臺灣博碩士論文加值系統

資訊科技的進步，造成多媒體資料與日俱增，因此以內容為導向的影像擷取技術部分就愈顯得重要。在本研究中，我們計畫了二種新的方法來作數位化的彩色影像擷取。首先第一種方法是以矩量保持原理的技術來發展影像資料庫檢索系統。一張輸入的影像在經過彩色矩量保持以及相似的顏色合併的處理後，所得到的少數主要代表顏色值和其直方圖做為特徵值來求取相近的影像擷取。第二種方法則是彩色位元分解技術。在一張影像之每個像素的三原色，經由彩色位元分解轉化成二進位的數值所構成八個位元平面，同時計算每個位元平面中1的個數做為其影像之特徵值來做影像比對。同時也嘗試將彩色矩量保持技術與彩色位元分解技術兩者混合應用以求較佳的存取結果。最後經由實驗結果從1760張的自然影像為樣本，有效地驗證所提方法的可行性，並證明這些方法的效益性。

As the use of the Internet and multimedia continue to grow among users, researchers need to develop a good solution for accessing multimedia data. Consequently, content-based image retrieval has become a major research with increasing important. In this study, two novel methods for content-based image retrieval in digital images were proposed. The color moment preserving technique is used in the first approach. An input image will be quantized a few colors by color moment preserving and merge similar colors to produce a few dominant colors. Then the tristimulus values and their color histograms are obtained as the color feature for image retrieval. The second approach is using color bit decomposition technique. The tristimulus values of each pixel in an input image will be decompounded into 8 bit-planes and then the sum of 1’s in each bit-planes is computed as the feature for image matching. At the same time, an additional approach tries to hybridize the both proposed methods in order to get better retrieval results. First, using color moment preserving to quantize image into a few colors and merge similar colors to get dominant colors and their frequencies as the color features, then using color bit decomposition method to extract image features from the quantized image for similarity comparison. Experimental results are given to show the feasibility and effectiveness of all the proposed methods.

CONTENTS
ABSTRACT (in Chinese) I
ABSTRACT (in English) II
ACKNOWLEDGMENTS IV
CONTENTS V
LIST OF TABLES VII
LIST OF FIGURES VIII
CHAPTER 1 INTRODUCTION1
1.1 Research Motivation1
1.2 Image Databases1
1.3 Content-Based Image Retrieval3
1.4 Overview of Proposed Approaches7
1.4.1 Image Retrieval by Color Quantization with Color Moment Preserving Technique7
1.4.2 Image Retrieval by Color Bit Decomposition Technique7
1.5 Contributions of This thesis8
1.6 Thesis Organization9
CHAPTER 2 SURVEYS AND REVIEWS10
2.1 A Survey of Color Feature10
2.1.1 Color Histogram10
2.1.2 Color Quantization11
2.2 A Review of Moment-Preserving Thresholding14
2.3 A Review of Color Moment Preserving15
2.4 A Review of Bit Decomposition17
CHAPTER 3 IMAGE RETRIEVAL BY COLOR QUANTIZATION WITH MOMENT-PRESERVING TECHNIQUE21
3.1 Introduction21
3.2 Proposed Image Retrieval by Color Quantization with Moment-Preserving Technique22
3.2.1 The extraction steps of color features23
3.2.2 The measurement of similarity of color features25
3.3 Experimental Results27
3.4 Summary31
CHAPTER 4 IMAGE RETRIEVAL BY COLOR BIT DECOMPOSITION TECHNIQUE33
4.1 Introduction33
4.2 Proposed Image Retrieval by Color Bit Decomposition Technique34
4.2.1 The feature extraction by color bit decomposition34
4.2.2 The measurement of similarity of color bit decomposition35
4.3 Hybrid of The Proposed Methods35
4.3.1 The feature extraction of the hybrid method36
4.3.2 The measurement of similarity of the hybrid method36
4.4 Experimental Results37
4.4.1 Experimental results of color bit decomposition38
4.4.2 Experimental results of hybrid method45
4.5 Summary48
CHAPTER 5 CONCLUSIONS AND DISCUSSIONS49
5.1 Conclusions49
5.2 Discussions50
BIBLIOGRAPHY53
LIST OF TABLES
Table 2.1 The binary code of each pixel in the image of Fig.2.1………….…………19
LIST OF FIGURES
Fig. 1.1 The classification of image database systems.4
Fig. 1.2 The model of content-based image retrieval.6
Fig. 2.1 The sample values of the original image with size 4 4.18
Fig. 2.2 8 bit-planes are computed from Fig. 2.1 by bit decomposition technique.20
