Simple low-dimensional features approximating NCC-based image matching
Simple low-dimensional features approximating NCC-based image matching
复制标题
DOI：
10.1016/j.patrec.2011.07.027
复制
发表时间：
2011-10-15
影响因子：
5.1
通讯作者：
Satoh, Shin'ichi
中科院分区：
文献类型：
--
作者：
Satoh, Shin'ichi
本文提出了一种新的低维图像特征，使图像能够非常有效地匹配。图像匹配是许多基于视觉的应用的关键技术之一，包括模板匹配、块运动估计、视频压缩、立体视觉、图像/视频相似检测、图像/视频数据库的相似性连接等。归一化互相关(NCC)是一种广泛使用的图像匹配方法，具有对灰度偏移和对比度变化具有较好的稳健性，但计算量较大。通过拉格朗日乘子方法得到的特征，可以作为两个低维特征向量之间的简单点积来提供NCC的上界。利用本文提出的特征，可以有效地加速基于NCC的图像匹配。使用从实际广播视频中获得的图像库来演示与所提出的特征的匹配性能。新特征的性能优于其他方法：多级逐次消除算法(MSEA)、离散余弦变换(DCT)系数和直方图，在仅略微牺牲召回率的情况下实现了非常高的精度。(C)2011爱思唯尔B.V.保留所有权利。
This paper proposes new low-dimensional image features that enable images to be very efficiently matched. Image matching is one of the key technologies for many vision-based applications, including template matching, block motion estimation, video compression, stereo vision, image/video near-duplicate detection, similarity join for image/video database, and so on. Normalized cross correlation (NCC) is one of widely used method for image matching with preferable characteristics such as robustness to intensity offsets and contrast changes, but it is computationally expensive. The proposed features, derived by the method of Lagrange multipliers, can provide upper-bounds of NCC as a simple dot product between two low-dimensional feature vectors. By using the proposed features, NCC-based image matching can be effectively accelerated. The matching performance with the proposed features is demonstrated using an image database obtained from actual broadcast videos. The new features are shown to outperform other methods: multilevel successive elimination algorithm (MSEA), discrete cosine transform (DCT) coefficients, and histograms, achieving very high precision while only slightly sacrificing recall. (C) 2011 Elsevier B.V. All rights reserved.