(44.192.112.123) 您好!臺灣時間:2021/03/06 07:40
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:王玟淇
研究生(外文):Wen-Chi Wang
論文名稱:液晶光電相關濾波器應用於彩色影像辨識之設計與改善
論文名稱(外文):Designing and Improving the Optical Correlation Filter Using Liquid Crystal Devices for Color Image Recognition
指導教授:陳祖龍
指導教授(外文):Chulung Chen
學位類別:碩士
校院名稱:元智大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:英文
論文頁數:59
中文關鍵詞:相關器
外文關鍵詞:Multi-channel non-zero order joint transform correlatorshift method
相關次數:
  • 被引用被引用:0
  • 點閱點閱:162
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在本論文中,我們應用無零階項多通道聯合轉換相關器之架構於彩色圖像辨識,並利用了液晶面板。此架構可將影響系統辨識效能之零階項去除,讓我們獲得良好的辨識效果。另外,我們使用訓練影像位移的技術來合成參考函數,作為此光學相關濾波器。

在過去的研究中,經常地將訓練影像置於假想中心,但卻不能保證旁辦能量是最小的。爲了改善這個問題,我們將訓練影像在訓練影像平面上由左至右由上而下做位移,每次位移一個畫素後即計算參考函數及記錄功率頻譜,找出最小旁辦能量的位置。利用此技術,我們將最終輸出平面的旁辦能量降低並使得相關峰值更尖銳,優化了此架構的辨識能力及減少判斷錯誤的機會。
In this thesis, we propose a multi-channel nonzero order JTC for color image recognition and apply the liquid crystal devices to this system. This system is able to remove the zero order term that influences the ability of recognition.

In our previous research, training images were located at the presumed center as usual. Nevertheless, it can not guarantee that the sidelobe energy is minimum. In order to improve this weakness, training images are shifted pixel by pixel from the left to the right and from the top to the bottom. We calculate the reference function and record the power spectrum in each shift. Hence the position to yield minimum sidelobe energy would be discovered. As a result, we will obtain lower sidelobes and sharper correlation peaks at the output plane. Finally, the recognition ability can be better and erroneous discrimination is diminished.
Contents
Chinese Abstract...i
English Abstract...ii
Acknowledgement...iii
Contents...iv
Figure Captions...vi
Chapter 1 Introduction...1
Chapter 2 Optical Pattern Recognition...5
2.1 The Fourier transform of optics...5
2.2 4f optical correlator...9
2.3 Hybrid optical correlator...11
2.4 Multi-channel nonzero order joint transform correlator...12
2.5 Minimum average correlation energy (MACE) method...19
2.6 MACE multi-channel NOJTC...22
2.7 Performance evaluation...24
2.7.1 Correlation peak intensity (CPI)...24
2.7.2 Peak to correlation energy (PCE)...24
2.7.3 Peak to sidelobe ratio (PSR)...25
2.7.4 Signal to noise ratio (SNR)...26
Chapter 3 Numerical Results...27
3.1 Proposed method...27
3.2 Results and comparison...31
3.2.1 Sidelobe energy comparison...33
3.2.2 Recognition ability comparison for distorted targets...37
3.2.3 Results for noisy images...44
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 functions,” Appl. Opt., Vol. 5, pp. 1248-1249, 1966.
[3]F. T. S. Yu and X. J. Lu, “A real-time programmable joint transform correlator,” Opt. Commun., Vol. 52, pp. 10-16, 1984.
[4]F. T. S. Yu, G. Lu, M. Lu, and D.Zhao, “Application of position encoding to complex joint transform correlator,” Appl. Opt., Vol. 34, pp. 470-483, 1997.
[5]G. Lu, Z. Zhang, S. Wu, and F. T. S. Yu, “Implementation of a nonzero-order joint-transform correlator by use of phase shifting techniques,” Appl. Opt., Vol. 36, pp. 470-483, 1997.
