Proceedings ArticleDOI
Automatic video classification using decision tree method
Ye Yuan,Qinbao Song,Jun-Yi Shen +2 more
- Vol. 3, pp 1153-1157
TLDR
The experimental results show that the decision tree method is promising for video genre recognition.Abstract:
Automatic digital video classification is emerging as an important problem in the fields of video analysis and multimedia database. In this paper the decision tree method is used for automatic video classification. Video clips are first segmented into shots, then features of the video clips are generated, and a video features database is created at the same time. After that, the decision tree method is used to classify the videos as different genres and a set of decision rules are produced. The discovered decision rules are used to predicate the genre of a new video. The experimental results show that the decision tree method is promising for video genre recognition.read more
Citations
More filters
Proceedings ArticleDOI
Automatic Video Genre Categorization using Hierarchical SVM
TL;DR: Experimental results show that the proposed scheme outperforms C4.5 decision tree, typical 1-vs-1 SVM scheme, as well as the hierarchical SVM built by K-means.
Journal ArticleDOI
Object-based analysis and interpretation of human motion in sports video sequences by dynamic Bayesian networks
TL;DR: In the proposed scheme, video objects are first segmented, followed by a video object abstraction algorithm for identifying key frames to reduce data redundancy and provide reliable feature data for next stage of the algorithm.
Journal ArticleDOI
Parallel neural networks for multimodal video genre classification
TL;DR: This article proposes in this article a methodology for classifying the genre of television programmes, which reaches a classification accuracy rate of 95% and is used for training a parallel neural network system able to distinguish between seven video genres.
Journal ArticleDOI
Classification of sport videos using edge-based features and autoassociative neural network models
TL;DR: It is shown that combining evidence from complementary edge features results in improved classification performance, and combination of evidence from different classifiers like AANN, hidden Markov model (HMM) and support vector machine (SVM) helps improve the classification performance.
Proceedings ArticleDOI
Implementation of high performance objectionable video classification system
TL;DR: This work proposes and implements the obscene video classification system using two visual features to determine a video's lewdness with very excellent performance, enabling automatic filtering of obscene videos.
References
More filters
Book
C4.5: Programs for Machine Learning
TL;DR: A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Journal ArticleDOI
Induction of Decision Trees
TL;DR: In this paper, an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, is described, and a reported shortcoming of the basic algorithm is discussed.
Journal ArticleDOI
Automatic partitioning of full-motion video
TL;DR: A twin-comparison approach has been developed to solve the problem of detecting transitions implemented by special effects, and a motion analysis algorithm is applied to determine whether an actual transition has occurred.
Induction of Decision Trees
TL;DR: In this paper, an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, is described, and a reported shortcoming of the basic algorithm is discussed.
Proceedings ArticleDOI
Comparison of automatic shot boundary detection algorithms
TL;DR: Comparative investigations on early shot boundary detection algorithms designed explicitly to detect specific complex editing operations, such as fades and dissolves, are taken into account and show that while hard cuts and fades can be detected reliably, dissolves are still an open research issue.