Parallel Image Segmentation Using Reduction-Sweeps on Multicore Processors and GPUs

In this paper we introduce the Reduction Sweep algorithm, a novel graph-based image segmentation algorithm that is designed for easy parallelization. It is based on a clustering approach focusing on local image characteristics. Each pixel is compared with its neighbors in an implicitly independent manner, and those deemed sufficiently similar according to a color criterion are joined. We achieve fast execution times while still maintaining the visual quality of the results. The algorithm is presented in four different implementations: sequential CPU, parallel CPU, GPU, and hybrid CPU-GPU. We compare the execution times of the four versions with each other and with other closely related image segmentation algorithms.

[1]  Zachary Dodds,et al.  Robot control via region-based 3d reconstruction , 2007 .

[2]  Xiaodong Wu,et al.  Faster Segmentation Algorithm for Optical Coherence Tomography Images with Guaranteed Smoothness , 2011, MLMI.

[3]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[4]  Yong Cao,et al.  GPU accelerated fuzzy connected image segmentation by using CUDA , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Wolfgang Middelmann,et al.  An Efficient Parallel Algorithm for Graph-Based Image Segmentation , 2009, CAIP.

[6]  Mariusz Bajger,et al.  Two graph theory based methods for identifying the pectoral muscle in mammograms , 2007, Pattern Recognit..

[7]  Esteban Walter Gonzalez Clua,et al.  Using graph cuts in GPUs for color based human skin segmentation , 2011, Integr. Comput. Aided Eng..

[8]  智一 吉田,et al.  Efficient Graph-Based Image Segmentationを用いた圃場図自動作成手法の検討 , 2014 .

[9]  Falko Kuester,et al.  GPU-Based Active Contour Segmentation Using Gradient Vector Flow , 2006, ISVC.

[10]  Janko Calic,et al.  FreeEye: interactive intuitive interface for large-scale image browsing , 2009, MM '09.

[11]  Babette Dellen,et al.  Real-Time Image Segmentation on a GPU , 2010, Facing the Multicore-Challenge.

[12]  Pham The Bao,et al.  A New CBIR System Using SIFT Combined with Neural Network and Graph-Based Segmentation , 2010, ACIIDS.

[13]  Zsolt Kira,et al.  Inter-robot transfer learning for perceptual classification , 2010, AAMAS.

[14]  Stefano Soatto,et al.  Really Quick Shift: Image Segmentation on a GPU , 2010, ECCV Workshops.

[15]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.