Curvelet and fast marching method‐based technique for efficient artifact detection and removal in dermoscopic images

Author(s):  
Priya Choudhary ◽  
Jyoti Singhai ◽  
J. S. Yadav
2013 ◽  
Vol 51 (6) ◽  
pp. 2999-3035 ◽  
Author(s):  
E. Carlini ◽  
M. Falcone ◽  
Ph. Hoch

2018 ◽  
Vol 7 (3) ◽  
pp. 1233
Author(s):  
V Yuvaraj ◽  
S Rajasekaran ◽  
D Nagarajan

Cellular automata is the model applied in very complicated situations and complex problems. It involves the Introduction of voronoi diagram in tsunami wave propagation with the help of a fast-marching method to find the spread of the tsunami waves in the coastal regions. In this study we have modelled and predicted the tsunami wave propagation using the finite difference method. This analytical method gives the horizontal and vertical layers of the wave run up and enables the calculation of reaching time.  


2008 ◽  
Vol 48 (1-3) ◽  
pp. 189-211 ◽  
Author(s):  
Nicolas Forcadel ◽  
Carole Le Guyader ◽  
Christian Gout

2019 ◽  
Vol 28 (4) ◽  
pp. 517-532 ◽  
Author(s):  
Sangeeta K. Siri ◽  
Mrityunjaya V. Latte

Abstract Liver segmentation from abdominal computed tomography (CT) scan images is a complicated and challenging task. Due to the haziness in the liver pixel range, the neighboring organs of the liver have the same intensity level and existence of noise. Segmentation is necessary in the detection, identification, analysis, and measurement of objects in CT scan images. A novel approach is proposed to meet the challenges in extracting liver images from abdominal CT scan images. The proposed approach consists of three phases: (1) preprocessing, (2) CT scan image transformation to neutrosophic set, and (3) postprocessing. In preprocessing, noise in the CT scan is reduced by median filter. A “new structure” is introduced to transform a CT scan image into a neutrosophic domain, which is expressed using three membership subsets: true subset (T), false subset (F), and indeterminacy subset (I). This transform approximately extracts the liver structure. In the postprocessing phase, morphological operation is performed on the indeterminacy subset (I). A novel algorithm is designed to identify the start points within the liver section automatically. The fast marching method is applied at start points that grow outwardly to detect the accurate liver boundary. The evaluation of the proposed segmentation algorithm is concluded using area- and distance-based metrics.


Author(s):  
Michael Quell ◽  
Georgios Diamantopoulos ◽  
Andreas Hössinger ◽  
Siegfried Selberherr ◽  
Josef Weinbub

Sign in / Sign up

Export Citation Format

Share Document