Real Time Object Visual Inspection Based On Template Matching Using FPGA

SANDHYA P; OMKAR NAIDU V

doi:https://doi.org/10.14445/22315381/IJETT-V4I8P146

Research Article | Open Access | Download PDF

Volume 4 | Issue 8 | Year 2013 | Article Id. IJETT-V4I8P146 | DOI : https://doi.org/10.14445/22315381/IJETT-V4I8P146

Real Time Object Visual Inspection Based On Template Matching Using FPGA

SANDHYA P , OMKAR NAIDU V

Citation :

SANDHYA P , OMKAR NAIDU V, "Real Time Object Visual Inspection Based On Template Matching Using FPGA," International Journal of Engineering Trends and Technology (IJETT), vol. 4, no. 8, pp. 3521-3526, 2013. Crossref, https://doi.org/10.14445/22315381/IJETT-V4I8P146

Abstract

In similarity measure, normalized cross - correlation has found application in broad range of in image processing. This work proposes a novel technique aimed at improving the performance of exhaustive template matching based on NCC. An effective sufficient condition, capable of rapidly pruning those cross correlation score with respect to the current best candidate, can be obtained exploiting an upper bound of the NCC function. In this work Real - Time FPGA accelerates time consuming NCC template matching was presented. With this type of template matching we can inspect any industrially manufactured product on its production line with high accuracy, with increased speed of matching where huge amount of production is concerned. We got Good results by reducing s earch window size by reducing complexity in matching template

Keywords

FPGA, Normalized cross-correlation, Search window, Template I

References

[1] CHIN, AUTOMATED VISUAL INSPECTION: A SURVEY IEEE PAMI 1982
[2] S. C. Wang, "Human reliability in visual inspection," Quality, Sept. 1974.
[3] Tsai, D. - M., Chiang, C. - H., 2002. Rotation - invariant pattern matching using wavelet decomposition. Pattern Recognition Lett. 23, 191±201.
[4] Wakahara, T., Kimura, Y., Tomono, A., 2001. Affine - invariant recognition of gray - scale characte rs using global affine transformation correlation. IEEE Trans. Pattern Anal. Machine Intell. 23, 384±395.
[5] Kim, J.H., Cho, H.S., Kim, S., 1996. Pattern classification of solder joint images using a correlation neural network. Eng. Appl. Artif. Intell. 9, 655±669.
[6] Cai, X.Y., Kvasnik, F., Blore, R.W., 1994. Wafer fault measurement by coherent optical pro cessor. Appl. Opt. 33, 4487±4496.
[7] Stefano,”An Efficient Algorithm for Exhaustive Template Matching based on Normalized cross correlation”, IEEE ICIAP03
[8] Xiaotao Wang, Xingbo Wang, "FPGA Based Parallel Architectures for Normalized Cross - Correlation ", The 1st International Conference on Information Science and Engineering (ICISE2009), pp. 225 – 229
[9] Nisheeth Gupta, Nikhil Gupta, "A VLSI Architecture for Image Registration in Real Time," IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYS TEMS, VOL. 15, NO. 9, SEPTEMBER 2007