全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于支持向量机的视频关键帧语义提取

DOI: 10.13190/jbupt.200602.123.caojr, PP. 123-126

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对如何从视频关键帧中提取语义的问题,提出了一个使用多类支持向量机(SVM)对风光纪录片的关键帧进行分类来提取语义的方法.支持向量机利用从风光纪录片的关键帧中提取的彩色直方图和MPEG(活动图像专家组)7的边缘直方图特征对关键帧图像进行分类,从而得到关键帧的语义.对具有不同核函数的支持向量机的分类进行了研究,并对分类的结果进行了对比.结果显示,具有二项式(Polynomial)和RBF(radialbasisfunction)核函数的SVM,其分类准确度比其他的SVM约高3%.

References

[1]  Olivier C, Patrick H, Vladimir N V. Support vector machines for histogram-based image classification
[2]  [J] IEEE Transactions on Neural Network, 1999, 10(5): 1055-1064.
[3]  KEE C J, Jung H H, Kwang I K, et al. Support vector machines for text location in news video images// IEEE TENCON 2000 Proceedings. Kuala Lumpur:, 2000: 176-180.
[4]  Vakkalanka S, Krishna M C, Swamy R K, et al. Content-based video classification using support vector machines//Proceedings of 11th International Conference on Neural Information Processing. Calcutta: , 2004: 726-731.
[5]  Ren Jianfeng, Shen Yuntao, Ma Songhui, et al. Applying multi-class SVMs into scene image classification//Proceedings of 17th International Conference on Indust-rial and Engineering Applications of Artificial Intelligence and Expert Systems. Ottawa: , 2004: 924-934.
[6]  Weston J, Watkins C. Multiclass support vector machines . Univ London, U K, Tech Rep CSD-TR-98-04, 1998: 1-12.
[7]  Vpanik V. The nature of statistical learning theory
[8]  [M] New York: Springer Verlag, 1995: 78-126.
[9]  Chee S W, Dong K P, Soo J P. Efficient use of MPEG-7 edge histogram descriptor
[10]  [J] ETRI Journal, 2002, 24 (1): 23-30.
[11]  Chang C C, Lin C J. LIBSVM: a library for support vector machine . .

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133