Abstract
This paper presents a novel approach for video retrieval from a large archive of MPEG or Motion JPEG' compressed video clips. We introduce a retrieval algorithm that takes a video clip as a query and searches the database for clips with similar contents. Video clips are characterized by a sequence of representative frame signatures, which are constructed from DC coefficients and motion information ("DC+M" signatures). The similarity between two video clips is determined by using their respective signatures. This method facilitates retrieval of clips for the purpose of video editing, broadcast news retrieval, or copyright violation detection.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 59-70 |
| Number of pages | 12 |
| Journal | Proceedings of SPIE - The International Society for Optical Engineering |
| Volume | 3022 |
| DOIs | |
| State | Published - Jan 15 1997 |
| Event | Storage and Retrieval for Image and Video Databases V 1997 - San Jose, United States Duration: Feb 8 1997 → Feb 14 1997 |
Fingerprint
Keywords
- Compressed domain video processing
- Content-based retrieval
- Video representation
- Video retrieval
- Video signature extraction
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Cite this
Content-based video retrieval by example video clip. / Dimitrova, Nevenka; Abdel-Mottaleb, Mohamed.
In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 3022, 15.01.1997, p. 59-70.Research output: Contribution to journal › Conference article
}
TY - JOUR
T1 - Content-based video retrieval by example video clip
AU - Dimitrova, Nevenka
AU - Abdel-Mottaleb, Mohamed
PY - 1997/1/15
Y1 - 1997/1/15
N2 - This paper presents a novel approach for video retrieval from a large archive of MPEG or Motion JPEG' compressed video clips. We introduce a retrieval algorithm that takes a video clip as a query and searches the database for clips with similar contents. Video clips are characterized by a sequence of representative frame signatures, which are constructed from DC coefficients and motion information ("DC+M" signatures). The similarity between two video clips is determined by using their respective signatures. This method facilitates retrieval of clips for the purpose of video editing, broadcast news retrieval, or copyright violation detection.
AB - This paper presents a novel approach for video retrieval from a large archive of MPEG or Motion JPEG' compressed video clips. We introduce a retrieval algorithm that takes a video clip as a query and searches the database for clips with similar contents. Video clips are characterized by a sequence of representative frame signatures, which are constructed from DC coefficients and motion information ("DC+M" signatures). The similarity between two video clips is determined by using their respective signatures. This method facilitates retrieval of clips for the purpose of video editing, broadcast news retrieval, or copyright violation detection.
KW - Compressed domain video processing
KW - Content-based retrieval
KW - Video representation
KW - Video retrieval
KW - Video signature extraction
UR - http://www.scopus.com/inward/record.url?scp=85076109632&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076109632&partnerID=8YFLogxK
U2 - 10.1117/12.263444
DO - 10.1117/12.263444
M3 - Conference article
AN - SCOPUS:85076109632
VL - 3022
SP - 59
EP - 70
JO - Proceedings of SPIE - The International Society for Optical Engineering
JF - Proceedings of SPIE - The International Society for Optical Engineering
SN - 0277-786X
ER -