臺灣博碩士論文加值系統

ATD是被認為最接近人眼的色彩模型。在本論文中，我們將ATD色彩模型應用到多通道聯合轉換相關轉換器進行圖像辨識。為了評估ATD色彩模型是否適用於圖像辨識，我們首先利用多階量化參考函數的技術探討基於此模型之圖像辨識的效果。此外，我們和最常被用來做圖像辨識的RGB色彩模型做比較。評比的項目包含旋轉形變之辨識能力、對亮度強弱的辨識能力、多階量化參考函數效果、雜訊容忍度、真實背景的辨識能力、各通道間相關程度。我們利用PCE、PSR、CPI、Mutual correlation coefficient作為評估效能的工具。由結果得知，ATD色彩模型適合用來做圖像辨識。

People consider that ATD color model is the most to be close to human eyes. In this thesis, we apply ATD color model to multi-channel nonzero order joint transform correlator and perform pattern recognition. To estimate whether ATD color model is suitable for pattern recognition, we utilize the multi-level quantized reference functions to discuss the effect of pattern recognition. Furthermore, we compare with RGB, which is common used to perform pattern recognition. The terms of estimation contain recognition ability of rotational distortion, brightness performance, effect of multi-level quantized reference functions, noise tolerance ability, recognition ability of realistic background, and relationship between channels and channels. We utilize peak to correlation energy, peak to sidelobe ratio, correlation peak intensity, and mutual correlation coefficient as our performance evaluation parameters. Finally, the results show that ATD color model is suitable for pattern recognition.

Chinese Abstract i
English Abstract ii
Acknowledgement iii
Contents iv
Figure Captions vi
Tables ix
Chapter 1 Introduction 1
Chapter 2 Optical Pattern Recognition 4
2.1 Color model 4
2.1.1 ATD color model 4
2.2 Multi-channel nonzero order joint transform correlator 6
2.3 Theoretical analysis 8
2.3.1 Correlation process 8
2.3.2 Method of removal of zero order term 11
2.3.3 Minimum average correlation energy 14
2.3.4 Multi-level quantized reference functions 18
2.4 Performance evaluation 19
Chapter 3 Numerical Results 23
3.1 Pattern recognition with MQRF based on ATD color model 23
3.1.1 Results for MQRF of original pattern 29
3.1.2 Results for MQRF of multi-target pattern 41
3.2 Differences of pattern recognition between ATD and RGB color models 44
3.2.1 Results for noise-free original pattern 44
3.2.2 Results for different brightness 47
3.2.3 Results for different quantization parameters 48
3.2.4 Results for noisy environment 50
3.2.5 Results for pattern with background 53
3.2.6 Results for correlation between channels 54
Chapter 4 Conclusions 55
References 57

