Edge detection : wavelets versus conventional methods on DSP processors

• Autorzy: Abdel-Qader I. M. , Maddix M. E.
• Języki publikacji: EN

Abstrakty

EN

Edge detection is a cornerstone in any computer, robotic or machine vision system. Real time edge detection is a pre-process to many critical applications, such as assembly line inspection and surveillance. Wavelets-based algorithms are replacing traditional algorithms, especially the Haar wavelet because of its simplicity. The Haar algorithm uses a multilevel decomposition to produce images edges corresponding to high frequency wavelet coefficients. In this paper, a real time edges detection algorithm based on Haar is analyzed and compared to conventional edge detectors. Other implemented and compared algorithms are the traditional Prewitt algorithm, and, from a newer generation, the Canny algorithm. The real implementation of all algorithms is accomplished using TI TMS320C6711 card. In case of Haar, the multilevel decomposition improves the results obtained with noise images. The results show that the Haar-based edge detector has a low execution time with accurate edges results, and thus represent a suitable algorithm for on-line vision system applications. Canny has produced the thinnest edges, but is not suitable for time processing using the 6711, and falls short in edge results compared to the Haar results. The Wavelet-based algorithm has outperformed other edges detectors.

Słowa kluczowe

EN

Haar wavelets; edge detection; DSP processor

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2005
• Tom: Vol. 14, No. 1
• Strony: 83--101
• Opis fizyczny: Bibliogr. 22 poz., rys., tab., wykr.

Twórcy

autor

Abdel-Qader I. M.

• Electrical and Computer Engineering Departament, College of Engineering and Applied Sciences, Western Michigan University, Kalamazoo, MI 49008

autor

Maddix M. E.

• Electrical and Computer Engineering Departament, College of Engineering and Applied Sciences, Western Michigan University, Kalamazoo, MI 49008

Bibliografia

• [1] Blicher A.: Edge Detection and Geometric Methods in Computer Vision. Technical Report CS-851041, Stanford University, Department of Computer Science, 1985.
• [2] Canny J.: A computational approach to edge detection. IEEE Trans. on PAMI, 8(6), 769-798, 1986.
• [3] Erlebacher G., Hussaini M.Y., Jameson L.M. (Eds.): Wavelets: Theory and Applications. Oxford University Press, Inc., New York, 1996.
• [4] Castleman K. R.: Digital Image Processing. Prentice Hall, New Jersey, 1996.
• [5] Alzahrani F., Chen T.: A real-time edge detector: algorithm and VLSI architecture. Real-Time Imaging, 3(5), 363-378, 1997.
• [6] Rajeev S., Ramon V., Reena S.: Edge Detection: Conventional Operators vis-a-vis wavelets. Proc. of SPIE BIOS Conf., San Jose, CA 1997.
• [7] Heath M., Sarka S., Sanocki T., Bowyer K.: Comparison of edge detectors: a methodology and initial study. Journal of Commputer Vision and Image Understanding, 69(1), 38-54, 1998.
• [8] Lacassagne L., Lohier F., Garda P.: Real time execution of optimal edge detectors on RISC and DSP processors. Proc. of IEEE ICASSP, Seattle, 1998.
• [9] Lee C., et al.: An efficient ASIC architecture for real time edge detection. IEEE Trans. on Circuits and Systems, 36(10), 1350-1359, 1998.
• [10] Hajj H., Nguyen T., Chin R.: 2D multirate bayesian framework for multiscale feature detection. Journal of Mathematical Imaging and Vision, Volume 8, December, 1999.
• [11] Gevers T., Stokman H.: Reflectance Based Edge Classification. Nouboud F. (Ed.): Visual Interface, Canadian Image Processing and Pattern Recognition Society, 25-32, 1999.
• [12] Bachman G., Narici L., Beckenstein E.: Fourier and Wavelet Analysis. Springer-Verlag. New York, Inc., 2000.
• [13] Kehtarnavaz N., Simsek B.: DSP System Design: Using the TMS320C6000, Prentice Hall, 2000.
• [14] Kehtarnavaz N., Simsek B.: C6X-Based Digital Signal Processing, Prentice Hall, 2000.
• [15] Dahnoun N.: Digital Signal Processing Implementation using the TMS320C 6000TM Platform, Prentice Hall, 2000.
• [16] TMS320C6000 Imaging Developer’s kit (ID K ) User’s Guide, Texas Instruments, Dallas, Texas, 2000.
• [17] TMS320C6000 Imaging Developer’s kit (IDK) Programmer’s Guide, Texas Instruments, Dallas, Texas, 2000.
• [18] Meer P., Georgescu B.: Edge detection with embedded confidence. IEEE Trans. on PAMI, 23(12), 1351-1365, 2001.
• [19] Chassaing R.: DSP Applications Using C and the Tms320C6X Dsk (Topics in Digital Signal Processing) John Wiley, New York, NY, 2002.
• [20] Draper B., Beveridge R., Bdhm W., Ross C., Chawathe M.: Implementing image applications on FPGA. Proc. of Int. Conf. on Pattern Recognition, Quebec City, August, 2002.
• [21] Abdel-Qader I., Maddix M.: Real-Time Edge Detection Using TMS320C6711 DSP. Proc. of the IEEE Electro/Information Technology Conference, Milwaukee, WI, 2004.
• [22] Evans B.: Notes on Texas Instruments Processors, http://www.ece.utexas.edu/~bevans/courses/realtime/lectures/01_Architecture/texaslnstruments.html ; 2004.