Real-time topological image smoothing on shared memory parallel machines

TL;DR

This paper introduces a parallel topological image smoothing method for shared memory machines, achieving efficient processing of 2D binary images while preserving topology through homotopic transformations.

Contribution

A novel parallelization strategy called SDM is proposed, enabling efficient topological image processing including smoothing, skeletonization, and watershed algorithms.

Findings

Achieved a speedup of 5.2 times on an 8-core shared memory machine.

Processed 512x512 binary images at 32 images per second.

Preserved topology during parallel smoothing using homotopic transformations.

Abstract

Smoothing filter is the method of choice for image preprocessing and pattern recognition. We present a new concurrent method for smoothing 2D object in binary case. Proposed method provides a parallel computation while preserving the topology by using homotopic transformations. We introduce an adapted parallelization strategy called split, distribute and merge (SDM) strategy which allows efficient parallelization of a large class of topological operators including, mainly, smoothing, skeletonization, and watershed algorithms. To achieve a good speedup, we cared about task scheduling. Distributed work during smoothing process is done by a variable number of threads. Tests on 2D binary image (512*512), using shared memory parallel machine (SMPM) with 8 CPU cores (2 Xeon E5405 running at frequency of 2 GHz), showed an enhancement of 5.2 thus a cadency of 32 images per second is achieved.