A Survey of Content-Based Video Retrieval

Abstract

This study surveys current trends/methods in video retrieval. The major themes covered by the study include shot segmentation, key frame extraction, feature extraction, clustering, indexing and video retrieval-by similarity, probabilistic, transformational, refinement and relevance feedback. This work has done in an aim to assist the upcoming researchers in the field of video retrieval, to know about the techniques and methods available for video retrieval

Search in WikiImages using mobile phone

“…Since visual, auditory media and the adherent information requires large amounts of memory and computing power for storage and processing, there is a need to efficiently index, store, and retrieve the visual information from multimedia/cross-media databases [1]. Experiments based on the above system are limited by several real life scenarios:…”

Video Retrieval using Histogram and Sift Combined with Graph-based Image Segmentation

“…In most case, it is used to create a useful indexing scheme for video retrieval by grouping similar shots. There are mainly two types of clustering: partition clustering where similar data is arranged into separate clusters (example: shot clustering techniques of (Cao et al, 2003) K-means, ISODATA,) and hierarchical clustering which generates a hierarchical classification tree and considers groups as nodes of the tree (Geetha and Narayanan, 2008) That means hierarchical clustering methods tell us relationship (in tree structure) of different groups at different levels. Therefore, in our scheme, we choose a hierarchical clustering method for clustering process.…”

“…Even if there are some approaches do not use histogram, histogram difference is still the most widely used method (Geetha and Narayanan, 2008) Many shot detection techniques use it as a feature, such as a feature optimal choice method based on rough-fuzzy set of (Han et al, 2005) hidden Markov model method of (Boreczky and Lynn, 1998) sliding window method of (Li and Lee, 2005) and some other directly bases on histogram, such as the method of (O'Toole et al, 1999) and our method, which is presented.…”

“…Although this approach does not use the spatialtemporal relationship among video frames effectively, this extension also gains some success (Geetha and Narayanan, 2008) in our model, SIFT feature is chosen due to its ability of being almost unchanging under variations of recording frames (light intensity, rate and geometric transformations). Moreover, SIFT detection algorithm runs fast and SIFT matching algorithm has high precision and recall.…”

“…Although being a young field, there are many different approaches in CBVR proposed, such asousing visual information methods, retrieval based on textual information presented in the video, relevance feedback algorithms (Geetha and Narayanan, 2008) A framework of these methods often includes breaking videos into shots, keyframes and retrieve suitable keyframes for input data based on some chosen features extracted from these shots or key frames (Flickner et al, 1995) There are many different approaches which focus on various properties of frames and videos (such as visual effects, motion, sound,) used to solve each sub-problem.…”