This paper proposes a region-based active contour model for image segmentation that addresses intensity inhomogeneity. The model uses a region-scalable fitting (RSF) energy functional, which incorporates intensity information from local regions at a controllable scale. The RSF energy is defined in terms of a contour and two fitting functions that approximate image intensities on either side of the contour. This energy is then incorporated into a variational level set formulation with a level set regularization term, which ensures the regularity of the level set function and avoids expensive reinitialization. The model is able to handle intensity inhomogeneity by using a kernel function to extract local intensity information and guide the motion of the contour. Experimental results on synthetic and real images show that the proposed method performs well in segmenting images with intensity inhomogeneity. The model is compared with existing methods such as the piecewise smooth (PS) model and the mean shift algorithm, demonstrating its superior performance in terms of computational efficiency and accuracy. The paper also discusses the region-scalability of the model and its ability to handle different scales of intensity information. The proposed method is shown to be robust to the initial contour location and can achieve accurate segmentation results even with a small scale parameter. The model is also extended to a multiphase level set formulation to handle images with multiple regions. Overall, the proposed method provides a promising approach for image segmentation in the presence of intensity inhomogeneity.This paper proposes a region-based active contour model for image segmentation that addresses intensity inhomogeneity. The model uses a region-scalable fitting (RSF) energy functional, which incorporates intensity information from local regions at a controllable scale. The RSF energy is defined in terms of a contour and two fitting functions that approximate image intensities on either side of the contour. This energy is then incorporated into a variational level set formulation with a level set regularization term, which ensures the regularity of the level set function and avoids expensive reinitialization. The model is able to handle intensity inhomogeneity by using a kernel function to extract local intensity information and guide the motion of the contour. Experimental results on synthetic and real images show that the proposed method performs well in segmenting images with intensity inhomogeneity. The model is compared with existing methods such as the piecewise smooth (PS) model and the mean shift algorithm, demonstrating its superior performance in terms of computational efficiency and accuracy. The paper also discusses the region-scalability of the model and its ability to handle different scales of intensity information. The proposed method is shown to be robust to the initial contour location and can achieve accurate segmentation results even with a small scale parameter. The model is also extended to a multiphase level set formulation to handle images with multiple regions. Overall, the proposed method provides a promising approach for image segmentation in the presence of intensity inhomogeneity.