跳到主要內容

臺灣博碩士論文加值系統

(44.192.48.196) 您好!臺灣時間:2024/06/16 09:51
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

: 
twitterline
研究生:羅辰瑋
研究生(外文):Chen-Wei Luo
論文名稱:以FPGA設計並實現基於第二型TSK模糊系統之新型光源估測演算法與其在影像白平衡上的應用
論文名稱(外文):FPGA Design and Implementation of a Novel Illuminant Estimation Algorithm Based on Type-2 TSK Fuzzy System with Application to Image White Balance
指導教授:陳正倫陳正倫引用關係
口試委員:江佩如范志鵬
口試日期:2015-07-30
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
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:2015
畢業學年度:103
語文別:英文
論文頁數:138
中文關鍵詞:光源估測白平衡FPGA第二型TSK模糊系統
外文關鍵詞:Illuminant estimationWhite balanceFPGAType-2 TSK fuzzy system
相關次數:
  • 被引用被引用:0
  • 點閱點閱:205
  • 評分評分:
  • 下載下載:22
  • 收藏至我的研究室書目清單書目收藏:0
環境光源為數位影像擷取的重要影響因素之一。影像的色彩隨不同光源產生變動,人類的視覺系統可以適應不同光源且自動校正色彩。而數位影像擷取裝置沒有相應的機制,在某些光源下擷取的影像會呈現與人類視覺系統所見不同的色彩,此現象稱為色偏。然而目前許多數位影像處理相關的研究仍未考慮到光源的影響。基於type-2 TSK (Takagi-Sugeno-Kang)模糊系統的色溫估測演算法有良好的色溫估測表現,搭配白平衡的應用更能有效消除數位影像的色偏。然而,受制於type-2 TSK模糊系統結構複雜導致執行時間長的問題,無法推及至實際應用的層面。本論文提出對基於type-2 TSK模糊系統色溫估測演算法的FPGA硬體實現,包括白平衡應用。使用Xilinx spartan-6 XC6SLX150晶片開發,且具備相關的實驗結果以及比較探討。FPGA實現的硬體設計報告進一步指出本論文提出的FPGA設計可以達到實時運作的效能,對於一般規格的1080p影像以最大操作時脈運作從估測光源至白平衡處理可以達到一秒39.427張的frame rate,成功解決type-2 TSK模糊系統執行時間長的問題。本論文其他相關的內容包括對type-2 TSK模糊系統的分群探討,原始的參數設置無法穩定達到良好的估測表現,對某些含有高斯雜訊的測式影像估測失敗。本論文透過詳細的直方圖數據分析找出估測失敗的原因,並提出分群原則,使type-2 TSK模糊系統參數能穩定地達到更好的效果。

Environmental illuminant is one of important factors which affect color of digital image capturing closely. The color of image varies with different illuminant. Human vision can adjust color of image automatically under different illuminant but digital captured devices can not. The color of captured images is different from human vision while images are captured under some specific illuminant. This phenomenon called color cast. However, there are still many research about digital image process do not consider about effect of illuminant. Illuminant estimation algorithm based on type-2 TSK (Takagi-Sugeno-Kang) fuzzy system has elegant performance in illuminant estimation and application of image white balance can remove color cast effectively. However, Restricted by inefficient execution speed of type-2 TSK fuzzy system, practical application is quietly difficult. This thesis proposes FPGA implementation of illuminant estimation algorithm based on type-2 TSK fuzzy system using Xilinx spartan-6 XC6SLX150 FPGA chip. Relative experimental results and comparative study are provided. FPGA design report further points that proposed FPGA design can achieve real-time operation. For generic 1080p image it can reach the frame rate of 39.427 frames per second on maximal operation frequency for illuminant estimation and white balance. Successfully solve the insufficient execution speed problem of the algorithm. Other included relative content is the cluster allocation study of type-2 TSK fuzzy system. The original setting of cluster allocation does not stably perform well every time. . Sometimes it fails on some cases of the test image with Gaussian noise. This thesis analysis the factor of failure by detailed histogram plot and proposes new set of cluster allocation which improves parameters of type-2 TSK fuzzy system for better and more stable effects.

