Dedicated Hardware for Real-Time Computation of Second-Order Statistical Features for High Resolution Images
We present a novel dedicated hardware system for the extraction of second-order statistical features from high-resolution images. The selected features are based on gray level co-occurrence matrix analysis and are angular second moment, correlation, inverse difference moment and entropy. The proposed system was evaluated using input images with resolutions that range from 512(512 to 2048(2048 pixels. Each image is divided into blocks of user-defined size and a feature vector is extracted for each block. The system is implemented on a Xilinx VirtexE-2000 FPGA and uses integer arithmetic, a sparse co-occurrence matrix representation and a fast logarithm approximation to improve efficiency. It allows the parallel calculation of sixteen co-occurrence matrices and four feature vectors on the same FPGA core. The experimental results illustrate the feasibility of real-time feature extraction for input images of dimensions up to 2048(2048 pixels, where a performance of 32 images per second is achieved.
KeywordsFeature Vector Input Image Image Block Very Large Scale Integration Memory Bank
Unable to display preview. Download preview PDF.
- 5.Iivarinen, J., Heikkinen, K., Rauhamaa, J., Vuorimaa, P., Visa, A.: A Defect Detection Scheme for Web Surface Inspection. Int. J. Pat. Rec. Artif. Intell., 735–755 (2000)Google Scholar
- 7.Iakovidis, D.K., Maroulis, D.E., Karkanis, S.A., Flaounas, I.N.: Color Texture Recognition in Video Sequences Using Wavelet Covariance Features and Support Vector Machines. In: Proc. 29th EUROMICRO, Antalya, Turkey, September 2003, pp. 199–204 (2003)Google Scholar
- 8.Wei, C.-H., Li, C.-T., Wilson, R.: A Content-Based Approach to Medical Image Database Retrieval. In: Ma, Z. (ed.) Database Modeling for Industrial Data Management: Emerging Technologies and Applications. Idea Group Publishing, USA (2005)Google Scholar
- 10.Ba, M., Degrugillier, D., Berrou, C.: Digital VLSI Using Parallel Architecture for Co-occurrence Matrix Determination. In: Proc. Int. Conf. on Acoustics, Speech, and Signal Proc., vol. 4, pp. 2556–2559 (1989)Google Scholar
- 11.Heikkinen, K., Vuorimaa, P.: Computation of Two Texture Features in Hardware. In: Proc. 10th Int. Conf. Image Analysis and Processing, Venice, Italy, September 1999, pp. 125–129 (1999)Google Scholar
- 12.Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press, San Diego (1999)Google Scholar
- 14.Hennesy, J.L., Patterson, D.A.: Computer Architecture, A Quantitative Approach. Morgan Kaufmann, San Francisco (2002)Google Scholar