基于边缘扩展相位相关的眼底图像拼接

Fundus Images Mosaicking Based on Edge Extended Phase Correlation

该文采用了一种基于边缘扩展相位相关的图像拼接算法。首先使用改进的小波边缘检测算法对眼底图像进行边缘检测,再对检测出的边缘进行扩展相位相关计算得出图像间的平移、旋转和尺度变化,利用这些参数拼接图像,最后用渐进渐出的算法来实现拼接图像的融合。实验证明这种算法能够简化计算,并且有效的实现眼底图像的拼接。

With regard to the large amount of calculation in image mosaic algorithm, an image mosaic algorithm based on extended phase correlation of edge is presented. The improved wavelet edge detection algorithm is to detect edge of blood vessels. Then the image translation, rotation and scale changes are calculated by the extended phase correlation method. These parameters are utilized to stitch images. Finally, image fusion can be achieved by fade-in- fade-out method. It is proved by experiments that this algorithm is simple to calculate, and can effectively achieve the image mosaic.