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Literature Review 4
1.2.1 Existing Illuminant Estimation Methods 4
1.2.2 Existing White/Color Balance Method 12
1.2.3 Existing Hardware Implementation of Image Process algorithm 18
1.3 Organization and Contribution 29
Chapter 2 System Description and Configuration 31
2.1 Illuminant 31
2.1.1 Color Temperature 31
2.1.2 Illuminant Chromaticity 32
2.2 Color Space 33
2.3 Experimental Setup 39
2.3.1 Software 39
2.3.2 Hardware 41
Chapter 3 Methodology 45
3.1 Illuminant Estimation Algorithm 45
3.2 White Balance 47
Chapter 4 Pre-evaluation of FPGA Implementation 49
4.1 Fixed-Point Arithmetic 49
4.2 Complicated Computation 49
4.3 Setting of Type-2 TSK Fuzzy System 50
4.3.1 Quantity of the Fuzzy Rule. 50
4.3.2 Search for Optimal Parameters 51
4.3.3 Data Width of Type-2 TSK Fuzzy System 52
4.3.4 Arithmetic of Rule Layer 53
4.4 FPGA Implementation of KM Algorithm 53
Chapter 5 FPGA Implementation 60
5.1 System Overview 60
5.2 Fuzzy System 63
5.2.1 Type-2 Fuzzy System Pre-stage 65
5.2.2 64-Inputs Bitonic Sorter 67
5.2.3 KM Algorithm Module 68
5.2.4 Average Calculating Module 70
5.3 Histogram System 71
5.4 White balance module 73
5.5 Design Report of FPGA Implementation 74
Chapter 6 Results of Illuminant Estimation 79
6.1 Test Image 79
6.2 Results 82
6.3 Discussion 90
Chapter 7 Results of White Balance 95
7.1 Results 95
7.2 Discussion 104
Chapter 8 Conclusion and Future Work 106
Reference 108
Appendix A Relationship between Cluster Allocation and Histogram 114

[1]L. Yucheng and Z. Buyue, "Photometric alignment for surround view camera system," in Image Processing (ICIP), 2014 IEEE International Conference on, 2014, pp. 1827-1831.
[2]H. Garud, U. K. Pudipeddi, K. Desappan, and S. Nagori, "A fast color constancy scheme for automobile video cameras," in Signal Processing and Communications (SPCOM), 2014 International Conference on, 2014, pp. 1-6.
[3]M. Sridharan and P. Stone, "Towards on-board color constancy on mobile robots," in Computer and Robot Vision, 2004. Proceedings. First Canadian Conference on, 2004, pp. 130-137.
[4]L. Huimin, Z. Hui, Y. Shaowu, and Z. Zhiqiang, "Camera parameters auto-adjusting technique for robust robot vision," in Robotics and Automation (ICRA), 2010 IEEE International Conference on, 2010, pp. 1518-1523.
[5]T. Ai, M. A. Ali, G. Steffan, K. Ovtcharov, S. Zulfiqar, and S. Mann, "Real-time HDR video imaging on FPGA with compressed comparametric lookup tables," in Electrical and Computer Engineering (CCECE), 2014 IEEE 27th Canadian Conference on, 2014, pp. 1-6.
[6]V. Balaji and R. Krishnaveni, "FPGA based low complexity multipurpose reconfigurable image processor," in Information Communication and Embedded Systems (ICICES), 2014 International Conference on, 2014, pp. 1-6.
[7]A. Gabiger-Rose, M. Kube, R. Weigel, and R. Rose, "An FPGA-based fully synchronized design of a bilateral filter for real-time image denoising," Industrial Electronics, IEEE Transactions on, vol. 61, pp. 4093-4104, 2014.
[8]A. Lluis-Gomez and E. Edirisinghe, "A novel colour management system for image signal processors in commercial digital cameras," in Consumer Electronics (ICCE), 2014 IEEE International Conference on, 2014, pp. 41-44.
[9]A. Amara, F. Amiel, and T. Ea, "FPGA vs. ASIC for low power applications," Microelectronics Journal, vol. 37, pp. 669-677, 2006.
[10]K. Ian and J. Rose, "Measuring the Gap Between FPGAs and ASICs," Computer-Aided Design of Integrated Circuits and Systems, IEEE Transactions on, vol. 26, pp. 203-215, 2007.
