REGION GROWING IMAGE SEGMENTATION ON LARGE DATASETS USING GPU

Image segmentation is an important image processing, and it seems everywhere if we want to analyze what inside the image. There are varieties of applications of image segmentation such as the field of filtering noise from image, medical imaging, and locating objects in satellite images and in automatic traffic control systems, machine vision in problem of feature extraction and in recognition. This paper focuses on accelerating the image segmentation mechanism using region growing algorithm inside GPU (Graphical Processing Unit). In region growing algorithm, an initial set of small areas are iteratively merged according to similarity constraints. We have started by choosing an arbitrary seed pixel and compare it with neighboring pixels. Region is grown from the seed pixel by adding in neighboring pixels that are similar, increasing the size of the region. When the growth of one region stops we simply choose another seed pixel which does not yet belong to any region and start again. This whole process is continued until all pixels belong to some region. If any of the segment makers has the fusion cost lower than the maximum fusion cost (a given threshold), it is selected to grow. Avoid information overlapping like two threads attempting to merge its segment with the same adjacent segment.  Experiments have demonstrated that the proposed shape features do not imply in a significant change of the segmentation results, as long as the algorithm’s parameters are properly adjusted. Moreover, experiments for performance evaluation indicated the potential of using GPUs to accelerate this kind of application. For a simple hardware (GeForce 630M GT), the parallel algorithm reached a maximum speed up of approximately 20-30% for different datasets. Considering that segmentation is responsible for a significant portion of the execution time in many image analysis applications, especially in object-oriented analysis of remote sensing images, the experimentally observed acceleration values are significant. Two variants of PBF (Parallel Best Fitting) and PLMBF (Parallel Local Mutual Best Fitting) have been used to analyze the best merging cost of the two segments. It has been found that the PLMBF has been performed better than PBF.  It should also be noted that these performance gains can be obtained with low investment in hardware, as GPUs with increasing processing power are currently available on the market at declining prices. The parallel computational scheme is well suited for cluster computing, leading to a good solution for segmenting very large data sets.

[1]  A. Ram Baek,et al.  Speed-up image processing on mobile CPU and GPU , 2015, 2015 Asia Pacific Conference on Multimedia and Broadcasting.

[2]  Siau-Chuin Liew,et al.  A review on parallel medical image processing on GPU , 2015, 2015 4th International Conference on Software Engineering and Computer Systems (ICSECS).

[3]  Kwang-Yeob Lee,et al.  A design of a GP-GPU based stream processor for an image processing , 2015, 2015 38th International Conference on Telecommunications and Signal Processing (TSP).

[4]  N. Aitali,et al.  New fine-grained clustering algorithm on GPU architecture for bias field correction and MRI image segmentation , 2015, 2015 27th International Conference on Microelectronics (ICM).

[5]  Mun-Ho Jeong,et al.  Real-time range image segmentation on GPU , 2014, 2014 14th International Conference on Control, Automation and Systems (ICCAS 2014).

[6]  Abu Asaduzzaman,et al.  A time-efficient image processing algorithm for multicore/manycore parallel computing , 2015, SoutheastCon 2015.

[7]  Raul Queiroz Feitosa,et al.  A PARALLEL IMAGE SEGMENTATION ALGORITHM ON GPUS , 2012 .

[8]  Jeffrey A. Fessler,et al.  Edge-Preserving Image Denoising via Group Coordinate Descent on the GPU , 2015, IEEE Transactions on Image Processing.

[9]  Mihail Gaianu,et al.  Multi-phase Identification in Microstructures Images Using a GPU Accelerated Fuzzy C-Means Segmentation , 2014, 2014 16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing.

[10]  Xiaoxiao Li,et al.  Semantic Image Segmentation via Deep Parsing Network , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Kyung Ki Kim,et al.  A robust and parallel-friendly distance image based hand detection , 2015, 2015 International SoC Design Conference (ISOCC).

[12]  Rachita Misra,et al.  A new approach for parallel region growing algorithm in image segmentation using MATLAB on GPU architecture , 2015, 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS).

[13]  Arthur Daniel Costea,et al.  Multi-class segmentation for traffic scenarios at over 50 FPS , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[14]  Hyungsuk Choi,et al.  Vivaldi: A Domain-Specific Language for Volume Processing and Visualization on Distributed Heterogeneous Systems , 2014, IEEE Transactions on Visualization and Computer Graphics.

[15]  Bin Wang,et al.  GPU Accelerated Edge-Region Based Level Set Evolution Constrained by 2D Gray-Scale Histogram , 2013, IEEE Transactions on Image Processing.

[16]  Peter Bajcsy,et al.  MIST: Microscopy Image Stitching Tool , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[17]  Terry M. Peters,et al.  Interactive Hierarchical-Flow Segmentation of Scar Tissue From Late-Enhancement Cardiac MR Images , 2014, IEEE Transactions on Medical Imaging.

[18]  Sangkeun Lee,et al.  Low-Complexity Topological Derivative-Based Segmentation , 2015, IEEE Transactions on Image Processing.

[19]  Dimitris Maroulis,et al.  MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU , 2017, IEEE Journal of Biomedical and Health Informatics.

[20]  Suk-Ju Kang,et al.  Image segmentation using linked mean-shift vectors and its implementation on GPU , 2014, IEEE Transactions on Consumer Electronics.

[21]  Anna Fabijanska,et al.  New accelerated graph-based method of image segmentation applying minimum spanning tree , 2014, IET Image Process..

[22]  Lizhuang Ma,et al.  Temporally Coherent Video Saliency Using Regional Dynamic Contrast , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[23]  Raul Queiroz Feitosa,et al.  A Region-Growing Segmentation Algorithm for GPUs , 2013, IEEE Geoscience and Remote Sensing Letters.

[24]  Vladan Papic,et al.  Image segmentation based on complexity mining and mean-shift algorithm , 2014, 2014 IEEE Symposium on Computers and Communications (ISCC).

[25]  Mahmoud Al-Ayyoub,et al.  Improving FCM and T2FCM algorithms performance using GPUs for medical images segmentation , 2015, 2015 6th International Conference on Information and Communication Systems (ICICS).

[26]  Anju Soosan Baby,et al.  A parallel approach for region-growing segmentation , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[27]  Mingyu Chen,et al.  A Reliable Distributed Convolutional Neural Network for Biology Image Segmentation , 2015, 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[28]  Zoltan Juhasz,et al.  A GPU-based simultaneous real-time EEG processing and visualization system for brain imaging applications , 2015, 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[29]  Nabil Aouf,et al.  GPU based GMM segmentation of kinect data , 2014, Proceedings ELMAR-2014.