基于CUDA的眼底图像快速自动配准与拼接

Fast Automatic Fundus Images Registration and Mosaic Based on CUDA

针对眼底图像对比度低、光照不均匀、视场局限及不同视场间存在几何畸变等特点,提出一种基于CUDA的眼底图像快速自动配准与拼接算法。该算法利用CUDA加快了各视场眼底图像同态滤波增强的速度及增强后各有效视场的SIFT特征提取与相互匹配的速度,并加快了结合透视变换模型的RANSAC算法进行的匹配点对提纯速度、周围视场与中央视场变换矩阵的计算速度,配准、融合后得到了眼底全景图像。实际的眼底照相机获取图像的自动配准与拼接表明,该算法可以快速、高精度地实现不同视场眼底图像的自动配准与拼接,算法速度是未采用CUDA的算法的10～30倍,精度达到像素级,具有很好的鲁棒性。

In order to overcome the characteristics of low contrast, non--uniform illumination, limited field of view （FOV）, and the geometric distortion between different FOV of the fundus ima- ges, a fast automatic fundus image registration and mosaic algorithm was presented based on CUDA. Fundus images were enhanced by homomorphism filtering and the SIFT features in effective FOV were extracted and matched between images with CUDA speeded up. With CUDA application, point pairs were purified using RANSAC algorithm employed perspective model, transformation matrixes were computed according to the matching point pairs of surrounding FOV images to the central, im- age registration and image fusion was implemented to get fundus panoramic image finally. The auto- matic registration and mosaic results of multiple FOV images obtained by fundus camera show that the algorithm is robust and stability with registration accuracy is up to pixel level, the algorithm speed upgrades 10 to 30 times, high--precision automatic fundus image mosaic can be achieved.