[11]S. Tominaga and B. Wandell, "Natural scene-illuminant estimation using the sensor correlation," Proceedings of the IEEE, vol. 90, pp. 42-56, 2002.
[12]V. C. Cardei, B. Funt, and K. Barnard, "Estimating the scene illumination chromaticity by using a neural network," JOSA A, vol. 19, pp. 2374-2386, 2002.
[13]!!! INVALID CITATION !!!
[14]C.-L. Chen and S.-H. Lin, "Intelligent color temperature estimation using fuzzy neural network with application to automatic white balance," Expert Systems with Applications, vol. 38, pp. 7718-7728, 2011.
[15]C.-F. Yang, C.-W. Luo, and C.-L. Chen, "Fuzzy Neural System for Estimating the Color Temperature of Digitally Captured Image with FPGA Implementation," presented at the 10th IEEE Conference on Industrial Electronics and Applications (ICIEA), Auckland, New Zealand, 2015.
[16]J.-R. Shen, "Parametric Optimization of a Fuzzy System Based on Combined Global and Local Search Methods with Application to Illuminant Estimation," M.S. thesis, Electrical Engineering, National Chung Hsing University, 2014.
[17]J.-R. Shen, C.-F. Yang, and C.-L. Chen, "Illuminant estimation using a particle swarm optimized fuzzy neural network," in Control & Automation (ICCA), 11th IEEE International Conference on, 2014, pp. 449-454.
[18]C.-F. Yang, "A Novel Illuminant Estimation Algorithm Based on Type-2 TSK Fuzzy System with Application to Image White Balance," M.S. thesis, Electrical Engineering, National Chung Hsing University, 2014.
[19]T. Haruki and K. Kikuchi, "Video camera system using fuzzy logic," IEEE Transactions on Consumer Electronics, vol. 38, pp. 624-634, 1992.
[20]Y.-C. Liu, W.-H. Chan, and Y.-Q. Chen, "Automatic white balance for digital still camera," IEEE Transactions on Consumer Electronics, vol. 41, pp. 460-466, 1995.
[21]J. Chiang, "Gray world assumption," PSYCH221/EE362 curse project, Department of Psychology, Stanford University, USA, 1999.
[22]J. Wang, Y. Liu, F. Liu, H. Xiong, and C. Li, "A method of automatic white balance using fuzzy logic," in Circuits and Systems, 2000. IEEE APCCAS 2000. The 2000 IEEE Asia-Pacific Conference on, 2000, pp. 615-617.
[23]Y. Kim, J.-S. Lee, A. W. Morales, and S.-J. Ko, "A video camera system with enhanced zoom tracking and auto white balance," Consumer Electronics, IEEE Transactions on, vol. 48, pp. 428-434, 2002.
[24]H.-K. Lam, O. C. Au, and C.-W. Wong, "Automatic white balancing using adjacent channels adjustment in RGB domain," in Multimedia and Expo, 2004. ICME''04. 2004 IEEE International Conference on, 2004, pp. 979-982.
[25]H.-K. Lam, O. C. Au, and C.-W. Wong, "Automatic white balancing using standard deviation of RGB components," in Circuits and Systems, 2004. ISCAS''04. Proceedings of the 2004 International Symposium on, 2004, pp. III-921-4 Vol. 3.
[26]C. Shumate and H. Li, "Perfect Reflector Assumption," ed: Psych, 2000.
[27]E. Y. Lam, "Combining gray world and retinex theory for automatic white balance in digital photography," in Consumer Electronics, 2005.(ISCE 2005). Proceedings of the Ninth International Symposium on, 2005, pp. 134-139.
[28]C.-L. Chen and S.-H. Lin, "Formulating and solving a class of optimization problems for high-performance gray world automatic white balance," Applied Soft Computing, vol. 11, pp. 523-533, 2011.
[29]R. Lukac, "New framework for automatic white balancing of digital camera images," Signal Processing, vol. 88, pp. 582-593, 2008.
[30]J. Van De Weijer and T. Gevers, "Color constancy based on the grey-edge hypothesis," in Image Processing, 2005. ICIP 2005. IEEE International Conference on, 2005, pp. II-722-5.
