(3.238.240.197) 您好!臺灣時間:2021/04/12 03:47
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:盧彥瑋
研究生(外文):Yen-Wei Lu
論文名稱:基於類神經網路的半色調與連續調之轉換技術與壓縮
論文名稱(外文):Halftone/Contone Conversion Using Neural Network and Its Application to Image Compression
指導教授:蘇文鈺蘇文鈺引用關係
指導教授(外文):Wen-Yu Su
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系碩博士班
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:2003
畢業學年度:91
語文別:中文
論文頁數:79
中文關鍵詞:連續調類神經網路壓縮半色調
外文關鍵詞:halftonecontonecompressionneural networksRBF
相關次數:
  • 被引用被引用:2
  • 點閱點閱:185
  • 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:22
  • 收藏至我的研究室書目清單書目收藏:0
不論是在彩色或是灰階的影像,halftoning [17] 對於影像印刷設備來說確實是一項相當重要的技術。其中dithering [17] 和error diffusion [17] 是最普遍的兩種halftoning技術。然而對於這兩種方法所產生的半色調影像 (halftone) [17] 的評估方式主要還是靠個人主觀的感覺。另一方面,對於inverse halftoning [17] 的相關研究並不多,主要是因為它的應用範圍相當有限。不過有時候當我們想要在螢幕上顯示影像,還是需要將半色調影像轉回連續調影像 (contone) [17]。在這篇論文裡面,首先我們提出一個以類神經網路為基礎的inverse halftoning方法。這個方法結合了兩個階段的處理過程。第一個階段是以一個RBF (Radial Basis Function) [11] 的類神經網路架構來完成基本的半色調轉連續調處理。第二個階段則是利用MLP (Multi-Layer Perceptron) [11] 的類神經網路架構來做後處理。在經過inverse halftoning的處理後,我們可以利用PSNR比較重建後的影像與原本影像之間失真的程度。接著我們規劃出另一個利用feedforward 類神經網路來達成error diffusion的halftoning過程。而重建後的影像與原影像之間的誤差會被反饋到整個類神經網路,這整個類神經網路包含了inverse halftoning的網路與halftoning的網路。之所以會將兩部分類神經網路結合是因為結合後有助於兩個部分在影像品質上的提昇。電腦模擬的結果顯示我們的方法在半色調影像上提供較佳的視覺品質,而在inverse halftoning也能有較高PSNR。此外,我們也使用BACIC [26] 的編碼方法來壓縮半色調影像,配合inverse halftoning希望能增加inverse halftoning的實用性。
Halftoning [17] technologies are important to an image printing device, be it for color or grey scale images. Dithering and error diffusion [17] are two most popular techniques. However, the performances provided by these methods are mostly evaluated subjectively. On the other hand, inverse halftoning techniques are less researched because the applications are much rarer. However, it is sometimes necessary to convert a halftone image to a contone (Continuous Tone) [17] image when one wants to see it in devices such as computer monitors. In this thesis, a Neural Network based inverse halftoning method is first proposed. This method combines two stages of processing. The first stage is a RBF (Radial Basis Function) network [11] which performs the basic inversion. The second stage is a MLP (Multi-Layer Perceptron) network [11] for post-processing. After inverse halftoning processing, we are able to compare the reconstructed image and the original image using distortion measure such as MSE (Mean Square Error or PSNR). Next, we formulate the halftoning processing as another feedforward neural network based on error diffusion methods. The errors between the original images and the reconstructed images are fed back to train the overall network which includes the two-stage inverse halftoning network and the halftoning network such that both processings achieve the best quality when combined together. Computer simulations show that the proposed schemes provide better visual quality of halftone images and higher PSNR performance compared to other inverse halftoning methods.
第1章:簡介9
第2章:影像半色調技術的回顧11
2.1基本觀念11
2.2半色調的發展13
2.3Noise Encoding14
2.3.1Random Dither14
2.3.2Ordered Dither16
2.4Clustered Dot Ordered Dither18
2.5Dispersed Dot Ordered dither20
2.6Error Diffusion23
2.7Summary26
第3章:Inverse Halftoning27
3.1Look Up Table (LUT) Inverse Halftoning28
3.1.1LUT Inverse Halftoning 演算法29
3.2RBF Networks Inverse Halftoning31
3.2.1RBF Networks31
3.2.2RBF Inverse Halftoning 演算法34
3.3Multi Layer Perceptrons (MLP) 演算法38
3.4實驗結果與比較42
3.4.1實驗142
3.4.2實驗244
第4章:Halftoning by Inverse Halftoning55
4.1演算法與網路架構55
4.2實驗結果與比較60
4.2.1實驗160
4.2.2實驗262
第5章:半色調影像壓縮69
5.1BACIC 演算法69
5.2實驗結果72
第6章:結論與未來研究方向75
參考文獻76
[1]J. Allebach and P. W. Wong, “Introduction to digital halftoning,” Tutorial notes of IS&Ts NIP 13, Seattle, Washington, November 2, 1997.
[2]P. G. Anderson, “Linear pixel shuffling for image processing: an introduction,” JEI, Vol. 2, pp. 147-154, 1993.
[3]P. G. Anderson, “Linear pixel shuffling applications,” ICPS’94: The Physics and Chemistry of Image Systems─IS&Ts 47th Annual Conf., Rochester, NY, 1994, Vol. II, pp. 506-508.
[4]P. G. Anderson, “An algebraic mask for halftone dithering,” ICPS’94: The Physics and Chemistry of Image Systems─IS&Ts 47th Annual Conf., Rochester, NY, 1994, Vol. II, pp. 487-489.
[5]B. E. Bayer, “An optimum method for two-level rending of continuous-tone pictures,” IEEE Int. Conf. Commum., Vol.1, pp. 26-11-26-15, 1973.
