基于贝塞尔滤波改进的测地活动轮廓图像分割模型

Improved geodesic active contour image segmentation model based on Bessel filter

活动轮廓模型广泛应用于图像分割和目标轮廓提取,基于边缘的测地活动轮廓(GAC)模型在提取边缘明显的物体时得到广泛的应用,但GAC演化过程中,迭代次数较多,耗时较长。针对这一问题,结合贝塞尔滤波理论,对GAC模型改进。首先,利用贝塞尔滤波对图像进行平滑处理,降低噪声;其次,基于贝塞尔滤波的边缘检测函数,构建新的边缘停止项,且并入到GAC模型中;最后,在构造的模型中同时加入反应扩散(RD)项以避免水平集重新初始化。实验结果表明,与多个基于边缘的模型相比,所提模型在保证分割结果精确度的同时,提高了时间效率,更适用于实际应用。

Active contour model is widely used in image segmentation and object contour extraction, and the edge-based Geodesic Active Contour （GAC） model is widely used in the object extraction with obvious edges. But the process of GAC evolution costs many iterations and long time. In order to solve the problems, the GAC model was improved with Bessel filter theory. Firstly, the image was smoothed by Bessel filter to reduce the noise. Secondly, a new edge stop term was constructed based on the edge detection function of Bessel filter and incorporated into the GAC model. Finally, the Reaction Diffussion （RD） term was added to the constructed model for avoiding re-initialization of the level set. The experimental results show that, compared with several edge-based models, the proposed model improves the time efficiency and ensures the accuracy of segmentation results. The proposed model is more suitable for practical applications.