Leveraging Graphics Hardware for an Automatic Classification of Bone Tissue
- 1.1k Downloads
Zernike moments are fundamental digital image descriptors used in many application areas due to their good properties of orthogonality and rotation invariance, but their computation is too expensive and limits its application in practice, overall when real-time constraints are imposed. The contribution of this work is twofold: Accelerate the computation of Zernike moments using graphics processors (GPUs) and assess its expressiveness as descriptors of image tiles for its subsequent classification into bone and cartilage regions to quantify the degree of bone tissue regeneration from stem cells. The characterization of those image tiles is performed through a vector of features, whose optimal composition is extensively analyzed after testing 19 subsets of Zernike moments selected as the best potential candidates. Those candidates are later evaluated depending on its ability for a successful classification of image tiles via LDA, K-means and KNN classifiers, and a final rank of moments is provided according to its discriminative power to distinguish between bone and cartilage. Prior to that study, we introduce a novel approach to the high-performance computation of Zernike moments on GPUs. The proposed method is compared against three of the fastest implementations performed on CPUs over the last decade using recursive methods and the fastest direct method computed on a Pentium 4, with factor gains up to 125 ×on a 256 ×256 image when computing a single moment on a GPU, and up to 700 ×on a 1024 ×1024 image when computing all repetitions for a given order using direct methods.
KeywordsBone tissue classification Digital image descriptors Zernike moments Graphics processors
This work was supported by the Junta de Andalucía of Spain, under Project of Excellence P06-TIC-02109. We want to thank Silvia Claros, José Antonio Andrades and José Becerra from the Cell Biology Department at the University of Malaga for providing us the biomedical images used as input to our experimental analysis.
- 2.Andrades, J.A., Santamaría, J., Nimni, M., Becerra, J.: Selection, amplification and induction of a bone marrow cell population to the chondroosteogenic lineage by rhOP-1: An in vitroand in vivostudy. Int. J. Dev. Biol. 45, 683–693 (2001)Google Scholar
- 5.Fisher, R.: The statistical utilization of multiple measurements. Ann. Eugenics 8, 376–386 (1938)Google Scholar
- 6.Fix, E., Hodges, J.: Discriminatory Analysis – Nonparametric Discrimination: Consistency Properties. Project Number 21-49-004, USAF School of Aviation Medicine4, University of California, Berkeley, Randolph Field, Texas (USA) (1951)Google Scholar
- 7.GPGPU: General-Purpose Computation Using Graphics Hardware (2009) http://www.gpgpu.org
- 11.MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, vol.1, pp. 281–297. University of California Press (1967)Google Scholar
- 15.Nvidia: CUDA Home Page (2009) http://developer.nvidia.com/object/cuda.html
- 17.Pratt, W.: Digital Image Processing. Fourth Edition. Ed. Wiley-Interscience (2007)Google Scholar
- 19.Rao, C.: Linear Statistical Inference and its Applications, second edn. Wiley, New York (2002)Google Scholar
- 24.Tuceryan, M., Jain, A.K.: Texture Analysis. World Scientific Publishing Co (1998)Google Scholar