高斯尺度参数自适应算法研究

Adaptive algorithm of Gaussian scale parameter

为了避免计算过于复杂或因丢弃过多关键信息而造成失真过大的问题,在高斯尺度空间的构造中正确选用尺度参数,以使图像信息的变化呈现均匀的特点就显得尤其重要。目前许多高斯尺度空间应用中采用的层之间的尺度参数关系并不明确,有可能使得分层效果不理想。基于视觉特征模型提出一种自适应高斯尺度参数的算法,并通过实验验证了它的有效性,从而为图像的高层次处理如目标识别等提供信息量稳定变化的尺度空间。

For the purpose of avoiding the problem of complicated computation or over-distortion because of losing too much key information,it is crucial to choose appropriate scale parameter during constructing Gaussian scale-space in order to represent the image information in uniform distribution.At present,many applications in Gaussian scale-space about the scale parameter is not clear,which may lead to bad effect of layer.The paper proposes a kind of adaptive algorithm of scale parameter in terms of the module of visual characters.The method is evaluated by experiment in the last section.Experimental results present the uniformly distributed information in scale-space which will be useful for higher-level image processing technologies such as object recognition.