[6]C. Li, S. Yin, and F. T. S. Yu, “Nonzero-order joint transform correlator,” Opt. Eng., Vol. 37, pp. 58-65, 1998.
[7]M. S. Alam, X. Chen, and M. A. Karim, “Distortion-invariant fringe-adjusted joint transform correlation,” Appl. Opt., Vol. 36, pp. 7422-7427, 1997.
[8]D. Casasent, “Unified synthetic discriminant function computation formulation,” Appl. Opt., Vol. 23, pp. 1620-1627, 1984.
[9]A. Mahalanobis, B. V. K. Vijaya Kumar, and D. Casasent, “Minimum average correlation energy filters,” Appl. Opt., Vol. 26, pp. 3633-3640, 1987.
[10]M. S. Kim, M. R. Feldman, and C. C. Guest, “Optimum encoding of binary phase-only filters with a simulated annealing algorithm,” Opt. Lett., Vol. 14, pp. 545-547, 1989.
[11]M. S. Kim and C. C. Guest, “Simulated annealing algorithm for binary phase only filters in pattern classification,” Appl. Opt., Vol. 29, pp. 1203-1208, 1990.
[12]C. Li, M. Lu, S. Yin, F. T. S. Yu, T. D. Hudson, and D. K. McMillen, “Performance of quantized composite filters in a joint transform correlator,” Opt. Eng., Vol. 35, pp. 2218-2226, 1996.
[13]C. Li, J. Li, S. Yin, T. D. Hudson, and D. K. McMillen, “Synthesize multi-level composite filter for synthetic aperture radar image identification,” Opt. Commun., Vol. 146, pp. 285-301, 1998.
[14]C. Chen and J. Fang, “Cross-correlation peak optimization on joint transform correlators,” Opt. Commun., Vol. 178, pp. 315-322, 2000.
[15]C. Chen and J. Fang, “Nonzero order joint transform correlators with an optimized real-valued reference function,” J. Mod. Opt., Vol. 48, pp. 1329-1338, 2001.
[16]C. Chen and J. Fang, “Optimal synthesis of a real-valued template for synthetic aperture radar pattern recognition,” Microw. Opt. Technol. Lett., Vol. 32, pp. 91-95, 2002.
[17]J. Fang and C. Chen, “Nonzero order joint transform correlator with multi-level quantized reference function,” Opt. Commun., Vol. 220, pp. 41-47, 2003.
[18]J. D. Gaskill, Linear systems Fourier transform and Optics, John Wiley and Sons Inc., 1978.
[19]Joseph Goodman, Introduction to Fourier optics, 2nd edition, McGraw-Hill Book Co Ltd, 2000.
[20]王仕偉,「利用液晶裝置做光學影像辨識的最佳化研究」,元智大學,電機系碩士論文,2000月6月。
[21]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.
[22]C. Wu, C. Chen and J. Fang, “Constrained optimization for color pattern recognition with a nonzero order joint transform correlator,” Microw. Opt. Technol. Lett., Vol. 33, pp.385-388, 2002.
[23]C. Chen and J. Fang, “Synthetic aperture radar image recognition by constrained joint transform correlator,” Optik, pp.125-130, 2001.
[24]C Chen, “Minimum-variance nonzero order joint transform correlator,” Opt. Commun.182, pp.91-94, 2000.
[25]C. Chen and J. Fang, “Nonzero order joint transform correlators with an optimized real-valued reference function,” J. Mod. Opt., Vol. 48, pp. 1329-1338, 2001.
[26]鍾耀寰,「光學相關濾波器之最佳化影像位置的研究」,元智大學,電機系碩士論文,2001月12月。
[27]陳哲緯,「液晶光電相關濾波器的設計與改善」,元智大學,電機系碩士論文,2002月06月。
[28]W. Wang, C. Chen, and C. Lee, “Reduction of sidelobe energy using shift in color pattern recognition for the nonzero order joint transform correlator,” 台灣光電科技研討會暨國科會光電學門研究成果發表會 (OPT 2005), (CD file, no page number), 2005.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