图割算法是图像分割方法中一种高效最优化的计算方法，针对图像中目标物体光照不均匀导致的分割不准确问题，本文提出了一种基于光度信息的图割方法：该方法利用彩色图像的RGB值，得到像素的颜色值和亮度值，用其平均值表示像素的光度值，将图像的光度信息融入到主动轮廓模型的能量函数中，构建新的能量函数，利用最大流/最小割算法求解新的能量函数的最优解，得到目标的轮廓；实验结果证明，该方法能够使初始轮廓较准确较迅速地收敛到目标物体的轮廓。%The graph cuts algorithm is one of high effective optimal methods in the image segmentations. To improve the accuracy of segmentation caused by uneven illumination,a method which combines the information of luminosity with graph cuts is proposed. This method will get the color values and brightness values of pixel depending on the color image,with the average representative luminosity values,then integrate the photometric information into ener-gy function of active contour model,and build a new energy function,finally get the optimal solution for solving new energy function with max-flow/min-cut algorithm,partial contour of target is obtained lastly. The experimental re-sults show that this method can make the initial contour convergence to the target object more accurately and faster.
展开▼
