Similarity Analysis of Video Sequences Using an Artificial Neural Network

Abstract

Comparison of video sequences is an important operation in many multimedia information systems. The similarity measure for comparison is typically based on some measure of correlation with the perceptual similarity (or difference) amongst the video sequences or with the similarity (or difference) in some measure of semantics associated with the video sequences. In content-based similarity analysis, the video data are expressed in terms of different features. Similarity matching is then performed by quantifying the feature relationships between the target video and query video shots, with either an individual feature or with a feature combination. In this study, two approaches are proposed for the similarity analysis of video shots. In the first approach, mosaic images are created from video shots, and the similarity analysis is done by determining the similarities amongst the mosaic images. In the second approach, key frames are extracted for each video shot and the similarity amongst video shots is determined by comparing the key frames of the video shots. The features extracted include image histograms, slopes, edges, and wavelets. Both individual features and feature combinations are used in similarity matching using an artificial neural network. The similarity rank of the query video shots is determined based on the values of the coefficients of determination and the mean absolute error. The study reported in this paper shows that the mosaicbased similarity analysis can be expected to yield a more reliable result, whereas the key frame-based similarity analysis could be potentially applied to a wider range of applications. The weighted non-linear feature combination is shown to yield better results than a single feature for video similarity analysis. The coefficient of determination is shown to be a better criterion than the mean absolute error in similarity matching analysis.

C-Rank: A link-based similarity measure for scientific literature databases

“…Various similarity measures and their applications have been proposed in the past [3,4,10,13,20,21,26,38,46,48]. Text-based similarity measures count the number of keywords in common between two papers.…”

Research and Application of a Combined Art Image Query Method

“…So far, there are two aspects of image retrieval in the image search process. One is the correlation between the retrieval results and target image [20][21], and the other one is the diversity of the results compared to the target image [22][23]. The correlation of the retrieval results is whether the images shown in front of the results list are related to the user's retrieval intention.…”

Improving estimate at completion (EAC) cost of construction projects using adaptive neuro-fuzzy inference system (ANFIS)

“…proposed an ANN model to solve two models for portfolio selection with uncertain variables Sheikhi and Babamir (2017). presented a predictive framework using a recurrent ANN Bhandarkar et al (2005). used ANN for the analysis of video sequences Cavalieri et al (2004).…”