资 源 简 介
本文完成了对唇动身份识别技术几个基本问题的理论研究,并对整个系统加以实现.作为本文研究的实验基础,我们建立了唇动方式身份识别数据库(HITLUDB),
该库目前包含30个说话人每人20个汉语词的音视频语料.数据库的扩充与完善工作仍在不断的进行之中.在嘴唇检测方面,
我们对自适应色度过滤模型进行改进,提高了算法的鲁棒性,完成了对嘴唇的精确定位.结合DCT变换与K-L变换的各自特点,
我们提出了特征提取算法,使用较少维数的特征完成了对嘴唇区域主要信息的刻画.由于唇动信息同时包含了生理特征与行为特征,
我们使用静念动念混合建模的方式,完成了对说话人唇动个性特点的精确描述.在HMM训练时,我们提出了特征的归一化处理方法,提高了HMM在实际应用中的性能.
最后,我们分别对身份辨认系统与身份确认系统的基本理论进行了叙述,并完成了系统的实践工作.
关 键 词：身份识别 唇动 特征提取 隐马尔可夫模型 K-L变换 -paper completed the lip movements identification technology several basic issues of theoretical study, system as a whole be achieved. As this paper, the experimental basis, We have established a dynamic manner lip identification database (HITLUDB) The library currently contains 30 words each of 20 Chinese words, sound and video corpus. and the expansion of the database is still perfect keep going on. Detection of the lips, we adaptive color filter model improvements, improve the robustness of the algorithm, completed a pair of lips the precise positioning. DCT combined with
文 件 列 表
基于VQ与GMM的说话人识别
ml.htm
y7906150001.pdf
y7906150002.pdf
y7906150004.pdf
y7906150005.pdf
y7906150006.pdf
y7906150007.pdf
y7906150008.pdf
y7906150009.pdf
y7906150010.pdf
y7906150011.pdf
y7906150014.pdf
y7906150015.pdf
y7906150016.pdf
y7906150018.pdf
y7906150019.pdf
y7906150020.pdf
y7906150021.pdf
y7906150022.pdf
y7906150023.pdf
y7906150024.pdf
y7906150025.pdf
y7906150026.pdf
y7906150027.pdf
y7906150028.pdf
y7906150029.pdf
y7906150030.pdf
y7906150031.pdf
y7906150032.pdf
y7906150034.pdf
y7906150035.pdf
y7906150036.pdf
y7906150037.pdf
y7906150038.pdf
y7906150039.pdf
y7906150040.pdf
y7906150041.pdf
y7906150042.pdf
y7906150043.pdf
y7906150044.pdf
y7906150046.pdf
y7906150047.pdf
y7906150048.pdf
y7906150050.pdf
y7906150051.pdf
y7906150052.pdf
y7906150053.pdf
y7906150054.pdf
y7906150056.pdf
y7906150057.pdf
y7906150058.pdf
y7906150059.pdf
y7906150060.pdf
y7906150061.pdf
y7906150062.pdf
y7906150063.pdf
y7906150067.pdf
y7906150068.pdf
y7906150070.pdf
y7906150071.pdf
y7906150072.pdf
y7906150073.pdf
y7906150074.pdf
y790615wz.pdf
y790615zye.pdf
