Semantic feature extraction from signal and image using lifting wavelet filters.

使用提升小波滤波器从信号和图像中提取语义特征。

• 批准号: 15300048
• 负责人: NIIJIMA Koichi
• 金额: $ 10.11万
• 依托单位: KYUSHU UNIVERCITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2003
• 资助国家: 日本
• 起止时间: 2003 至 2006
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-15300048/
• 关键词: biorthogonal wavelet; dyadic wavelet; lifting scheme; free parameters; learning; multi-resolution analysis; person identification; リフティングウェーブレット; 方向余弦最大化学習; 分散最大化学習; カートシス最小化学習; 対象物検出; 表情認識; 顔画像認識; リフティング双直交ウェーブレットフィルタ; 顔部位; 逐次学習; 追跡; リフ

Lifting wavelet is called the second generation wavelet, which is developed by Wim Sweldens of Lucent Technologies' Bell Labs. The lifting wavelet has a lifting term which incorporates controllable free parameters. Lifting scheme is a set of the down sampling filters constructed by adding the lifting term to initial biorthogonal wavelet filters. The constructed filters are also biorthogonal wavelet filters and keep the perfect reconstruction. These are very important properties for the lifting wavelet filters.In this research, using such properties, we proposed a new learning method for determining the free parameters in the lifting term and developed a tracking system of moving objects based on the learned lifting scheme. And then, the various learning methods to determine the lifting parameters were produced by our lifting dyadic wavelet scheme which is extended version of the biorthogonal lifting scheme. Using the learned lifting scheme, we developed the image extraction algorithm and constructed person identification system via facial images captured by video frames. Furthermore, using the dyadic lifting scheme, we presented the technique for designing biorthogonal wavelets by dyadic wavelet. In addition, we studied to generate 3D objects by utilizing the wavelet multi-resolution analysis.

起重小波被称为第二代小波，它是由Lucent Technologies的Bell Labs的Wim Sweldens开发的。起重小波的起重术语包含可控的自由参数。提升方案是通过将起重项添加到初始生物表定小波滤波器中构建的一组向下采样过滤器。构造的过滤器也是生物三相的小波过滤器，并保持完美的重建。这些是提起小波过滤器的非常重要的属性。在这项研究中，使用此类属性，我们提出了一种新的学习方法，用于确定提起术语中的自由参数，并根据学习的提升方案开发了移动对象的跟踪系统。然后，确定提升参数的各种学习方法是通过我们的提升二元小波方案产生的，该方案是生物表定提升方案的扩展版本。使用学习的提升方案，我们通过视频框架捕获的面部图像开发了图像提取算法和构造的人识别系统。此外，使用二元提升方案，我们介绍了通过二元小波设计生物双相小波的技术。此外，我们研究了通过使用小波多分辨率分析来生成3D对象。

项目成果

Fast face detection by lifting dyadic wavelet filters

• DOI: 10.1109/icip.2003.1247389
• 发表时间: 2003-11
• 期刊: Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
• 作者: Turghunjan Abdukirim Türüki;K. Niijima;S. Takano

3D visual component based voice input/output interfaces for interactive 3D graphics applications

用于交互式 3D 图形应用的基于 3D 视觉组件的语音输入/输出接口

• 发表时间: 2004
• 期刊: Proceedings of the 5th Game-On International Conference on Computer Games : AI, Design and Education(CGAIDE 2004)
• 作者: H.Fukutake;Y.Okada;K.Niijima
• 通讯作者: K.Niijima

Yoshihiro Okada, Yoshiaki Akazawa, Koichi Niijima: "Manipulation using magnet metaphor for 2D and 3D integrated toolkit systems"13th International Conference on Artificial Reality and Tele-existence (ICAT2003). 298-303 (2003)

Yoshihiro Okada、Yoshiaki Akazawa、Koichi Niijima：“使用磁铁隐喻进行 2D 和 3D 集成工具包系统的操纵”第 13 届人工现实和远程存在国际会议 (ICAT2003)。

Time-tunnel : Visual analysis tool for Time-series numerical data and its extension toward parallel coordinates

时间隧道：时间序列数值数据的可视化分析工具及其向平行坐标的扩展

• 发表时间: 2005
• 期刊: Computer Graphics, Imaging and Visualization as Proc.of CGIV 05 (IEEE CS Press)
• 作者: H.Notsu;Y.Okada;Y.Akaishi;K.Niijima
• 通讯作者: K.Niijima

Video scene retrieval based on the Layerization of images and the matching of layer-trees,

基于图像分层和层树匹配的视频场景检索，

• 发表时间: 2005
• 期刊: Proc. of the Image and Vision Computing New Zealand 2005 (IVCNZ2005)
• 作者: N.Nakamura;S.Takano;K.Niijima
• 通讯作者: K.Niijima