A longest common subsequence approach to detect cut and wipe video transitions

We address in this work the problem of video transition detection, which is an important task in the video indexing and retrieval domain. The video slice is a single two-dimensional image that represents a video preserving information allowing the detection of different visual events in the original video. In particular it is possible to characterize shot transitions. We use the longest common subsequence (LCS) between two strings to transform the video slice into one-dimensional signals obtaining a highly simplified representation of the video content. Further we developed a chain of operations over these signals leading to the detection of cut and wipe transitions.