The Community for Technology Leaders
RSS Icon
Issue No.12 - December (2008 vol.30)
pp: 2218-2228
Yi-Chin Fang , National Kaohsiung First University of Science, Institute of Engineering Science and Technology, Kaohsiung City
Bo-Wen Wu , National Kaohsiung First University of Science, Institute of Engineering Science and Technology, Kaohsiung City
Thermal imaging is an important technology in both national defense and the private sector. An advantage of thermal imaging is its ability to be deployed while fully engaged in duties, not limited by weather or the brightness of indoor or outdoor conditions. However, in an outdoor environment, many factors, including atmospheric decay, target shape, great distance, fog, temperature out of range and diffraction limits can lead to bad image formation, which directly affects the accuracy of object recognition. The visual characteristics of the human eye mean that it has a much better capacity for picture recognition under normal conditions than artificial intelligence does. However, conditions of interference significantly reduce this capacity for picture recognition for instance, fatigue impairs human eyesight. Hence, psychological and physiological factors can affect the result when the human eye is adopted to measure MRTD (minimum resolvable temperature difference) and MRCTD (minimum resolvable circle temperature difference). This study explores thermal imaging recognition, and presents a method for effectively choosing the characteristic values and processing the images fully. Neural network technology is successfully applied to recognize thermal imaging and predict MRTD and MRCTD (Appendix A), exceeding thermal imaging recognition under fatigue and the limits of the human eye.
Artificial Intelligence, Image Processing and Computer Vision
Yi-Chin Fang, Bo-Wen Wu, "Prediction of the Thermal Imaging Minimum Resolvable (Circle) Temperature Difference with Neural Network Application", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 12, pp. 2218-2228, December 2008, doi:10.1109/TPAMI.2007.70839
[1] D.H. Lee, “Thermal Analysis of Integrated-Circuit Chips Using Thermographic Imaging Techniques,” IEEE Trans. Instrumentation and Measurement, vol. 43, no. 6, pp. 824-829, Dec. 1994.
[2] S.A. Merryman and R.M. Nelms, “Diagnostic Technique for Power Systems Utilizing Infrared Thermal Imaging,” IEEE Trans. Industrial Electronics, vol. 42, no. 6, pp. 615-628, Dec. 1995.
[3] P.J. Moore and F. Harscoet, “Low Cost Thermal Imaging for Power Systems Applications Using a Conventional CCD Camera,” Proc. Energy Management and Power Delivery (EMPD '98), vol. 2, pp.589-594, Mar. 1998.
[4] T.C. Yuan and S.W. Ming, “Human Face Recognition Using Thermal imaging,” J. Medical Biological Eng., vol. 22, no. 2, pp. 97-102, 2002.
[5] L. Pavlidis and J. Levine, “Thermal Imaging Analysis for Polygraph Testing,” IEEE Eng. in Medicine and Biology, vol. 21, no. 6, pp. 56-64, 2002.
[6] J. Head and R. Elliott, “Infrared Imaging: Making Progress in Fulfilling Its Medical Promise,” IEEE Eng. in Medicine and Biology, vol. 21, no. 6, pp. 80-85, 2002.
[7] G.L. Cash and M. Hatamian, “Optical Character Recognition by the Method of Moments,” Computer Vision, Graphics, and Image Processing, vol. 39, no. 3, pp. 291-310, 1987.
[8] M.S. Umansky, “Image Recognition by the Radon Optical Transform and the Method of Moments,” Analytical Methods for Optical Tomography, vol. 1843, pp. 344-355, 1992.
[9] Y. Li, “Reforming the Theory of Invariant Moments for Pattern Recognition,” Pattern Recognition, vol. 25, no. 7, pp. 723-730, 1992.
[10] L. Nigel, “Some Applications of Neural Networks in Optics and Image Processing,” PhD dissertation, J.J. Thomson Physics Laboratory, Univ. of Reading, pp. 48-71, 1998.
[11] D.J. Burr, “Experiments on Neural Net Recognition of Spoken and Written Text,” IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 36, no. 7, pp. 1162-1168, 1988.
[12] I.C. Yeh, “Classification Using Extend-Neuron Networks,” J.Computers, vol. 14, no. 2, pp. 16-22, 2002.
[13] A.M. Fairhurst and A.H. Lettington, “Method of Predicting the Probability of Human Observers Recognizing Targets in Simulated Thermal Images,” Optical Eng., vol. 37, no. 3, pp. 744-751, 1998.
[14] A.M. Fairhurst and A.H. Lettington, “The Effect of Visual Perception on the Required Performance of Imaging Systems,” J.Modern Optics, vol. 47, no. 8, pp. 1435-1446, 2000.
[15] A.H. Lettington and J. MacDonald, “Measurement of the MTF and MRTD for Focal Plane Arrays,” Proc. SPIE Int'l Soc. for Optical Eng., vol. 1969, pp. 217-224, 1993.
[16] F. Yi-chin, “Performance Evaluation of Discrete IR Optical System,” PhD dissertation, J.J. Thomson Physics Laboratory, Univ. of Reading, pp. 61-106, 2000.
[17] A.H. Lettington and Q.H. Hong, “Measurement of the Discrete Modulation Transfer Function,” J. Modern Optics, vol. 40, no. 2, pp.203-212, 1993.
[18] A.H. Lettington and Q.H. Hong, “An Objective MRTD for Discrete Infrared Imaging Systems,” Measurement Science and Technology, vol. 4, no. 10, pp. 1106-1110, 1993.
[19] A.H. Lettington, D. Dunn, A.M. Fairhurst, and F. Yi-Chin, “Proposed Performance Measures for Imaging Systems with Discrete Detector Arrays,” J. Modern Optics, vol. 48, no. 1, pp.115-123, 2001.
[20] M.K. Hu, “Visual Pattern Recognition by Moment Invariants,” IRE Trans. Information Theory, vol. 8, pp. 179-187, 1962.
[21] A. McAulay, A. Coker, and K. Saruhan, “Effect of Noise in Moment Invariant Neural Network Aircraft Classification,” Proc. IEEE Nat'l Aerospace and Electronics Conf. (NAECON '91), pp. 743-749, May 1991.
[22] G.S. Linda and C.S. George, Computer Vision, pp.21-185. Pearson Education Prentice Hall, 2001.
[23] I.P. Leonid, Neural Networks and Intellect: Using Model-Based Concepts, chapters 2-5, 2000.
16 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool