Earticle

초록

영어

The performance of video automatic classification algorithm depends largely on the extraction of video features and selection of classification algorithm. From the perspective of video contents and video style type, the paper presents a new feature representation scheme, i.e. MPEG-7 visual description sub-combination model, a new method based on support vector machine (SVM) to solve problems with existing algorithms, by analyzing visual differences between five types of videos. Also we improve the classifier decision scheme and then propose the secondary prediction mechanism based on SVM 1-1 approach, improving the accuracy of SVM multi-classification method. The experimental results indicate that the proposed method manifests differences of different videos about feature selection, enhances the discrimination ability of videos pending for classification and increases the effectiveness of SVM multi-video classification.

목차

Abstract
 1. Introduction
 2. SVM-Based Video Automatic Classification System
  2.1. Video Automatic Classification System Framework
  2.2. Process of Video Automatic Classification Algorithm
  2.3. Feature Selection and Extraction
 3. Multi-Classifier Design of Support Vector Machine
  3.1. Classification Decision Algorithm of SVM
  3.2. Secondary Prediction Mechanism Based on 1-1 Method
 4. Experiment Design and Discussion
  4.1. Experimental Environments
  4.2. Comparison of Classifying Accuracy for Single Descriptor
  4.3. Accuracy Comparison of Different Multi classification Algorithms
 5. Conclusion
 Acknowledgement 
 References

키워드

저자

• Chao Jiang [ Jilin Communications Polytechnic, Changchun 130012, china ]
• Shuguang Wang [ Jilin Communications Polytechnic, Changchun 130012, china ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605