基于边缘约束局部区域MRF的图像分割方法

针对常规马尔科夫随机场（MRF）模型对复杂自然图像分割时，存在对噪声敏感且边缘模糊的问题，构建一种基于边缘约束局部区域MRF（ECLRMRF）的图像分割模型。利用欧氏距离度量局部区域内邻接像素的相似度，依据其相似度构建局部空间来约束高斯混合模型，有效描述丰富的局部区域统计特征，并建立MRF模型的局部区域一致性约束项。利用Canny边缘检测算子提取图像的边缘特征，并在分割过程中建立图像分割区域的边缘约束，通过在MRF模型框架下将局部区域统计特征和图像边缘特征相融合，解决局部区域MRF模型对图像分割边缘模糊的问题，再采用Gibbs采样算法实现对复杂自然图像的准确分割。实验结果表明，该模型能够更好地保留图像边缘信息，并且具有更好的分割效果。

Image Segmentation Method Based on MRF with Edge Constrained Local Region

The conventional Markov Random Field(MRF) model is sensitive to noise and produces fuzzy edges when segmenting complex natural images.To address the problem, this paper proposes an Edge Constrained Local Region MRF(ECLRMRF) segmentation model.Euclidean distance is used to measure the similarity of adjacent pixels in the local region, and the local space is constructed according to the similarity to constrain the Gaussian Mixture Model(GMM), which can effectively describe the rich statistical features of the local region and establish the local region consistency constraints of the MRF model.Canny edge detection operator is used to extract the edge features of the image, and the edge constraints of the image segmentation region are established in the process of segmentation.By fusing the local region statistical features and image edge features in the framework of MRF model, the problem of blurring the edge of image segmentation in the local region MRF model is solved, and then Gibbs sampling algorithm is used to achieve accurate segmentation of complex natural images.Experimental results show that the model can better retain the edge information of the image and has better segmentation effect.