Analysis of Edge Detection Operators on Fiber Optic Inspection Microscope Connector end face Image Profiles
|International Journal of Electronics and Communication Engineering|
|© 2015 by SSRG - IJECE Journal|
|Volume 2 Issue 7|
|Year of Publication : 2015|
|Authors : Adetiba O.E , Bajoga B.G.and Sani S. M|
How to Cite?
Adetiba O.E , Bajoga B.G.and Sani S. M, "Analysis of Edge Detection Operators on Fiber Optic Inspection Microscope Connector end face Image Profiles," SSRG International Journal of Electronics and Communication Engineering, vol. 2, no. 7, pp. 30-33, 2015. Crossref, https://doi.org/10.14445/23488549/IJECE-V2I7P110
This research was aimed at determining the most suitable image detection operator to be used on a fiber optic connector endface profile from a fiberscope. The contemporary edge detection techniques analyzed are the Canny, Sobel, Prewitt, Laplacian of the Gaussian (LoG), Roberts and Frei-Chen operators using the Matlab® 2013 script. Histogram equalization was implemented on the connector profiles at the onset to improve the performances of the operators. By using the “task-based” empirical evaluation whose figure of merit is the sum total of edges detected, the Canny operator emerged the best candidate technique after yielding the maximum value of 139.1 average detections per section (adps) closely followed by the Laplacian of the Gaussian (LoG) with 103.2 average detections per section. The Sobel, Prewitt, Roberts and Frei-chen operators yielded 49.3, 49.57, 45.19 and 50.98 average detections per profile section respectively
histogram equalization, edge detection, image processing, Matlab
Baghai, W. (2013). 'Basic image processing: edge detection'. Retrieved from http://www.dip.ee.uct.ac.za/~nicolls/lectures/eee401f/03_edgedet_notes_2up.pdf 26/06/ 2013
Barghavi, G. (2008). A progressive approach to Feedback-Controlled edge Detection using Boolean Derivatives (pp. 56-60). Denmark: Proquest Inc.
Ian, T. Y. (1998). Fundamentals Of Image Processing. Retrieved from http://www.tnw.tudelft.nl/en/about-faculty/departments/imaging-physics/research/researchgroups/quantitative-imaging/courses/ on 26/04/2014, pp. 1-3
Jayaraman, S., Esakkirajan, S. & Veerakumar, T. (2011). Digital Image Processing (pp. 2-70). India, New Delhi: Tata McGraw-Hill Education.
Li, T. & Jean, J. (2013). Digital Signal Processing: Fundamentals and Application (pp. 706-720). Massachusetts, USA: Academic Press,.
Maria, P. & Panagiota, B. (1999). Image Processing: The Fundamentals (pp. 125-127). New Jersey, USA: John Wiley & Sons.
Paul, W. & Derek, M. (2001). Machine vision Algorithms in Java: Techniques and Implementation (pp.224-300). London: Springer-Verlage
Rashmi, Mukesh, K., &Rohini, S. (2013). Algorithm and Technique on various edge detection: A survey. Signal & Image Processing International Journal, Vol.4 ( 3), pp 65-75.
Trucco, E. & Verri, A. (1998). Introductory techniques for 3D computer Vision (pp 16-26, 68-91, 248-275). New Jersey, USA: Prentice Hall.