一种通用的仿射不变特征区域提取方法

A General Approach for Extracting Affine Invariant Regions

本文利用尺度-空间理论和自相关矩阵的局部形状提出了一种通用的提取仿射不变特征区域的方法.首先,在尺度-空间中对图像的归一化高斯微分求三维局部极大值获得特征点和特征尺度位置,然后在特征点的特征尺度上用自相关矩阵刻画局部的灰度变化,提取的椭圆区域即为仿射不变特征区域.在此通用方法框架下构造了Har-ris3D、Laplace3D、Hessian3D和Localjet43D四种仿射不变特征区域算法.实验结果表明这四种算法都具有照度、旋转和尺度不变性.用本文设计的一种仿射不变性仿真实验方法验证了算法的仿射不变性.比较四种算法发现除了Harris3D性能稍差外其他三种算法性能接近.

Using scale-space theory and the local shape of auto-correlation matrix,a new general approach is proposed to extract affine invariant regions. First, the feature points and their characteristic scales are detected by the local maxima of nonnal Gaussian derivatives over scale-space; Then, the auto-correlation matrices, which are used to describe local image structure, are computed on the characteristic scales of feature points. The extracted ellipse regions are affine invariant. Four affine invariant region algorithms, namely Harris3D, Laplace3D, Hessian3D and Localjet43D, are presented using the general approach. The experimental results show the four algorithms are invariant to illumination, rotation and scale changes. The affine invariance is verified by the simulation test we designed for affine invariance. Comparing the four algorithms, we fred that the performance of other three algorithms is similar except for Harris3D.