Implementation of an Improved Watershed Algorithm in a Virtex 5 Platform

Abstract

Watershed transform, as was described by Vincent and Soille, is a segmentation algorithm based on a flooding process of the gradient image, which is observed as a topographic surface. Watershed transform aims at finding the peaks in this surface and identifying them as image contours. This algorithm is used in many applications for its flexibility. However, its main limitation is the over segmentation. In this paper, we will try to overcome this limitation. The enhancement phase is based on filtering the original image by an anisotropic diffusion filter and then quantizing the gradient image. For evaluation, the improved algorithm is applied on an empirical basis for image segmentation research in order to be compared with other segmentation algorithms. Simulation results prove the effectiveness of our algorithm. Watershed algorithm is used in medical field in order to extract areas of interest in an image representing a section bone. Finally, the implementation phase in a Virtex 5 is based on the co design methodology. The synthesis results show that the performance of the developed design is 130 MHz and the hardware occupation is about 78% for an image of size of 256*256.

Reference

• A.Michael Parfitt, Mark k.Dreznzr, Francis H.Glorieux, Jhon A.Kanis, Hartmut Malluche, Pierre J.Menuier, Susan Mott and Robert R.Recker « A bone histomorphometry: Standardization of Nomenclature. Sumbols and Units», Journal of bone and Mineral Research, Volume 2, Number 6, 1987.
• Bo Zhao, Zhongxiang Zhun, Enrong Mao and Zhenghe Song «Image Segmentation Based on Ant Colony Optimization and K-Means Clustering» College of Engineering China Agricultural University Beijing. China , 2007.
• C. Rambabu. I. Chakrabarti and A. Mahanta «Flooding-based watershed algorithm and its prototype hardware architecture» IEE Proc.-Vis. Image Signal Process, Volume. 151. Number. 3, June 2004.
• Carolina A. Moreira Kulak, David W. Dempster «Bone histomorphometry: a concise review for endocrinologists and clinicians», Arq Bras Endocrinol Metab, 2010.
• DO Minh Chau « Evaluation de la segmentation d’images », Institut de la francophonie pour l’informatique, Vitnam, 2007.
• Eric Lespessailles, Christine Chappard, Nicolas Bonnet, Claude Laurent Benhamou, «Imaging techniques for evaluating bone microarchitecture». Elsevier, Revue du Rhumatisme 73 (2006) 435443.
• G. F. Zaki. R. A. Girgis. W. W. Moussa , and W.R. Gobran. Junior Member. IEEE «Using HW/SW Co-design to Implement an Embedded Face Recognition/ Verification System on an FPGA».
• H.S.Sheshadri and A. Kandaswamy «Detection of Breast Cancer Tumor based on Morphological Watershed Algorithm» Department of ECE. PSG College of Technology. Coimbatore.
• Hye Suk Kim, Hyo Sun Yoon, Nguyen Dinh Toan and Guee Sang Lee «Anisotropic Diffusion Transform based on Directions of Edges» Korea IEEE 8th International Conference on Computer and Information Technology Workshops.
• H.LOUKIL HADJ KACEM and M.S BOUHLEL «Elaboration d’une Quantification Semilogarithmique pour l’Amlioration de la Norme de Compression JPEG», 5th International Conference: Sciences of Electronic. Technologies of Information and Telecommunications March 2009, TUNISIA.
• K.Karantzalos. D. Argialas «Improving edge detection and watershed segmentation with anisotropic diffusion and morphological levellings» Remote Sensing Laboratory, School of Rural and Surveying Engineering (SRSE), National Technical University of Athens (NTUA), Athens. Greece June 2006.
• Wafa Abid. Khaled Taouil. Tarek Rebai , Med Salim Bouhlel «Segmentation d’image par seuillage d’histogramme application l’analyse des coupes histologiques osseuses». 3rd International Conference: Sciences of Electronic. Technologies of Information and Telecommunications, Tunisia, 2005.
• Li Gao, Shuyuan Yang, Jie Xia, Junli Liang . Yuhua, Qin «A new marker-based watershed algorithm», China 2006
• Luc Vincent and Pierre Soille ” Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations ” 0162 ¡ 8828=91=0600 ¡ 058301:0001991IEEE
• N. Smaoui Zghal. A. Yangui Jammoussi. D. Sellami Masmoudi «Implementation of a watershed based image segmentation system in Virtex II pro platform» DTIS 2009. Cairo. Egypt .
• M.-H. Lafage-Proust «Peut-on optimiser l’evaluation du statut osseux chez l’insuffisant renal par les explorations complementaires ?». Flammarion Mdecine- Sciences-Actualits nephrologiques 2009.
• P. Dillinger. J. F. Vogelbruch. J. Leinen. S. Suslov. R.Patzak. H. Winkler. and K. Schwan «FPGA-Based Real-Time Image segmentation for Medical Systems and Data Processing» IEEE Transactions on nuclear Science VOL. 53. NO. 4. August 2006
• S.Chen1. J.Luo1. Z.Shen1. X.Hu1. L. Gao1 ”Segmentation of Multi-spectral Satellite Images Based on Watershed Algorithm” Institute of Remote Sensing Application. Chinese Academy of Scienses. Beijing. 100101. China 2008
• S.Chabrier. H.Laurent. C.Rosenberger, “Supervised evaluation of synthetic and real contour segmentation results”.14 th European Signal Processing Conference. Italy.2006
• Accelerate Software Algorithms on FPGAs, available at www.impulseaccelerated.com/eval/index
• Computer Vision Group, available at www.eecs.berkeley.edu/Research/Projects/CS/vision /grouping/segbench/
• Xcell Journal, available at www.Xilinx.com
• Xiutao Shi . X. Sherry Liu . XiangWang . X. Edward Guo. Glen L. Niebur « Effects of trabecular type and orientation on microdamage susceptibility in trabecular bone» .Elsevier. Bone 46 (2010)
• Xun Wang and Jian-Qiu Jin «An Edge Detection Algorithm Based on Improved CANNY Operator» College of Computer and Information Engineering Zhejiang Gongshang University. Hangzhou. 310035. China 0-7695-2976-3/07 5:002007 IEEE

Index Terms

Key words