相容粗糙集在音频检索中的应用  

Application of compatible rough sets in audio indexing

作　　者：李晓丽[1] 杜振龙[1] 王彤[1] 

机构地区：[1]兰州理工大学计算机与通信学院,甘肃兰州730050

出　　处：《兰州理工大学学报》2006年第4期96-98,共3页Journal of Lanzhou University of Technology

摘　　要：针对数字技术的发展促使个人的多媒体数据资料量越来越大,给人们的使用造成很大的不便,人们迫切需要能对这些资料进行检索和管理的工具,提出了利用相容粗糙集理论对音频数据进行预检索的新方法,即在相容类的近似空间中对音频数据进行预检索.实验结果表明,该方法可以有效地克服等价粗糙集在音频检索方面的限制,对提高检索效率具有一定的作用.With the development of digital technology, the volume of personal multimedia archives are made ever-increasing, which brings much inconvenience to the users, so that it is urgent for the user to efficiently index and retrieve the multimedia. A novel method for audio data pre-indexing was presented with the help of compatible rough set, where the audio data were pre-indexed in a compatible-type approximate space. Experimental evaluation showed that the proposed approach could effectively overcome the limita- tion of equivalent rough set in respect of audio indexing and improve the efficiency of audio indexing to a certain extent.

关 键 词：音频检索 相容粗糙集 粗匹配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]