An Active Contour Model Based on Region Based Fitting Terms Driven by p-Laplace Length Regularization

• Published in: IEEE access Vol. 6; pp. 58272 - 58283
• Main Authors: Soomro, Shafiullah, Soomro, Toufique Ahmed, Choi, Kwang Nam
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active contours; Bias; bias field; Computational modeling; Contours; Gaussian distribution; Image edge detection; Image segmentation; Laplace equation; Level set; Mathematical model; Noise reduction; Nonhomogeneous media; Normal distribution; p-Laplace; Partial differential equations; Regularization; Shape; Statistical analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2018.2874812

In this paper, we propose a partial differential equation structure that permits an active contour method to obtain intensity inhomogeneous image segmentation. We consider fitted model comprised of local and global energy functions dictated by the scaled p-Laplace term acting as a length regularization term. A new local model is formulated by taking bias field into the local fitted model, which improves the performance of the proposed method relatively. The scaled p-Laplace equation exhibited as a regularized length term, which is utilized to reduce the impact of noise over level set minimization while guaranteeing the curve not to go through feeble boundaries. Inhomogeneities comprise of unwanted pixel variations called bias field, which change the consequences of the level set-based methods. Thereby, Gaussian distribution is used for the approximation of the bias field, and further bias field is used for bias correction likewise. Moreover, local model has been remodeled by integrating bias field inside their local information; similarly, global model is also established on the pretext of the local model. At last, we demonstrate the results on some complex images to show the strong and exact segmentation results that are conceivable with this new class of dynamic active contour model. We have also performed statistical analysis on mammogram images using accuracy, sensitivity, and Dice index metrics. Results show that the proposed method gets high accuracy, sensitivity, and Dice index values compared to the previous state-of-the-art methods.