A Feature Selection Technique for Semantic Video Indexing System
Date Issued
2008
Date
2008
Author(s)
Chen, Chun-Kang
Abstract
For processing the growing and easily accessing videos, users desire an automatic video search system by semantic queries, such as objects, scenes, and events from daily life. To this end TRECVID supplies sufficient video data and a fair evaluation method, annually, to progress video search techniques. Many participants build their classification through fusing results from modeling low level features (LLFs), such as color, edge, and so on. With the development of computer vision, more and more useful LLFs are designed. However, modeling all acquirable LLFs requires tremendous amount of time. Hence, how to use these LLFs efficiently has become an important issue. In this thesis, we propose an evaluation technique for LLFs, then the most appropriate concept-dependent LLF combinations can be chosen to reduce the modeling time while still keep reasonable video search precisions. In our experiments, only modeling 5 chosen LLFs out of total 16 LLFs can reduce 3.51\% modeling time with only 6.78\% performance drop. However, if a half number of LLFs are used, we can even keep 98.88\% precision with 36.07\% time saving.
Subjects
feature selection
video search
semantic concept
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-97-R95922161-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):c23d11e4d0832d42aa7047521881638d