一种结合高帽变换和曲线演化模型的两阶段图像分割算法  

A Two-stage Image Segmentation Algorithm Combined Top-hat Transformation with Level Set Method

作　　者：倪倩 龚剑[2] 

机构地区：[1]广东广机国际招标股份有限公司,广东广州510080 [2]南方医科大学,广东广州510515

出　　处：《临床医学工程》2010年第8期11-13,共3页Clinical Medicine & Engineering

基　　金：广东省自然科学基金(06024583)

摘　　要：针对图像形态学处理中高帽变换能有效提取图像中不均匀背景的特点,提出了一种结合高帽变换和曲线演化模型的两阶段图像分割算法。该算法有效的扩展了曲线演化模型的适用范围,即使对于背景不均匀的自然图像和医学图像也能有效的加以分割。实验结果表明:该算法既保留了原有曲线演化模型的优势,又能高效稳健、快速地完成曲线演化过程。Traditional level set method is a very popular image segmentation algorithm for its highly flexibility.However,it is un able to handle images with uneven background which is a very common phenomenon existed among the natural optical and medical images.Meanwhile the morphological top-hat transform is very effective for estimating the uneven background.Thus we propose a two-stage algo rithm for image segmentation by combining top-hat transformation and level set method in this paper to remedy the drawback for the level set method to the uneven background.And the experimental results show that our proposed algorithm works perfectly to segment the images with uneven background.

关 键 词：图像分割 曲线演化 高帽变换 水平集 

分 类 号：R318.0[医药卫生—生物医学工程]