【作者】 杨涌；

【导师】 熊四昌；

【作者基本信息】 浙江工业大学 ， 机械电子工程， 2006， 硕士

【摘要】 由于显微镜物镜焦深范围有限，造成显微图像局部模糊，研究人员对图像的理解不完整等问题，本文研究了显微图像融合方法。 首先，通过本文提出的显著边界特征匹配法，对图像进行自动配准，经过分析和实验表明此配准方法能够达到高精度图像融合的要求；其次，分析了小波算法在图像分解与重构中的原理及其融合规则，并在此基础上提出了一种全新的基于能量规则的小波融合序列图像的方法，在实验中表明了小波能量融合的方法能相当好的抑制图像融合失真问题；然后，本文使用计算图像熵的方法对图像清晰度进行评定，效果良好，同时加以均值和标准差两种评价标准对本文所有的融合实验结果进行了综合的评价，避免单一参量的片面性；最后，将此系统成功的应用于刀具检测和工件表面检测。 本文提出了根据提取聚焦部分图像的小波参数，分析聚焦部分和模糊区域在小波变换域内图像能量分布密度的差异，以其高频部分与低频部分的比值为特征参照值，取其最大值为新的小波系数的融合规则。此方法能很好的判断、剔除成像中散焦部分及解决一些融合中的失真问题。在实验中将证明，所提出的方法比常规的基于区域的以像素点取最大值的小波融合方法有明显的优势。由此得出的聚焦合成图像使研究人员可直接测量所需的显微结果。更多还原

【Abstract】 Due to the limitation of the microscopic focal length, the obtained microscopic images are often blurred in some local areas, which causes that people can not recognize or understand it completely. And this paper researches the fusion method about the microscopy serial images.Firstly, the paper adopts the edge characteristic image registration, and the practical experiments prove this auto-matching method is effective. Secondly, the research analyses the principle of image decomposition and reconstruction based on wavelet-pyramid method. From the former way the paper proposes a new wavelet transform algorithm based on the energy fusion rules. And the new way can remove the defocused areas showed by the experimental result. And through the entropy and others evaluation, the comprehensive evaluation result was achieved. Thirdly, this research is successfully applied to the examination on the cutting tool surface and workpiece surface.Based on the different energy distributions of the low-frequency band and the high-frequency band, which are achieved by discrete wavelets transform, an original method for wavelet coefficient combination is proposed in this paper. It takes the ratio of the two bands as a characteristic更多还原