Image Segmentation Using an Active Contour Model Based on the Difference Between Local Intensity Averages and Actual Image Intensities

Xiaoying Shan,Yingchun Ren,Asoke K Nandi,Xiaoliang Gong

doi:10.1109/access.2020.2975854

Xiaoying Shan, Yingchun Ren + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2975854

Copy DOI

Abstract

The local intensity fitting active contour models can handle inhomogeneous images, but they suffer from the shortcomings of poor performance in segmenting images with severe intensity inhomogeneity and being sensitive to initializations. To overcome these problems, we put forward a robust active contour model by introducing two adjustment coefficient functions. The energy functional of the proposed model is presented by integrating the local fitting term and two adjustment coefficient functions. The local fitting term is defined by introducing two local fitting functions that approximate the image intensities inside and outside of the contour. These two adjustment coefficient functions, which improve the segmentation performance and enhance the robustness to initialization, are constructed by utilizing the Sigmoid function as well as the difference between local intensity averages and image actual intensities. The results of the experiments on synthetic and real images demonstrate that the presented model not only is capable of handling intensity inhomogeneity better under more flexible initializations but also takes less time in comparison with other region-based models. Furthermore, these two adjustment coefficients can be employed to other local intensity fitting models to enhance the robustness to initialization and to decrease the segmentation time.

Highlights

Active contour models, originally put forward by Kass et al [1], have attracted considerable attention and found an increasingly wide utilization in image segmentation [2]–[7]
An active contour model is generally represented by an energy functional and formulated in a principled way by applying the level set methods [8], [9], which implicitly represents contour curve as the zero-level set of a higher dimensional level set function
THE ENERGY FUNCTIONAL BASED ON TWO ADJUSTMENT COEFFICIENT FUNCTIONS Using the adjustment coefficient functions, we present a robust local region-based model for image segmentation

Summary

Introduction

Originally put forward by Kass et al [1], have attracted considerable attention and found an increasingly wide utilization in image segmentation [2]–[7]. On level set perform image segmentation by evolving the zero-level contour curve, and are able to deal with topological changes adaptively. Active contour models are able to obtain sub-pixel accuracy of object boundaries as well as smooth and closed contour as segmentation result. Various active contour models have been presented for image segmentation. The first kind of models commonly uses the gradient information to urge the active contour curve evolve towards the boundaries of the

Results

Discussion

Conclusion