融合显著性特征的自适应主动轮廓模型

主动轮廓模型存在演化速度慢、对初始轮廓和噪声敏感、弱边缘泄漏及目标过分割等问题。对以上问题进行了研究，提出了融合显著性特征的自适应主动轮廓模型。提出基于去雾算法的显著性映射作为正则项提升模型对初始轮廓位置的鲁棒性，防止轮廓演化过程过早陷入局部最优解，同时缩短轮廓演化时间。为了防止模型在演化过程中出现弱边界泄漏，模型中引入边缘检测函数作为能量泛函的权重。该模型利用最大面积稀疏约束，提出自适应目标提取方法来消除目标过分割影响。与多种主动轮廓模型在数据集MRSA500(500张)上进行实验对比，表明了提出的模型对初始轮廓和噪声的鲁棒性，而且提出模型的平均分割效率提升约5.6倍，平均Jaccard相似度系数提升约22%。

Adaptive Active Contour Model Combined with Salient Features

Active contour model exits some problems including slow evolution, sensitivity to initial contour and noise, weak edge leakage and target over-segmentation. The above problems are studied, an adaptive target extraction active contour model combined with image salient features（ASF） is proposed. Firstly, a saliency detection based on the defogging algorithm is used as a regularization term to improve the robustness of the model to the initial contour position to prevent the contour evolution process from falling into the local optimal solution prematurity meanwhile shorten the contour evolution time. Secondly, in order to prevent weak boundary leakage during the evolution of the model, the edge detection function is introduced into the model as the weight of the energy functional. Finally, oriented on the maximum area sparse constraint, an adaptive target extraction method is proposed to eliminate the over-segmentation effect of the target. Experimental comparison with various active contour models on MRSA500 data set shows that the proposed model is robust to the initial contour and noise, the average segmentation efficiency of the proposed model is improved by about 5.6 times, and the average Jaccard similarity coefficient is improved by about 22%.