Responsive image
博碩士論文 etd-0625118-154854 詳細資訊
Title page for etd-0625118-154854
論文名稱
Title
高效能無排序二維中值濾波器之設計與硬體實現
Design and Implementation of A High-Performance Sorting-Free Two-Dimensional Median Filter
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
75
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2018-06-28
繳交日期
Date of Submission
2018-07-29
關鍵字
Keywords
無排序、位元層級、容誤、中值濾波器、影像處理電路
sorting-free, error-tolerance, median filter, bit-level, image processing circuits
統計
Statistics
本論文已被瀏覽 5627 次,被下載 0
The thesis/dissertation has been browsed 5627 times, has been downloaded 0 times.
中文摘要
隨著製程的技術進步,半導體元件的尺寸越來越小,單一晶片上可以整合的電晶體個數也越來越多,這些因素導致製程難度的增加,使得晶片越來越容易受到製程上的缺陷影響,造成晶片無法正常運作。針對影像處理晶片,這些缺陷極可能導致影像錯誤,造成系統運作問題。然而若是影像錯誤並不嚴重,我們極可能無法察覺而可接受。另一方面,針對錯誤比較嚴重的影像我們可嘗試使用一些影像修復的方法來進行修復。值得一提的是,若是此修復方法可透過硬體方式達到即時處理,對於提升物聯網或是人工智慧等應用之可靠度將有極大助益。現今影像修復的方法主要可分為兩種,一種是平均濾波器,另外一種是排序值濾波器。由於平均濾波器的運算需使用到加減乘除,複雜許多,若是以硬體實現成本極可能會相當高,因此本論文以排序值濾波器進行硬體架構與實作研究探討,當中我們專注於具有極佳修復效果的中值濾波器。本論文開發出一基於位元層級的嶄新中值濾波器,具有高度成本效益。值得一提的是,我們所開發的中值濾波器採用無排序方式進行運算,此方式可大幅提升電路的操作頻率,使得即使是一張具有4K畫質的影像都能在16.67毫秒內修復完畢,若以視訊來說,可達到60FPS的流暢高解析度畫質。在本論文中我們也分析探討了我們所開發的中值濾波器用於支援不同窗口大小,包含3x3, 5x5, 及7x7,時的硬體效能與成本。分析結果顯示與文獻中其他方法相比,本論文所提出的中值濾波器能有更佳的成本效益。
Abstract
As the transistor feature size keeps scaling down, more and more transistors are integrated to a single chip. These factors increase the difficulty of the manufacturing and also the susceptibility of chips to manufacturing defects, which may result in operational failures of chips. For image processing chips, image errors may thus be incurred and accordingly causes system failures. However as long as the image errors are not significant, it is very likely that they are imperceptible and thus are acceptable. On the other hand, for unacceptable image errors, we can try to develop image restoration methods to deal with the errors. In particular, if these methods can be implemented by hardware to achieve real-time processing, reliability enhancement of IoT or AI applications can be greatly facilitated. In the literature there are mainly two types of image restoration methods developed. One is mean filter, and the other is order statistics filter. Since the former one requires complicated operations such as multiplication and division, the associated hardware implementation cost may be unaffordable. Therefore in this thesis we take the order statistics filter into account for hardware architecture and implementation investigation. In particular, we focus on the median filter method that has been shown to have excellent restoration performance. We propose a new bit-level median filter that does not need any sorting operations and has high cost-effectiveness. We will show that even a 4K image can be processed in only 16.67 ms by our filter. For video applications, a smooth and high-resolution video with 60fps can thus be supported. We also analyze the hardware performance and cost of the proposed median filter to support different window sizes, including 3×3, 5×5 and 7×7. Our analysis results show that our median filter has much higher cost-effectiveness than the previous methods.
目次 Table of Contents
摘要 i
目錄 iii
圖目錄 v
表目錄 vii
第一章 概論 1
1.1研究動機 1
1.2研究貢獻 2
1.3論文大綱 4
第二章 研究背景 5
2.1影像修復方法 5
2.1.1 窗口(window) 5
2.1.2平均濾波器(Mean filter) 6
2.1.2.1算術平均濾波器(Arithmetic mean filter) 6
2.1.2.2幾何平均濾波器(Geometric mean filter) 6
2.1.2.3調和平均濾波器(Harmonic mean filter) 7
2.1.2.4反調和平均濾波器(Contraharmonic mean filter) 7
2.1.2.5結果與討論 8
2.1.3排序統計值濾波器 8
2.1.3.1Alpha修整平均濾波器(Alpha-trimmed mean filter) 8
2.1.3.2最大值最小值濾波器 9
2.1.3.3中間點濾波器 10
2.1.3.4中值濾波器 10
2.1.3.5結果與討論 11
2.2影像品質評估參數 11
2.2.1 Peak signal-to-noise ratio (PSNR) 11
2.2.2 Structural Similarity (ssim) 13
2.2.3Feature Similarity Index with chrominance (FSIMc) 14
2.3 JPEG 2000 15
第三章 中值濾波器之論文探討 17
3.1中值濾波器的探討 17
3.1.1排序(sorting) 17
3.1.2無排序(non-sorting) 20
3.2結果與討論 22
第四章 中值濾波器之錯誤影像修復 23
4.1中值濾波器簡介 23
4.2有更新之中值濾波器演算法 23
4.2.1演算法流程 23
4.2.2效能分析 30
4.2.3 結果與討論 30
4.3 無更新之中值濾波器 33
4.3.1演算法流程 33
4.3.2 效能分析 35
4.4 可重組之中值濾波器 36
4.4.1 演算法流程 36
4.4.2 效能分析 38
4.5實驗結果 38
第五章 硬體實現 55
5.1硬體架構 55
5.2效能比較 58
第六章 結論與未來展望 61
第七章 參考文獻 62
參考文獻 References
[1] J. A. Rivers and P. Kudva, "Reliability challenges and system performance at the architecture level," IEEE Design & Test of Computers, 26(6):pp.62-73, 2009.