Fig. 3.1 The illustration of the query results with gray building images using color
moment preserving.28
Fig. 3.2 The illustration of the query results with blue sky images using color
moment preserving.29
Fig. 3.3 The experimental results with the percentage of pixels are processed in order to get the top n largest values of frequencies for production the number of dominant colors.30
Fig. 3.4 The average number of dominant colors which are obtained based on the
percentage (70, 80, and 90) of pixels.30
Fig. 3.5 The average retrieval efficiencies of experimental results.31
Fig. 4.1 The retrieval efficiency of color bit decomposition without weighted
value and with different weighted values on each color planes39
Fig. 4.2 The retrieval efficiency of color bit decomposition without and with
weighted value39
Fig. 4.3 The retrieval efficiency of color bit decomposition without and with
weighted value40
Fig. 4.4 The illustration of the query results using color bit decomposition without weighted value41
Fig. 4.5 The illustration of the query results using color bit decomposition with weighted value mentioned in Equation 4.442
Fig. 4.6 The illustration of the query results using color bit decomposition without weighted value43
Fig. 4.7 The illustration of the query results using color bit decomposition with weighted value mentioned in Equation 4.444
Fig. 4.8 The retrieval efficiency of hybrid method45
Fig. 4.9 The illustration of the query results using hybrid method with weighted
values wm and wb are 0.7 and 0.3, respectively.46
Fig. 4.10 The illustration of the query results using hybrid method with weighted
values wm and wb are 0.7 and 0.3, respectively.47
Fig. 5.1 The retrieval efficiency using mass moment technique52

[1] Arnold W.M. Smeulders, Maecel Worring, Simone Santini, Amarnath Gupta and Ramesh Jain, ”Content-Based Image Retrieval at the End of the Early Years,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no.12, pp. 1349-1380, Dec. 2000.
[2] C. Faloutsos, R. Barber, M. Flickner, J. Hafner, W. Niblack, D. Petkovic, and W. Equitz, “Efficient and effective querying by image content,” J. Intell. Inform.Syst., vol. 3, pp. 231—262, 1994.
[3] Pentland, R. W. Picard, and S. Sclaroff, “Photobook: Content-based manipulation of image databases,” Proc. SPIE Storage Retrieval Image Video Databases II, pp. 34—47, Feb. 1994.
[4] H. J. Zhang, C. Y. Low, S. W. Smoliar, and J. H. Wu, “Video parsing retrieval and browsing: An integrated and content-based solution,” Proc. ACM Multimedia ’95, San Francisco, CA, Nov. 5—9, pp.15—24, 1995.
[5] A. Hampapur, A. Gupta, B. Horowitz, C. F. Shu, C. Fuller, J. Bach, M. Gorkani, and R. Jain, “Virage video engine,” Proc. SPIE Storage Retrieval Image Video Databases V, San Jose, CA, pp. 188—197, Feb. 1997.
[6] J. R. Smith and S. F. Chang, “Visualseek: A fully automated content-based image query system,” Proc. ACM Multimedia, Boston, MA, pp. 87—98, Nov. 1996.
[7] W. Y. Ma and B. S. Manjunath, “Netra: A toolbox for navigating large image databases,” Proc. IEEE Int. Conf. Image Processing, vol. 1, Santa Barbara, CA, Oct. 1997, pp. 568—571. CA, pp. 415—426, Jan. 1999.
[8] S. Mehrotra, Y. Rui, M. Ortega, and T. S. Huang, “Supporting content-based queries over images in MARS,” Proc. IEEE Int. Conf. Multimedia Computing Systems, ON, Canada, June 3—6 pp. 632—633, 1997,.
[9] W. Niblack, R. Barber, W. Equitz, M. Flickner, E. Glasman, D. Petkovic, P. Yanker, C. Faloutsos, and G. Taubin, “The QIBC Project: Querying Images by Content Using Color, Texture and Shape.” Proc. of SPIE, Electronic Imaging: Storage and Retrieval for Image and Video Databases, pp. 173-187, Feb. 1993.
[10] M. J. Swain and B. H. Ballard, “Color Indexing,” Int’l J. Computer Vision, vol. 7, no. 1, pp. 11-32, 1991.
