ASIA unversity:Item 310904400/112503
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 90120/105263 (86%)
造访人次 : 7260074      在线人数 : 225
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    ASIA unversity > 資訊學院 > 資訊傳播學系 > 期刊論文 >  Item 310904400/112503


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://asiair.asia.edu.tw/ir/handle/310904400/112503


    题名: Film classification using HSV distribution and deep learning neural networks
    作者: 陸清達;Lu, Ching-Ta;沈俊宏;SHEN, JUN-HONG;王玲玲;Wang, Ling-Ling;劉佳樺;Liu, Chia-Hua;張嘉奕;Chang, Chia-Yi;曾崑福;Tseng, Kun-Fu
    贡献者: 資訊傳播學系
    日期: 2019-05
    上传时间: 2019-11-15 10:28:06 (UTC+8)
    摘要: The number of films is numerous and complex. A viewer wants to choose a favorite movie is time consuming. This study aims to develop an automatic film classification system. Firstly, a film is sampled frame by frame. The color space in terms of hue, saturation, and brightness value (HSV) in each frame is analyzed. Hence the mean and deviation of the HSV are computed and utilized as classification features for each film. These features are fed into deep learning neural networks. Twenty-five trailers are employed to train the model parameters of neural networks. In the classification phase, twenty-five trailers are classified into five categories, including science fiction, literature-love, action, comedy films, and horror and thrillers. Experimental results show that the proposed method can effectively classify the film types, where the precision rate can reach 93.3%.

    Keywords
    Film classification Video recognition HSV analysis Neural networks Deep learning
    關聯: Lecture Notes in Electrical Engineering
    显示于类别:[資訊傳播學系] 期刊論文

    文件中的档案:

    没有与此文件相关的档案.



    在ASIAIR中所有的数据项都受到原著作权保护.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