A factorization based active contour model for texture segmentation
Mingqi Gao, Hengxin Chen, Shenhai Zheng, Bin Fang · 2016
This paper presents a factorization based active contour model for 2-phase texture segmentation. We utilize the local spectral histogram as the texture features, and then establish a novel energy function based on the theory of the matrix decomposition. Unlike the existing methods, we only choose the combination weights from object region and background region to handle the motion of curve. We compare the proposed method to the recently active contour methods and the experiments are performed on synthetic and the real-world images. The experimental results show that our model is more robust against the complex background than the other strategies.