A mobile image retrieval system based on lifting complex wavelet transform

提出了一种适用于移动图像检索系统的局部特征提取方法。我们首先介绍了提升复小波变换在这项工作中的重要作用。由于慢波管具有一组可控的自由参数，我们可以通过调整其参数来设计具有不同性质的慢波管。在这项研究中，我们构造了一组小波变换，使它们能够从图像中提取多尺度的局部特征。将新的一组小波变换应用于训练图像，可以构建局部特征数据库。利用该数据库，我们在移动机器人上实现了一个基于LCWTs的图像检索系统。该方法的主要贡献在于可以设计出能够适应移动机器人环境的LCWTs。

This study proposes a local feature extraction method for a mobile image retrieval system. We first introduce Lifting Complex Wavelet Transform (LCWT) plays an important role in this work. Since the LCWT has a set of controllable free parameters, we can design the LCWTs with various properties by tuning their parameters. In this study, we construct a set of LCWTs so that they can extract local features from an image by multi-scale. Applying the new set of LCWTs to the training images, a local feature database can be constructed. By using this database, we implement an image retrieval system based on LCWTs on the mobile robot. The main contribution of our method is that the LCWTs can be designed so as to adapt to the environment for the mobile robot.