内窥镜图像畸变校正的新方法

本文提出了基于全局收敛线性搜索的内窥镜图像桶形畸变的校正方法。方法假定畸变为圆对称形式，并利用多项式映射将畸变图像从畸变图像空间映射到校正图像空间。根据内窥镜成像特性以及基于全局收敛的线性搜索法来确定畸变图像中心和多项式系数。采用非线性回归对校正图像进行补偿。试验结果证实，该方法校正效果好、响应速度快、满足需要定量分析的图像处理的要求。

A New Method for Distortion Correction of Endoscope Image

A new method to correct the barral distortion of endoscope image based on the line search method of guaranteed global convergence is presented.A mathematical model based on polynomial mapping is used to map the image from the distortion image space onto the corrected image space.The model parameters include the polynomial coefficients,distortion center,and corrected center.The proposed method utilizes the imaging characteristics of an endoscope and a line search method of global convergence for the iterative procedure to obtain the optimum parameters.The experimental results using the proposed method have verified thatthe degree of the distortion correction is sufficient for improved diagnostic evaluation and provides high speed response and forms a key step toward online distortion correction,which is required for accurate quantitative analysis of the image.