A parallel implementation of exact Euclidean distance transform based on exact dilations

2004 ◽  
Vol 28 (3) ◽  
pp. 107-113 ◽  
Author(s):  
Odemir Martinez Bruno ◽  
Luciano da Fontoura Costa
Keyword(s):  
Euclidean Distance ◽  
Parallel Implementation ◽  
Distance Transform ◽  
Euclidean Distance Transform

A HIGH PERFORMANCE 3D EXACT EUCLIDEAN DISTANCE TRANSFORM ALGORITHM FOR DISTRIBUTED COMPUTING

2010 ◽  
Vol 24 (06) ◽  
pp. 897-915 ◽  
Author(s):  
JULIO CESAR TORELLI ◽  
RICARDO FABBRI ◽  
GONZALO TRAVIESO ◽  
ODEMIR MARTINEZ BRUNO
Keyword(s):  
Data Compression ◽  
High Performance ◽  
Euclidean Distance ◽  
Parallel Implementation ◽  
Applied Mathematics ◽  
Distance Transform ◽  
3D Images ◽  
Euclidean Distance Transform ◽  
Communication Time ◽  
Performance Results

The Euclidean distance transform (EDT) is used in various methods in pattern recognition, computer vision, image analysis, physics, applied mathematics and robotics. Until now, several sequential EDT algorithms have been described in the literature, however they are time- and memory-consuming for images with large resolutions. Therefore, parallel implementations of the EDT are required specially for 3D images. This paper presents a parallel implementation based on domain decomposition of a well-known 3D Euclidean distance transform algorithm, and analyzes its performance on a cluster of workstations. The use of a data compression tool to reduce communication time is investigated and discussed. Among the obtained performance results, this work shows that data compression is an essential tool for clusters with low-bandwidth networks.

scholarly journals Parallel N-Dimensional Exact Signed Euclidean Distance Transform

2006 ◽  
Author(s):  
Robert Staubs ◽  
Andriy Fedorov ◽  
Leonidas Linardakis ◽  
Benjamin Dunton ◽  
Nikos Chrisochoides
Keyword(s):  
Data Structures ◽  
Euclidean Distance ◽  
Parallel Implementation ◽  
Three Dimensional ◽  
Distance Transform ◽  
Distance Transforms ◽  
Euclidean Distance Transform ◽  
Use Of Data ◽  
Computation Speed ◽  
Standard Tests

The computation speed for distance transforms becomes important in a wide variety of image processing applications. Current ITK library filters do not see any benefit from a multithreading environment. We introduce a three-dimensional signed parallel implementation of the exact Euclidean distance transform algorithm developed by Maurer et al. with a theoretical complexity of O(n/p) for n voxels and p threads. Through this parallelization and efficient use of data structures we obtain approximately 3 times mean speedup on standard tests on a 4-processor machine compared with the current ITK exact Euclidean distance transform filter.

Level Set Method Optimized with the Euclidean Distance Transform

2019 ◽  
Author(s):  
Luis Fernando Segalla ◽  
Alexandre Zabot ◽  
Diogo Nardelli Siebert ◽  
Fabiano Wolf
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Euclidean Distance ◽  
Distance Transform ◽  
Euclidean Distance Transform

Retinal image blood vessel extraction and quantification with Euclidean distance transform approach

2020 ◽  
Author(s):  
Kuryati Kipli ◽  
Mohammed Enamul Hoque ◽  
Lik Thai Lim ◽  
Tengku Mohd Afendi Zulcaffle ◽  
Siti Kudnie Sahari ◽  
...  
Keyword(s):  
Blood Vessel ◽  
Retinal Image ◽  
Euclidean Distance ◽  
Distance Transform ◽  
Euclidean Distance Transform ◽  
Vessel Extraction

scholarly journals Identification of protein pockets and cavities by Euclidean Distance Transform

2018 ◽  
Author(s):  
Sebastian Daberdaku
Keyword(s):  
Ligand Binding ◽  
Active Sites ◽  
Euclidean Distance ◽  
Protein Structures ◽  
Ligand Docking ◽  
Distance Transform ◽  
Structure Based Drug Design ◽  
Distance Map ◽  
Euclidean Distance Transform ◽  
Protein Pockets

Protein pockets and cavities usually coincide with the active sites of biological processes, and their identification is significant since it constitutes an important step for structure-based drug design and protein-ligand docking applications. This paper presents a novel purely geometric algorithm for the detection of ligand binding protein pockets and cavities based on the Euclidean Distance Transform (EDT). The EDT can be used to compute the Solvent-Excluded surface for any given probe sphere radius value at high resolutions and in a timely manner. The algorithm is adaptive to the specific candidate ligand: it computes two voxelised protein surfaces using two different probe sphere radii depending on the shape of the candidate ligand. The pocket regions consist of the voxels located between the two surfaces, which exhibit a certain minimum depth value from the outer surface. The distance map values computed by the EDT algorithm during the second surface computation can be used to elegantly determine the depth of each candidate pocket and to rank them accordingly. Cavities on the other hand, are identified by scanning the inside of the protein for voids. The algorithm determines and outputs the best k candidate pockets and cavities, i.e. the ones that are more likely to bind to the given ligand. The method was applied to a representative set of protein-ligand complexes and their corresponding unbound protein structures to evaluate its ligand binding site prediction capabilities, and was shown to outperform most of the previously developed purely geometric pocket and cavity search methods.

Sign in / Sign up

Export Citation Format

Share Document