Improved active contour modelling for isolating different hues in infrared thermograms
Thermograms are widely used in industries and medicine for quality assessment and diagnostics. Thermogram analysis involves isolating desirable Regions of Interest (RoIs) and characterizing them in terms of physical parameters. Conventionally, image segmentation techniques are developed to extract a specific Region of Interest. However, an efficient algorithm that could segment any desired Region of Interest is yet to be developed. In this study, an efficient color image segmentation technique for isolating RoIs (in infrared thermograms) is developed by using Improved Active Contour Modeling (I-ACM). Two different techniques namely thresholding and region growing, have been used for mask selection in order to increase the segmentation ability of the algorithm. The performance of the proposed techniques is measured in terms of error and computational complexity. A user friendly GUI has been also developed for computer-aided analysis.
Keywordsactive contour modeling mask selection thresholding region growing
Unable to display preview. Download preview PDF.
- 1.Maldague, X., Larbi, W.B., Bendada, A.H., Grenier, M., Ibarra-Castanedo, C., Klein, M., Saboktakin, A., and Ziadi, A, Recent research advances with industry transfer in infrared technology, Adv. Infrared Technol. Appl./Commun. Abstr.,, Florence, September 2009.Google Scholar
- 3.Selvarasu, N., Nachiappan, A., and Nandhitha, N.M, Effective representation of non-uniformity and asymmetry in breast thermographs using statistical parameters on histograms of wavelet coefficients for cancer detection, Eur. J. Sci. Res., 2012, pp. 10–19.Google Scholar
- 4.Selvarasu, N., Vivek, S., and Nandhitha, N.M, Performance evaluation of image processing algorithms for automatic detection and quantification of abnormality in medical thermograms, Proc. Int. Conf. Comput. Intell. Multimedia Appl. ICCIMA, December 13-15, 2007, pp. 388–393.Google Scholar
- 5.Ibarra-Castanedo, C., Avdelidis, N.P., Grinzato, E., Bison, P.G., Marinetti, S., Cochior-Plescanu, C., Bendada, A.H., and Maldague, X, Delamination detection and impact damage assessment of GLARE by active thermography, Int. J. Mater. Prod. Technol., 2011, vol. 41, nos. 1/2/3/4, pp. 5–16.CrossRefGoogle Scholar
- 8.Genest, M, Image processing for automated flaw detection in pulsed thermography, ASPN, 2009, pp. 1–5.Google Scholar
- 9.Yasaswi, V., Keerthi, S., Jainab Begum, S., Krishna Sravan, Y., amd Sridhar, B., Infrared thermal image segmentation for fault detection in electrical circuits using watershed algorithm, Int. J. Eng. Trends Technol. (IJETT), vol. 21, no. 9, pp. 423–429.Google Scholar
- 10.Khamisan, N., Ghazali, K.H., and Zin, A.H.M., A thermograph image extraction based on color features for induction motor bearing fault diagnosis monitoring, ARPN J. Eng. Appl. Sci., 2015, vol. 10, no. 22, pp. 17095–17101.Google Scholar
- 11.Laib dit leksir, Y., Bouhouche, S., Bendjama, H., and Balaska, Ad., Detection of defects in infrared thermal images by using the Gradient Vector Flow active contour, http://www.ndt.net/article/defektoskopie2009/ papers/Laib-6.pdf.2009.Google Scholar
- 12.Jen-Hong Tan, E.Y.K. Ng, and Rajendra Acharya U., Detection of eye and cornea on IRthermograph using genetic snake algorithm, 9th Int. Conf. Quant. Infrared Thermogr., Krakow, Poland, July 2–5, 2008.Google Scholar
- 13.Bilodeau, G.A., Ghali, R., Desgent, S., and Langlois, P, Where is the rat? Tracking in low contrast thermographic images, IEEE Comput. Soc. Conf. Comput. Vision Pattern Recognit. Workshops (CVPRW), 2011, pp. 55–60.Google Scholar