Burrows, Liam, Chen, Ke, Torella, Francesco. (1401). On two convex variational models and their iterative solutions for selective segmentation of images with intensity inhomogeneity. , 1(2), 86-103. doi: 10.52547/CMCMA.1.2.86
Liam Burrows; Ke Chen; Francesco Torella. "On two convex variational models and their iterative solutions for selective segmentation of images with intensity inhomogeneity". , 1, 2, 1401, 86-103. doi: 10.52547/CMCMA.1.2.86
Burrows, Liam, Chen, Ke, Torella, Francesco. (1401). 'On two convex variational models and their iterative solutions for selective segmentation of images with intensity inhomogeneity', , 1(2), pp. 86-103. doi: 10.52547/CMCMA.1.2.86
Burrows, Liam, Chen, Ke, Torella, Francesco. On two convex variational models and their iterative solutions for selective segmentation of images with intensity inhomogeneity. , 1401; 1(2): 86-103. doi: 10.52547/CMCMA.1.2.86

On two convex variational models and their iterative solutions for selective segmentation of images with intensity inhomogeneity

Computational Mathematics and Computer Modeling with Applications (CMCMA)
دوره 1، شماره 2، اسفند 2022، صفحه 86-103    اصل مقاله (7.41 M)
نوع مقاله: Regular paper
شناسه دیجیتال (DOI): 10.52547/CMCMA.1.2.86
نویسندگان
Liam Burrows1؛ Ke Chen* 2؛ Francesco Torella3
1Centre for Mathematical Imaging Techniques and Department of Mathematical Sciences, University of Liverpool, Liverpool L19 7ZL, United Kingdom.
2Department of Mathematical Sciences, University of Liverpool, Liverpool, UK
3Liverpool Vascular & Endovascular Service, Royal Liverpool and Broadgreen University Hospitals NHS Trust, Liverpool, L7 8XP, United Kingdom
چکیده
Treating images as functions and using variational calculus,
mathematical imaging offers to design novel and continuous methods, outperforming traditional methods based on matrices, for modelling real life tasks in image processing.
Image segmentation is one of such fundamental tasks  as  many application areas demand a reliable segmentation method. Developing reliable selective segmentation algorithms is
particularly important in relation to training data preparation in modern machine learning as accurately isolating a specific object in an image with minimal user input is a valuable tool. When an image's intensity is consisted of mainly piecewise constants, convex models are available.
Different from previous works, this paper
proposes two convex models that are capable of segmenting local features defined by geometric constraints for images having intensity inhomogeneity.
Our new, local, selective and convex variants are extended from the non-convex Mumford-Shah model intended for global segmentation.
They have fundamentally improved on previous selective models that assume intensity  of piecewise constants. Comparisons with related models are conducted to illustrate the advantages of  our new models.
کلیدواژه‌ها
Variational calculus؛ Inverse problems؛ Image segmentation؛ Mumford-Shah؛ Intensity inhomogeneity؛ Geometric constraints؛ Iterative methods
آمار
تعداد مشاهده مقاله: 363
تعداد دریافت فایل اصل مقاله: 307
آمار
تعداد نشریات41
تعداد شماره‌ها1,610
تعداد مقالات14,143
تعداد مشاهده مقاله97,777,387
تعداد دریافت فایل اصل مقاله62,391,977
اخبار نشریات