reflection reduction using super resolution technique for quality inspection of highly reflective metal
Madhura A. Limaye,P.B.Chopade ,P M Patil
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:5 Issue:3 Year: 22 March,2015 Pages:384-393
Abstract
In case of manufacturing industries, quality inspection plays very important role. This process can be performed manually. But manual inspection can lead to number of errors. It is a risky process. It thoroughly depends on the patience of inspector. Therefore to automate the industrial inspection nowadays image enhancement techniques are being rapidly used. In quality inspection all dimensions of mechanical object are inspected. When machine products are manufactured, defect detection is also performed in the process of quality inspection. In case of metal surface which is having high reflection coefficient, defect detection becomes difficult. This reflection can act as a noise in image. Because of this reflection in image edge detection cannot be performed easily. Hence for processes like edge detection and defect detection, reflection reduction is highly required. The goal of proposed method is to design a right system for quality inspection to beat problem of reflection from metal body. In proposed algorithm super resolution technique is used for reduction of reflection. Wavelet transform is used to perform hard thresholding and soft thresholding. Quality evaluation is performed with the help of parameters like PSNR, MSE, SSIM and correlation.
Kewords
Reflection reduction, wavelet transform, hard thresholding, soft thresholding, super resolution etc.
Reference
[1] Pedro de Almeida, “A knowledge-based approach to the iris segmentation problem”, Image and Vision Computing, july 2009. [2] Zhang Xue-wu, Ding Yan-qiong, Lv Yan-yun, Shi Ai-ye, and Liang Rui-yu, “A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM”, Expert Systems with Applications 2010. [3] Anis Farihan Mat Raffei, Hishammuddin Asmuni, Rohayanti Hassan and Razib M. Othman,” Fusing the line intensity profile and support vector machine for removing reflections in frontal RGB color eye images”, Information Sciences,2014 [4] Dae Sik Jeong, Jae Won Hwang, Byung Jun Kang, Kang Ryoung Park, Chee Sun Won, Dong-Kwon Park and Jaihie Kim, “A new iris segmentation method for non-ideal iris images”, Image and Vision Computing, April 2009. [5] P. P. Gajjar and M. V. Joshi , “New-Learning Bases Super-resolution:Use of DWT and IGMRF Prior”, IEEE Transactions on Image Processing, Vol. 15, No. 5, pp. 1201-1213, May 2010. [6] C. V. Jiji, M. V. Joshi, and S. Chaudhari, “Single-frame image super-resolution using learned wavelet coefficients,” Int. J. Imag. Syst.Technol., vol. 14, no. 3, pp. 105–112, 2004. [7] R.Y. Tsai and T.S. Huang, “Multiple frame image restoration and registration,” in Advances in Computer Vision and Image processing.Greenwich, CT:JAI Press Inc., 1984, pp. 317-339. [8] M. Irani and S. Peleg, “Motion analysis for image enhancement resolution, occlusion, and transparency,” J. Visual Commun. Image Represent., vol.4, pp. 324-335, Dec. 1993. [9] H. Ji and C. Fermullar, “Robust wavelet-based Super-resolution Reconstruction”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No.4, pp. 649-660, April 2009. [10] N. Nguyen and N.P. Milanfar, “A Wavelet-Based Interpolation-Restoration Method for Super-resolution,” Circuits, Systems, and Signal Processing, vol. 19, pp. 321-338, 2000. [11] G. Anbarjafari and H. Demirel, “Image Super Resolution Based on Interpolation of Wavelet Domain High Frequency Sub-bands and the Spatial Domain Input Image”, ETRI Journal, Vol. 32, No.3, pp. 390-394, June 2010. [12] P B Chopade and P M Patil,”Design of dydic-integer coefficient based bi_orthogonal wavelet filters for image super-resolution using image sub-pixel image”ICTACTJournals,vol. 04,Issue 04,May 2014.