[11] B. V. Funt and G. D. Finlayson, ”Color constant color indexing,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no.5, pp.522-529, May 1995.
[12] R. C. Nelson, ”Visual homing using an associative memory,” Biological Cybernetics, vol.65, pp.281-291, 1991.
[13] S. P. Engelson and D. V. McDermott, “Image signatures for place recognition and map construction,” SPIE Proc. Sensor Fusion IV: Control Paradiams and Data Structures, pp.282-293, 1991.
[14] P. Heckbert, “Color image quantization for frame buffer display,” Computer Graphics, vol.16, no.3, pp. 297-307, 1982.
[15] R. S. Gentile, J. P. Allebach, and E. Walowit, “Quantization of color images based on uniform color spaces,” J. Imaging Technology, vol. 16, No. 1, pp. 12-21, 1990.
[16] S. J. Wan, P. Prusinkiewics, and S. K. M. Wong, “Variance-based color image quantization for frame buffer display,” Color Research and Applications, vol. 15, no. 1, pp. 52-58, 1990.
[17] G. Braudaway, “A procedure for optimum choice of a small number of colors from a large color palette for color imaging,” Proc. Electronic Imaging ’86, San Francisco, CA, pp. 75-79, 1986.
[18] Ching-Yung Yang; Ja-Chen Lin, ”Color quantization by RWM-cut,” IEEE Proceedings of the Third International Conference, vol. 2, pp. 669 —672, 1995.
[19] J. T. Tou, and R. C. Gonzalez, Pattern recognition principles, Addison-Wesley, 1974.
[20] M. Celenk, “A color clustering technique for image segmentation,” Computer Vision, Graphics and Image Processing, vol. 52, pp.145-170, 1990.
[21] Z. Xiang, “Color image quantization by minimizing the maximum intercluster distance,” ACM Tran. on Graphics, vol.16, no.3, pp. 260-276, 1997.
[22] Xia Wan and C. C. Jay Kuo, “Image retrieval with an octree-based color indexing scheme,” IEEE International Symposium on Circuits and Systems, pp. 1357-1360, June 9-12, 1997.
[23] Xia Wan and C. C. Jay Kuo, “A new approach to image retrieval with hierarchical color clustering,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 8, no. 5, pp.628-643, Sep. 1998
[24] R. Balasubramanian, C. A. Bouman, and J. P. Allebach, “Sequectial scalar quantization of color images,” J. Electronic Imaging, vol. 3, no. 1, pp. 45-59, 1994.
[25] S. C. Cheng, C. K. Yang, “A fast and novel technique for color quantization using reduction of color space dimensionality,” Pattern Recognition Letters, vol. 22, pp.845-856, 2001.
[26] A. Rosenfeld and A. C. Kak, Digital Picture Processing, vol. I, NY: Academic Press, 1982.
[27] J. S. Weszka, “A survey of threshold selection techniques,” Computer Vision, Graphics, Image Processing, vol. 7, pp. 259-265, 1978.
[28] W. H. Tsai, “Moment-preserving thresholding:a new approach,” Computer Visioin,Graphics, Image Processing, vol.29, pp. 377-393,1985.
[29] C. K. Yang, T. C. Wu, J. C. Lin, and W. H. Tsai, ”Color image sharpening by moment-preserving technique,” Signal Processing, vol.45, pp.397-403, 1995.
[30] Lin Yin, “Stack Filter Design: A Structural Approach,” IEEE Trans. on SP, vol.43, no.4, pp.831-840, April 1995.
[31] P. Kuesmaner, “Optimal Stack Filter under Rank Selection and Structural Constraints,” Singal Processing, 41, pp.309-338, 1995.
[32] Xia-mu Niu, Zhe-ming Lu, and Sheng-he Sun, “Digital Watermarking of Still Images with Gray-Level Digital Watermarks,” IEEE Trans. on Consumer Electronics, vol.46, no.1, pp.137-145, Feb 2000.
[33] William K. Pratt, Digital Image Processing, NewYork: Wiley-Interscience, Second Edition, 1991.
[34] B. M. Mehtre, M. S. Kankanhalli, and W, -F. Lee, ”Content-Based Image Retrieval Using A Composite Color-Shape Approach,” Information Processing & Management, vol. 34, no. 1, pp.109-120, Jan 1998.