REGION GROWING IMAGE SEGMENTATION ON LARGE DATASETS USING GPU

  • Gurpreet Kaur Research Scholar, Department of Computer Science Engineering, SBSSTC, Ferozepur
  • Sonika Jindal Assistant Professor, Department of Computer Science Engineering, SBSSTC, Ferozepur
Keywords: Segmentation, GPU, Image Processing, OpenCV, Region Growing algorithm, CUDA

Abstract

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.

References

A. . K. Sahoo, G. Kumar, G. Mishra and R. Misra, "A New Approach for Parallel Region Growing Algorithm in Image Segmentation using MATLAB on GPU Architecture," IEEE , pp. 279-283, 2015.
J. X. Hua and M.-H. Jeong, "Real-Time Range Image Segmentation on GPU," International Conference on Control, Automation and Systems (ICCAS), pp. 150-153, 2014.
S. Katsigiannis, E. Zacharia and D. Maroulis, "MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU," IEEE, pp. 1-8, 2015.
H. Cho, S.-J. Kang, S. I. Cho and Y. H. Kim, "Image Segmentation Using Linked Mean-Shift Vectors and Its Implementation on GPU," IEEE, pp. 719-727, 2014.
Darian M. Onchis, D. Frunzaverde, M. Gaianu and R. Ciubotariu, "Multi-phase identification in microstructures images using a GPU accelerated fuzzy c-means segmentation," IEEE, pp. 602-607, 2015.
N. Aitali, B. Cherrad, O. Bouattane, M. Youssfi and A. Raihani, "New Fine-Grained Clustering Algorithm on GPU Architecture for Bias Field Correction and MRI Image Segmentation," IEEE, pp. 118-121, 2015.
C. S. Cho and S. Lee, "Low-Complexity Topological Derivative-Based Segmentation," IEEE, pp. 734-741, 2015.
J. Chalfoun, M. Majurski, T. Blattner, W. Keyrouzl, P. Bajcsy and M. Brady, "MIST: Microscopy Image Stitching Tool," IEEE, p. 1757, 2015.
Arthur D. Costea and Sergiu Nedevschi , "Multi-Class Segmentation for Traffic Scenarios at Over 50 FPS," IEEE, pp. 1390-1395, 2014.
X. Zhang, G. Tan and M. Chen, "A Reliable Distributed Convolutional Neural Network for Biology Image Segmentation," IEEE, pp. 777-780, 2015.
Mohammed A. Shehab, , Mahmoud Al-Ayyoub and Yaser Jararweh, "Improving FCM and T2FCM Algorithms Performance using GPUs for Medical Images Segmentation," IEEE, pp. 130-135, 2015.
Z. Liu, X. Li, P. Luo , C. C. Loy and X. Tang, "Semantic Image Segmentation via Deep Parsing Network," IEEE, pp. 1377-1785, 2015.
Z. Yi, X. Hu, B. Jang and K. K. Kim, "A Robust and Parallel-Friendly Distance Image Based Hand Detection," IEEE, pp. 33-34, 2015.
J. Sirotkovic, H. Dujmic and V. Papic , "Image segmentation based on complexity mining and mean-shift algorithm," IEEE, pp. 1-6, 2014.
A.-R. Baek, K. Lee and H. Choi , "Speed-up Image Processing on Mobile CPU and GPU," IEEE, pp. 79-81, 2015.
Z. Juhasz and G. Kozmann, "A GPU-based Simultaneous Real-Time EEG Processing and Visualization System for Brain Imaging Applications," IEEE, pp. 299-304, 2015.
H. L. Khor, S.-C. Liew and Jasni Mohd. Zain , "A Review on Parallel Medical Image Processing on GPU," IEEE, pp. 45-48, 2015.
A. Asaduzzaman, A. Martinez and A. Sepehri , "A Time-Efficient Image Processing Algorithm for Multicore/Manycore Parallel Computing," IEEE, pp. 1-5, 2015.
A. Fabija and J. Gocławski, "New accelerated graph-based method of image segmentation applying minimum spanning tree," IET Image Processing, pp. 239-251, 2013.
A. S. Baby and Balachandran K, "A Parallel Approach For Region-Growing Segmentation," IEEE, pp. 196-200, 2015.
C. Cho and S. Lee, "Effective Five Directional Partial Derivatives-based Effective Five Directional Partial Derivatives-based," IEEE, pp. 1-9, 2015.
K. Y. Lee, G. Kyung, T. R. Park, J. C. Kwak and Y. S. Koo, "A Design of a GP-GPU based Stream Processor for an Image Processing," IEEE, pp. 535-539, 2015.
M. G. McGaffin and Jeffrey A. Fessler, "Edge-Preserving Image Denoising via Group Coordinate Descent on the GPU," IEEE, pp. 1273-1281, 2015.
A. amamra, T. mouats and N. aouf, "GPU based GMM segmentation of Kinect data," International Symposium ELMAR, pp. 99-102, 2014.
R. Q. F. B. R. F. P. N. Happ, "A PARALLEL IMAGE SEGMENTATION ALGORITHM ON GPUS," Proceedings of the 4th GEOBIA, pp. 580-585, 2012.
H. Choi, W. Choi, T. M. Quan, , David G. C. Hildebrand, Hanspeter Pfister and Won-Ki Jeong, "Vivaldi: A Domain-Specific Language for Volume Processing and Visualization on Distributed Heterogeneous Systems," IEEE , pp. 2407-2416, 2014.
Y. Li, B. Sheng, Lizhuang Ma, Wen Wu and Zhifeng Xie, "Temporally Coherent Video Saliency Using Regional Dynamic Contrast," IEEE , pp. 2067-2076, 2013.
M. Rajchl, J. Yuan, E. Ukwatta, James A. White, J. Stirrat, Cyrus M. S. Nambakhsh, Feng P. Li and Terry M. Peters, "Interactive Hierarchical-Flow Segmentation of Scar Tissue From Late-Enhancement Cardiac MR Images," IEEE, pp. 159-172, 2014.
Patrick Nigri Happ, Raul Queiroz Feitosa, Cristiana Bentes and Ricardo Farias, "A Region-Growing Segmentation Algorithm for GPUs," IEEE, pp. 1612-166, 2013.
X. G. W. Souleymane Balla-Arabé, "GPU Accelerated Edge-Region Based Level Set Evolution Constrained by 2D Gray-Scale Histogram," IEEE, pp. 2688-2698, 2013.
Published
2016-01-12
How to Cite
Kaur, G., & Jindal, S. (2016). REGION GROWING IMAGE SEGMENTATION ON LARGE DATASETS USING GPU. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 15(14), 7486-7497. https://doi.org/10.24297/ijct.v15i14.5605
Section
Articles