Abstract
Grey Level Co-occurrence Matrix (GLCM), one of the best known tool for texture analysis, estimates image properties related to second-order statistics. These image properties commonly known as Haralick texture features can be used for image classification, image segmentation, and remote sensing applications. However, their computations are highly intensive especially for very large images such as medical ones. Therefore, methods to accelerate their computations are highly desired. This paper proposes the use of programmable hardware to accelerate the calculation of GLCM and Haralick texture features. Further, as an example of the speedup offered by programmable logic, a multispectral computer vision system for automatic diagnosis of prostatic cancer has been implemented. The performance is then compared against a microprocessor based solution.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M.A. Roula, J. Diamond, A. Bouridane, Paul Miller, and A. Amira, “A multispectral computer vision system for automatic grading of prostatic neoplasia,” in IEEE International Symposium on Biomedical Imaging, 2002.
R.M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification.” IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, 1973.
R.W. Conners and C.A. Harlow, “A Theoretical comaprison of texture algorithms.” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 2, pp. 204–222, 1980.
R.O. Duda, P.E. Hart, and D.G. Stork, “Pattern classification.” Willey-Interscience, 2nd edition, 2001.
A. Sharma, Programmable logic Handbook, PLDs, CPLDs and FPGAs. McGraw-Hill, 1998.
A. Baraldi and F. Parmiggiani, “An investigation of the textural caracteristics associated with gray level co-occurrence matrix statistical parameters.” IEEE Trans. on Geosciences and Remote Sensing, vol. 33, no. 2, pp. 293–304, 1995.
L.K. Soh and T. Tsatsoulis, “Texture analysis of SAR sea ice imagery using grey-level co-occurrence matrices.” IEEE Trans. on Geosciences and Remote Sensing, vol. 37, no. 2, pp. 780–795, 1999.
D. Smutek et al., “Image texture analysis of sonograms in chronic inflammations of tyriod gland.” Ultrasound in Med. and Biol., vol. 29, no. 11, pp. 1531–1543, 2003.
D.G. Vince et al., “Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images.” Computerized Medical Imaging and Graphics, vol. 24, pp. 221–229, 2000.
URL: http://www.celoxica.com.
URL: http://www.xilinx.com.
K. Wikantika, A.B. Harto, and R. Tateishi, “The use of spectral and textural features from Landsat TM image for land cover classification in mountainous area,” in Proceedings of the IECL Japan workshop, 2001.
URL: http://www.spss.com.
H.H. Harman, “Modern factor analysis.” 3rd ed., University of Chicago Press, Chicago, 1976.
M.M. Tatsuoka, Multivariate Analysis. John Wiley and Sons, Inc, New York, 1971.
M.A. Tahir, M.A. Roula, A. Bouridane, F. Kurugollu, and A. Amira, “An FPGA based co-processor for GLCM texture features measurement,” in Proceedings of the 10th IEEE International Conference on Electronics, Circuits and Systems, 2003.
M. A. Tahir, A. Bouridane, F. Kurugollu, and A. Amira, “An FPGA based coprocessor for calculating grey level cooccurrence matrix,” in Proceedings of the 46th IEEE International Midwest Symposium on Circuits and Systems, 2003.
Author information
Authors and Affiliations
Corresponding author
Additional information
Muhammad Atif Tahir received a BE degree in Computer Systems Engineering from NED University of Eng. and Tech. Karachi, Pakistan, and an MSc in Computer Engineering from KFUPM, Dhahran, Saudi Arabia. He is currently a PhD research student in School of Computer Science at Queen’s University Belfast, UK. His main research interests are Custom Computing using FPGAs, Image/Signal Processing, Pattern Recognition, QoS Routing and Optimization heuristics.
Ahmed Bouridane obtained an “Ingéniorat d’Etat” degree in Electronics from the National Polytechnic School of Algiers “ENP”, an MPhil degree in VLSI design for Signal Processing from the University of Newcastle Upon Tyne (UK) and a PhD degree in Computer Vision from the University of Nottingham (UK). Dr A Bouridane held several positions in R&D before joining Queen’s University Belfast where he is now a Reader in Computer Science. His research interests are in High Performance Image/Signal Processing, Image/Video Watermarking, Custom Computing using FPGAs, Computer Vision and High Performance Architectures for Image/Signal Processing.
Fatih Kurugollu received his B.Sc, M.Sc. and Ph.D degree in computer science from the Istanbul Technical University, Istanbul, Turkey in 1989, 1994 aand 2000, respectively. He is currently a lecturer in Computer Science at Queen’s University, Belfast (UK). His research interest include soft computing for image and video object segmentation, hardware architectures for image and video applications and image watermarking.
Rights and permissions
About this article
Cite this article
Tahir, M.A., Bouridane, A. & Kurugollu, F. An FPGA Based Coprocessor for GLCM and Haralick Texture Features and their Application in Prostate Cancer Classification. Analog Integr Circ Sig Process 43, 205–215 (2005). https://doi.org/10.1007/s10470-005-6793-2
Issue Date:
DOI: https://doi.org/10.1007/s10470-005-6793-2