[1]A. VanderLugt, “Signal detection by complex spatial filtering,” IEEE Trans. Inf. Theory, Vol. IT-10, pp. 139-145, 1964.
[2]C. S. Weaver and J. W. Goodman, “A technique for optically convolving two function,” Appl. Opt., Vol. 5, pp. 1248-1249, 1996.
[3]X. J. Lu, F. T. S. Yu and D. A. Gregory, “Comparison of VanderLugt and joint transform correlator,” Appl. Phys. B, Vol. 51, pp. 153-164, 1990.
[4]F. T. S. Yu, Q. W. Song, Y. S. Cheng and D. A. Gregory, “Comparison of detection efficiencies for VanderLugt and joint transform correlators,” Appl. Opt., Vol. 29, pp. 225-232, 1990.
[5]P. Putwosumarto and F. T. S. Yu, “Robustness of joint transform correlator versus VanderLugt correlator,” Opt. Eng., Vol. 36, pp. 2775-2780, 1997.
[6]F. T. S. Yu and X. J. Lu, “A real-time programmable joint transform correlator,” Opt. Commun., Vol. 52, pp. 10-16, 1984.
[7]B. Javidi and C. J. Kuo, “Joint transform image correlation using a binary spatial light modulator at the Fourier plane,” Appl. Opt., Vol. 27, pp. 663-665, 1988.
[8]G. Lu, Z. Zhang, S. Wu and F. T. S. Yu, “Implementation of a non-zero-order joint-transform correlator by use of shifting techniques,” Appl. Opt., Vol. 36, pp. 470-483, 1997.
[9]C. Li, S. Yin and F. T. S. Yu, “Nonzero-order joint transform correlator,” Opt. Eng., Vol. 37, pp. 58-65, 1998.
[10]M. S. Alam, X. Chen and M. A. Karim, “Distortion-invariant fringe-adjusted joint transform correlation,” Appl. Opt., Vol. 36, pp. 7422-7427, 1997.
[11]A. Mahalanobis, B. V. K. V. Kumar and D. Casasent, “Minimum average correlation energy filters,” Appl. Opt., Vol. 26, pp. 3633-3640, 1987.
[12]C. Chen, “Minimum-variance nonzero order joint transform correlators,” Opt. Commun., Vol. 182, pp. 91-94, 2000
[13]C. Chen and J. Fang, “Cross-correlation peak optimization on joint transform correlators,” Opt. Commun., Vol. 178, pp. 315-322, 2000.
[14]C. Chen, “Joint transform correlator with minimum peak variance in nonzero-mean noise environment,” Opt. Commun., Vol. 187, pp. 319-323, 2001.
[15]C. Chen and J. Fang, “Optimal design of a nonzero order joint transform correlator with a real-valued reference function for distortion invariant fingerprint recognition,” Opt. Memory and Neural Networks, Vol. 11, pp. 45-54, 2002.
[16]C. Chen and J. Fang, “Non-zero order joint transform correlator with multi-level quantized reference function,” Opt. Commun., Vol. 220, pp. 41-47, 2003.
[17]F. T. S. Yu, Z. Yang, and K. Pan, “Polychromatic target identification with a color liquid-crystal-TV-based joint-transform correlator,” Appl. Opt., Vol. 33, pp. 2170-2172, 1994.
[18]M. Corbalan and M. S. Millan, “Color image acquisition by charge- coupled device cameras in polychromatic pattern recognition,” Opt. Eng., Vol. 35, pp. 754-758, 1996.
[19]M. S. Alam and C. N. Wai, “Color pattern recognition using fringe-adjusted joint transform correlation,” Opt. Eng., Vol. 187, pp. 2407-2413, 2001
[20]Chen, C. Chen, C. Lee, and C. Chen, “Color face-image recognition with liquid-crystal spatial light modulators,” Microw. Opt. Technol. Lett., Vol. 42, pp. 234-237, 2004.
[21]D. Mendlovic, M. Deutsch, C. Ferreira and J. Garcia, “Single-channel polychromatic pattern recognition by the use of a joint transform correlator,” Appl. Opt., Vol. 35, pp. 6382-6389, 1996.
[22]M. Deutsch, J. Garcia and D. Mendlovic, “Multi-channel single-output color pattern recognition by use of a joint-transform correlator,” Appl. Opt., Vol. 35, pp. 6976-6982, 1996.
[23]A. Fares et al., “Multi-channel chromatic transformations for nonlinear color pattern recognition,” Opt. Commun., Vol. 203, pp. 255-261, 2002.
[24]M. S. Millan, and M. Corbalan, “Optical pattern recognition based on color vision models,” Opt. Lett., Vol. 20, pp. 1722-1724, 1995.
[25]M. S. Millan et al., “Improvement of the color discrimination capability in optical pattern recognition,” Proc. SPIE, Vol. 2730, pp. 207-210, 1996.
[26]S. L. Guth et al., “Vector model for normal and dichromatic color vision,” J. Opt. Soc. Am., Vol. 70, pp. 197-212, 1980.
[27]S. L. Guth, “Unified model for human color perception and visual adaptation,” Proc. SPIE, Vol. 107, pp.370, 1989.
[28]C. Chen and W. Wu, “Color pattern recognition with the multi-channel non-zero-order joint transform correlator based on the HSV color space,” Opt. Commun., Vol. 244, pp. 51-59, 2005.