[31]S. Lai, X. Tan, Y. Liu, B. Wang, and M. Zhang, "Fast and robust color constancy algorithm based on grey block-differencing hypothesis," Optical review, vol. 20, pp. 341-347, 2013.
[32]H.-C. Hung and C.-L. Chen, "A fuzzy inference model for removing the color cast of digitally captured images under unknown illuminants," in Fuzzy Theory and it''s Applications (iFUZZY), 2012 International Conference on, 2012, pp. 192-197.
[33]H.-C. Hung, C.-L. Chen, C.-F. Yang, and J.-R. Shen, "A fuzzy-neural system for removal of the color cast for digitally captured images under unknown illuminants," in Control and Automation (ICCA), 2013 10th IEEE International Conference on, 2013, pp. 1201-1206.
[34]C.-F. Yang, C.-W. Luo, and C.-L. Chen, "A Fuzzy Neural Approach to Novel Color Balance with FPGA Implementation," presented at the 10th Asian Control Conference (ASCC), Kota Kinabalu, Malaysia, 2015.
[35]K. P. Acken, M. J. Irwin, and R. M. Owens, "A parallel ASIC architecture for efficient fractal image coding," Journal of VLSI signal processing systems for signal, image and video technology, vol. 19, pp. 97-113, 1998.
[36]D. Doswald, J. Häfliger, P. Blessing, N. Felber, P. Niederer, and W. Fichtner, "A 30-frames/s megapixel real-time CMOS image processor," Solid-State Circuits, IEEE Journal of, vol. 35, pp. 1732-1743, 2000.
[37]Y. Zhang, S.-y. Yao, N. Zhang, and J.-t. Xu, "Design and implementation of two key image processing techniques for CMOS image sensor based on fpga," in Solid-State and Integrated-Circuit Technology, 2008. ICSICT 2008. 9th International Conference on, 2008, pp. 2152-2155.
[38]X. Tan, S. Lai, B. Wang, M. Zhang, and Z. Xiong, "A simple gray-edge automatic white balance method with FPGA implementation," Journal of Real-Time Image Processing, vol. 10, pp. 207-217, 2013.
[39]C.-H. Chen, S.-Y. Tan, and W.-T. Huang, "A novel hardware-software co-design for automatic white balance," International Journal of Mathematical Models and Methods in Applied Sciences, vol. 1, pp. 223-231, 2007.
[40]J. Khalifat and T. Arslan, "A novel Dynamic Partial Reconfiguration design for automatic white balance," in Adaptive Hardware and Systems (AHS), 2014 NASA/ESA Conference on, 2014, pp. 9-14.
[41]J. Schanda, Colorimetry: understanding the CIE system: John Wiley & Sons, 2007.
[42]R. Sepúlveda, O. Montiel, O. Castillo, and P. Melin, "Embedding a high speed interval type-2 fuzzy controller for a real plant into an FPGA," Applied Soft Computing, vol. 12, pp. 988-998, 2012.
[43]M. D. Schrieber and M. Biglarbegian, "Hardware implementation of a novel inference engine for interval type-2 fuzzy control on FPGA," in Fuzzy Systems (FUZZ-IEEE), 2014 IEEE International Conference on, 2014, pp. 640-646.
[44]M. D. Schrieber and M. Biglarbegian, "Hardware implementation and performance comparison of interval type-2 fuzzy logic controllers for real-time applications," Applied Soft Computing, vol. 32, pp. 175-188, 2015.
[45]H. Wu and J. M. Mendel, "Uncertainty bounds and their use in the design of interval type-2 fuzzy logic systems," Fuzzy Systems, IEEE Transactions on, vol. 10, pp. 622-639, 2002.
[46]C.-F. Juang and Y.-W. Tsao, "A type-2 self-organizing neural fuzzy system and its FPGA implementation," Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 38, pp. 1537-1548, 2008.
[47]J. Harkins, T. El-Ghazawi, E. El-Araby, and M. Huang, "Performance of sorting algorithms on the SRC 6 reconfigurable computer," in Field-Programmable Technology, 2005. Proceedings. 2005 IEEE International Conference on, 2005, pp. 295-296.
[48]K. E. Batcher, "Sorting networks and their applications," in Proceedings of the April 30--May 2, 1968, spring joint computer conference, 1968, pp. 307-314.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top