[6]C. G. Boncelet, “Block arithmetic coding for source compression,” IEEE Trans. Inform. Theory, vol. IT-39, pp. 1546-1554, Sept. 1993.
[7]N. Damera-Venkata, T. D. Kite, M. Ven kataraman, and B. L. Evans, “Fast blind inverse halftoning,” in Proc. Image Processing, Oct. 1998, pp. 64-68.
[8]P. Fink, PostScript Screening: Adobe accurate screens, Adobe Press, Mountain View, CA, 1992, Chapter 5, pp. 69-75.
[9]R. Floyd and L. Steinberg, “An adaptive algorithm for spatial grey scale,” Proc. Soc. Info. Display, Vol. 17, p. 75, 1976.
[10]W. W. Goodall, “Television by pulse code modulation,” Bell Sys. Tech. J., Vol. 30, pp. 33-49, 1951.
[11]Simon Haykin, “Neural Networks: A Comprehensive Foundation,” 2nd edition, Prentice Hall, 1999.
[12]S. Hein and A. Zakhor, “Halftone to continuous-tone conversion of error-diffusion coded images,” IEEE Trans. Image Processing, vol. 4, pp. 208-216, Feb. 1995.
[13]M. Hepher, “A comparison of ruled and vignetted screens,” Penrose Annual, Vol. 47, pp. 166-177, 1953.
[14]H. Inose and Y. Yasuda, “A unity bit coding method by negative feedback,” Proc. IEEE, Vol. 51, pp. 1524-1535, 1963.
[15]J. F. Jarvis, C. N. Judice, and W. H. Ninke, “A survey of techniques for the display of continuous-tone pictures on bilevel displays,” Comp. Graph. Image. Proc., Vol. 5, pp. 13-40, 1976.
[16]C. N. Judice, J. F. Jarvis, and W. H. Ninke, “Using ordered dither to display continuous tone pictures on AC plasma panel,” Proc. SID, Vol. 15, pp. 161-169, 1974.
[17]H. R. Kang, "Digital Color Halftoning,” SPIE Optical Engineering Press, 1999.
[18]H. R. Kang, “Color technology of electronic imaging devices,” SPIE Press, Bellingham, Washington, 1996, Chapter 9, pp. 208-260.
[19]T. Kite, N. D. Venkata, B. Evans, and A. C. Bovik, “A high quality, fast inverse halftoning algorithm for error diffused halftones,” in Proc. ICIP’98, vol. 2, Chicago, IL, 1998, pp. 59-63.
[20]L. E. Levy and M. Levy, “Screen for photomechanical printing,” US patent 492333, 1893.
[21]J. O. Limb, “Design of dither waveforms for quantized visual signals,” Bell Sys. Tech. J., Vol. 48, pp. 2555-2582, 1969.
[22]B. Lippel and M. Kurland, “The effect of dither on luminance quantization of pictures,” IEEE Trans. Commun. Tech., Vol. 6, pp. 897-888, 1971.
[23]M. Mese and P.P. Vaidyanathan, "Look Up Table (LUT) inverse halftoning," Proc. of IEEE ISCAS, Geneva, June 2000.
[24]T. Mitsa and K. J. Parker, "Digital Halftoning Technique Using a Blue Noise Mask," J. Opt. Soc. Am. A, Vol. 9, No. 11, pp. 1920-1929, November 1992.
[25]A. N. Netravali and E. G. Bowen, "Display of dithered images," Proc. SID, vol. 22, no. 3, pp. 185-190, 1981.
[26]Maire D. Reavy and Charles G. Boncelet, “An algorithm for compression of bilevel images,” IEEE Trans. Image Processing, vol. 10, pp. 669-676, May 2001.
[27]M. Riedmiller and H. Braun, “A direct adaptive method for faster backpropagation learning: the RPROP algorithm,” Proceeding of the ICNN, San Francisco, 1993.
[28]M. Riedmiller, “RPROP- description and implementation details,” technical report, University of Karlsruhe, January 1994.
[29]M. R. Schroeder, “Images from computer,” IEEE Spectrum 6, pp.66-78, 1969.
[30]L. Scuchman, “Dither signals and their effect on quantization noise,” IEEE Trans. Commun. Technol., Vol. COM-12, pp. 162-164, 1964.
[31]K. E. Spaulding, R. L. Miller, and J. Schildkraut, “Methods for generating blue-noise dither matrices for digital halftoning,” JEI, Vol. 6, pp. 208-230, 1997.
[32]P. Stucki, “MECCA-a multiple-error correcting computation algorithm for bilevel image hardcopy reproduction,” Research report RZ1060, IBM Research Lab., Zurich, Switzerland, 1981.
[33]W. H. F. Talbot, “Improvement in the art of engraying,” British Patent Specification No. 565, October 29, 1852.
[34]R. Ulichney, “Digital halftoning,” MIT Press, Cambridge, MA, 1987, Chapter 8, pp. 233-333.
[35]B. Widrow, “Statistical analysis of amplitude-quantized sampled-data system,” Trans. AIEE (Application and Industry) part II, Vol. 79, pp. 555-568, 1960.
[36]Edward Wilson and Stephen M. Rock, “Gradient-based parameter optimization for systems containing discrete-valued functions,” Int. J. Robust Nonlinear Control, vol. 12, pp. 1009-1028, 2002.
[37]P. W. Wong, “Inverse halftoning and kernel estimation for error diffusion,” IEEE Trans. Image Processing, vol. 6, Nov. 1997.
[38]Z. Xiong, K. Ramchandran, and M. Orchard, “Inverse halftoning using wavelets,” in Proc. Int. Conf. Image Processing, vol. 1, Lausanne, CH, 1996, pp. 569-572.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
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