Spectral sensitivity design for maximum color separation in artificial color systems

• Autorzy: Heidary K. , Caulfield J.
• Języki publikacji: EN

Abstrakty

EN

Engineers have utilized spectral information and have steadily improved its applications in imaging systems for more than a century. The course of technological developments in color imaging has been dictated by system improvements measured by their efficacy for direct human consumption. It seems reasonable to us to try to emulate nature and boost capabilities of machine vision systems by optimizing the way in which they exploit spectral information. This is a two-step process: First step involves using a few spectrally broad detectors to compress the information content of the scene and the second step constructs spectral discriminants for image segmentation based on a small number of spectrally generated features assigned to each pixel. In animals the discriminant value is attributed to the object as what is called color. Previous papers have concentrated on the final segmentation step. Here we show a straightforward way to design application-specific spectral sensitivity functions to improve image segmentation. The resulting functions can be used for reliable recognition of objects in a hyperspectral image in real-time. These functions can also be used to design task-specific specialized cameras that can outperform current hyperspectral systems in terms of sensitivity, size, power consumption, robustness, price, and complexity.

Słowa kluczowe

EN

spectral sensitivity; artificial color; multi/hyperspectral; classification; image segmentation

PL

klasyfikacja; segmentacja obrazu

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2007
• Tom: Vol. 12, no 2
• Strony: 3--15
• Opis fizyczny: Bibliogr. 22 poz., wykr.

Twórcy

autor

Heidary K.

autor

Caulfield J.

• Department of Electrical Engineering, Alabama A&M University, PO Box 702, Normal, AL 35762, USA,

Bibliografia

• [1] A. R. Parker, 515 Million years of structural colour, Journal of Optics A: Pure and Applied Optics, vol. 2, pp. 15-28, 2000.
• [2] A. R. Parker, The Cambrian light switch, Biologist, vol. 46, No. 1, pp. 26-30, 1999.
• [3] A. R. Parker, Colour in Burgess Shale animals and the effect of light on evolution in the Cambrian, Proceedings of the Royal Society of London: Biological Sciences, vol. 265, pp. 967-972, 1998.
• [4] G. H. Jacobs, Color Vision, Academic Press, New York, 1981.
• [5] 5. J. N. Lythgoe, J. C. Partridge, Visual Pigments and the Acquisition of Visual Information, Journal of Experimental Biology, vol. 146, pp. 1-20, 1989.
• [6] H. J. Caulfield, Artificial Color, Neurocom-puting, vol. 51, pp. 463-465, 2003.
• [7] H. J. Caulfield, J. Fu, S.M. Yoo, Artificial Color image logic, Information Science, vol. 167, pp. 1-7, 2004.
• [8] K. Heidary, H. J. Caulfield, Discrimination among similar looking, noisy color patches using Margin Setting, Optics Express, Journal of Optical Society of America, vol. 15, No. 1, pp. 62-75, 2007.
• [9] H. J. Caulfield, Nature's alternative to hyper spectral imaging and why nature is right, SPIE, vol. 4787, pp. 132-136, 2002.
• [10] K. Heidary, H. J. Caulfield, Color Classification using Margin-Setting with Ellipsoids, Submitted to Journal of Electronic Imaging, 2007.
• [11] H. J. Caulfield, K. Heidary, Exploring Margin Setting for Good Generalization in Multiple Class Discrimination, Journal of Pattern Recognition, vol. 38, Issue 8, pp. 1225-1238, 2005.
• [12] K. Heidary, H. J. Caulfield, Application of supergeneralized matched filters to target classification, Applied Optics, vol. 44, No. 1, pp. 47-54, 2005.
• [13] K. Heidary, H. J. Caulfield, Spectral sensitivity design for optical sensors, Submitted to Journal of Electronic Imaging.
• [14] D. H. Brainard, Hyperspectral Image Data, http://color.psych.ucsb.edu//hyperspectral/
• [15] S.P. Mohanty, Digital Watermarking: A tutorial Review, IEEE Trans. Image Process., vol. 6, pp.1673-1687, 1997.
• [16] N. Nikolaid and I. Pitas, Copyright Protection of images using Robust Digital Signatures, IEEE Trans.Signal Processing, vol. 4, pp.2168-2171, 1996.
• [17] N. Nikolaids and I. Pitas, Robust Image Watermark in the Spatial Domain, ACM Trans. Signal Process., vol. 66, pp. 385-403, 1998.
• [18] F.A.P Petitcolas, R. J. Anderson & M. G. Kuhn, Attacks on copyright making sys. 2nd Internal. Workshop on Information Hiding, Springer Lect. Notes in Computer Science, vol. 1525, pp. 219-239, 1998.
• [19] C. Shieh, H. Huang, F. Wang, and J. Pan, Genetic Watermark based on transform-domain techniques, Pattern Recog., vol. 37, pp. 555-565, 2004.
• [20] W. Zhu, Z. Xiong, Y. Zhang, Multiresolution Watermarking for Images and Video, IEEE Trans. Circuits & Systems for Video Technology, vol.9, pp.545-550, 1999.
• [21] W. Zhu, Z. Xiong, Y. Zhang, Multiresolution Watermarking for Images and Video: A Unified Approach, Proc. IEEE Internal. Conf. Image Process., 1999, vol.1, pp.465-468.
• [22] http://www.cosyt.sbg.ac.at/ pmeerw/Watermarking/source/