Image Segmentation Using Active Contours with Hessian-Based Gradient Vector Flow External Force

Qianqian Qian; Ke Cheng; Wei Qian; Qingchang Deng; Yuanquan Wang

doi:10.3390/s22134956

Image Segmentation Using Active Contours with Hessian-Based Gradient Vector Flow External Force

Sensors (Basel). 2022 Jun 30;22(13):4956. doi: 10.3390/s22134956.

Authors

Qianqian Qian¹, Ke Cheng¹, Wei Qian², Qingchang Deng¹, Yuanquan Wang³

Affiliations

¹ School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China.
² School of Electronics and Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China.
³ School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China.

Abstract

The gradient vector flow (GVF) model has been widely used in the field of computer image segmentation. In order to achieve better results in image processing, there are many research papers based on the GVF model. However, few models include image structure. In this paper, the smoothness constraint formula of the GVF model is re-expressed in matrix form, and the image knot represented by the Hessian matrix is included in the GVF model. Through the processing of this process, the relevant diffusion partial differential equation has anisotropy. The GVF model based on the Hessian matrix (HBGVF) has many advantages over other relevant GVF methods, such as accurate convergence to various concave surfaces, excellent weak edge retention ability, and so on. The following will prove the advantages of our proposed model through theoretical analysis and various comparative experiments.

Keywords: Hessian matrix; anisotropy; gradient vector flow; image structure.

Grants and funding

This work was supported in part by the National Science Foundation Program of China (NSFC) (grant number: 61976241), and the International Science and technology cooperation plan project of Zhenjiang (grant number: GJ2021008).