[2] M. A. Breuer, S. K. Gupta, and T. Mak, "Defect and error tolerance in the presence of massive numbers of defects," IEEE Design & Test of Computers, 21(3): pp. 216-227, 2004.
[3] S. S. Manek and H. Tjandrasa, "A soft weighted median filter for removing general purpose image noise," Proc. Int’l. Conf. in Information & Communication Technology and System (ICTS), pp. 25-30, 2017.
[4] H.-L. Eng and K.-K. Ma, "Noise adaptive soft-switching median filter," IEEE Transactions on image processing, 10(2): pp. 242-251, 2001.
[5] S. Zhang and M. A. Karim, "A new impulse detector for switching median filters," IEEE Signal processing letters, 9(11): pp. 360-363, 2002.
[6] N. Joshi, S. Jain, and A. Agarwal, "An improved approach for denoising MRI using non local means filter," Proc. Int’l. Conf. in Next Generation Computing Technologies (NGCT), pp. 650-653, 2016.
[7] C.-C. Cheng, F.-C. Cheng, P.-H. Lin, and S.-C. Huang, "A block-based switch median filter for removing high density salt-and-pepper noises," Proc. Int’l. Conf. in Consumer Electronics-Taiwan (ICCE-TW), pp. 153-154, 2014.
[8] J. O. Cadenas, G. M. Megson, and R. S. Sherratt, "Median filter architecture by accumulative parallel counters," IEEE Transactions on Circuits and Systems II: Express Briefs, 62(7), pp. 661-665, 2015.
[9] R.-D. Chen, P.-Y. Chen, and C.-H. Yeh, "Design of an area-efficient one-dimensional median filter," IEEE Transactions on Circuits and Systems II: Express Briefs, 60(10), pp. 662-666, 2013.
[10] R.-D. Chen, P.-Y. Chen, and C.-H. Yeh, "A low-power architecture for the design of a one-dimensional median filter," IEEE Transactions on Circuits and Systems II: Express Briefs, 62(3), pp. 266-270, 2015.
[11] E. Nikahd, P. Behnam, and R. Sameni, "High-speed hardware implementation of fixed and runtime variable window length 1-D median filters," IEEE Transactions on Circuits and Systems II: Express Briefs, 63(5), pp. 478-482, 2016.
[12] V. Kumar, A. Asati, and A. Gupta, "Low-latency median filter core for hardware implementation of 5× 5 median filtering," IET Image Processing, 11(10), pp. 927-934, 2017.
[13] E. Kalali and I. Hamzaoglu, "A low energy 2D adaptive median filter hardware," in Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, pp. 725-729,2015.
[14] A. Hore and D. Ziou, "Image quality metrics: PSNR vs. SSIM," Proc. Int’l. Conf. in Pattern recognition (icpr), pp. 2366-2369, 2010.
[15] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE transactions on image processing, 13 (4), pp. 600-612, 2004.
[16] L. Zhang, L. Zhang, X. Mou, and D. Zhang, "FSIM: A feature similarity index for image quality assessment," IEEE transactions on Image Processing, 20(8), pp. 2378-2386, 2011.
[17] C. Christopoulos, A. Skodras, and T. Ebrahimi, "The JPEG2000 still image coding system: an overview," IEEE transactions on consumer electronics, 46(4), pp. 1103-1127, 2000.
[18] G. K. Wallace, "The JPEG still picture compression standard," IEEE transactions on consumer electronics, 38(1), pp. xviii-xxxiv, 1992.
[19] I. Daubechies and W. Sweldens, "Factoring wavelet transforms into lifting steps," Journal of Fourier analysis and applications, 4( 3), pp. 247-269, 1998.
[20] O. Astrachan, "Bubble sort: an archaeological algorithmic analysis," in ACM SIGCSE Bulletin, 35(1), pp. 1-5,2003
[21] E. Nikahd, P. Behnam, and R. Sameni, "High-speed hardware implementation of fixed and runtime variable window length 1-D median filters," IEEE Transactions on Circuits and Systems II: Express Briefs, 63(5), pp. 478-482, 2016.
[22] S.-H. Lin, P.-Y. Chen, and C.-K. Hsu, "Modular Design of High-Efficiency Hardware Median Filter Architecture," IEEE Transactions on Circuits and Systems I: Regular Papers, 2017.
[23] C.-Y. Lien, C.-C. Huang, P.-Y. Chen, and Y.-F. Lin, "An efficient denoising architecture for removal of impulse noise in images," IEEE Transactions on computers, 62(4), pp. 631-643, 2013.
[24] Y.-H. Peng, Development and Implementation of Efficient Test Methods for Image Processing Circuits. Master’s Thesis of Department of Electrical Engineering. Kaohsiung National Sun Yat-Sen University,2015
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code