TY - JOUR
T1 - Video scene change detection using neural network
T2 - Improved ART2
AU - Lee, Man Hee
AU - Yoo, Hun Woo
AU - Jang, Dong Sik
N1 - Funding Information:
This work was supported by Korea Research Foundation Grant (KRF-2004-005-H00005).
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 2006/7
Y1 - 2006/7
N2 - A common video indexing technique is to segment a video sequence into shots and then select representative key-frames. This paper proposes a new method using an improved ART2 neural network for scene change detection. The proposed algorithm extracts DC-sequence from a video and then makes a gray variance sequence for detecting smooth intervals. During that procedure, a local minimum sequence occurring at typical gradual changes is extracted and eliminated from the smooth intervals by our local minimum detection algorithm. Then, a new sequence is constructed by concatenating obtained smooth intervals. Feature elements such as pixel-wise difference, histogram difference, and correlation coefficients are extracted from the new sequence. These three elements, plus one extra element reducing the distortion of the ART2 neural network, are presented as an input vector to the ART2 neural network that has two output units in the F2 layer. Frames at the ends of each smooth interval are assigned to the second cluster that represents key-frames. Experimental results showed that the proposed algorithm using the extra element was better than the method without it in terms of precision and recall rates. Also, it produced better results than Patel's method (Patel and Sethi, 1996) and the twin comparison method (Zhang et al., 1993).
AB - A common video indexing technique is to segment a video sequence into shots and then select representative key-frames. This paper proposes a new method using an improved ART2 neural network for scene change detection. The proposed algorithm extracts DC-sequence from a video and then makes a gray variance sequence for detecting smooth intervals. During that procedure, a local minimum sequence occurring at typical gradual changes is extracted and eliminated from the smooth intervals by our local minimum detection algorithm. Then, a new sequence is constructed by concatenating obtained smooth intervals. Feature elements such as pixel-wise difference, histogram difference, and correlation coefficients are extracted from the new sequence. These three elements, plus one extra element reducing the distortion of the ART2 neural network, are presented as an input vector to the ART2 neural network that has two output units in the F2 layer. Frames at the ends of each smooth interval are assigned to the second cluster that represents key-frames. Experimental results showed that the proposed algorithm using the extra element was better than the method without it in terms of precision and recall rates. Also, it produced better results than Patel's method (Patel and Sethi, 1996) and the twin comparison method (Zhang et al., 1993).
KW - Local minimum sequence
KW - Neural network, ART2
KW - Scene change detection
KW - Smooth intervals
KW - Variance
UR - http://www.scopus.com/inward/record.url?scp=33644756673&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33644756673&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2005.09.031
DO - 10.1016/j.eswa.2005.09.031
M3 - Article
AN - SCOPUS:33644756673
SN - 0957-4174
VL - 31
SP - 13
EP - 25
JO - Expert Systems With Applications
JF - Expert Systems With Applications
IS - 1
ER -