<title>Automatic generation of pictorial transcripts of video programs</title>

An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis

“…Automated extraction of key frames has been addressed by many researchers [1], [2], [4], [6]- [9], [13], [16], [17], [19]- [26]. A first attempt to automate the key-frame extraction was to choose as a key frame the frame appearing after each detected shot boundary [16].…”

“…A first attempt to automate the key-frame extraction was to choose as a key frame the frame appearing after each detected shot boundary [16]. However, while being sufficient for stationary shots, one key frame does not provide an acceptable representation of the visual content in dynamic sequences.…”

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

“…The simplest method is to select the first/middle/last frame of each shot as key frames. Shahraray and Gibbon [14] propose a content-based sampling method to select key frames. Panagiotakis et al [15] first choose the first and last frames of each shot as key frames and then compute the remaining key frames with the maximum equidistant in the sense of the Iso-Content.…”

A Geometrical Key-Frame Selection Method Exploiting Dominant Motion Estimation in Video

“…When considering fast video content visualization, the selection of one frame per shot, typically the median frame, could be sufficient to avoid visual content redundancies ( [1], [2]). On the other hand, key-frames can also be used in the content-based video indexing stage to extract spatial descriptors to be attached to the shot and related to intensity, color, texture or shape, which enables to process a very small set of images while analyzing the whole shot content.…”