframe identification with interest point matching and pattern learning
title_full Near-duplicate keyframe identification with interest point matching and pattern learning
title_fullStr Near-duplicate keyframe identification with interest point matching and pattern learning
title_full_unstemmed Near-duplicate keyframe identification with interest point matching and pattern learning
title_sort near-duplicate keyframe identification with interest point matching and pattern learning
publisher Institutional Knowledge at Singapore Management University
publishDate 2007
url https://ink.library.smu.edu.sg/sis_research/6334
https://ink.library.smu.edu.sg/context/sis_research/article/7337/viewcontent/Near_Duplicate_Keyframe_Identification_W.pdf
_version_ 1770575936532512768