• 沒有找到結果。

Image Fusion Using Transform Algorithms with Segmentation 許文豪、劉仁俊 ; 鍾翼能

N/A
N/A
Protected

Academic year: 2022

Share "Image Fusion Using Transform Algorithms with Segmentation 許文豪、劉仁俊 ; 鍾翼能"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

Image Fusion Using Transform Algorithms with Segmentation 許文豪、劉仁俊 ; 鍾翼能

E-mail: [email protected]

ABSTRACT

Image fusion has wide areas of applications, such as computer-aided piloting system, medical imaging, reconstruction of defocused images, and safety inspection. The importance is gaining popularity. A good fused image is obtained by finding the important features of the source images and combining them appropriately. The suitable fusion algorithms might be different for different sources of sensors. For defocused images, edge detection is used for preprocessing. Hence the important features and regions with apparent activity are extracted. Transforms are performed on the regions that contain less variation. Coefficients can then be extracted and fused. The reconstructed image can be obtained by applying an inverse transform. For computer-aided piloting system and medical imaging, redundant wavelet transform is applied and local energy feature is then selected. The main concern is to discriminate features in brightness variation. In such way, the fused image clearly explains the features in the source images. The effectiveness and performance will be demonstrated in the simulation results.

Keywords : image fusion ; edge detection ; DCT ; DWT ; RWT

Table of Contents

封面內頁 簽名頁 博碩士論文授權書...iii 中文摘要...iv 英文摘要...v 誌謝...vi 目錄...vii 圖目錄...ix 表目

錄...xi 第一章 緒論 1.1 研究背景...1 1.2 研究目的...2 1.3 研究 內...3 1.4 論文架...5 第二章 影像分割 2.1 前言...6 2.2 邊界法之影 像分割...7 2.3 臨界值法之四分樹影像分割...8 2.4 四分樹影像分割之智慧型選擇...11 第三章 離 散餘弦轉換和離散小波轉換 3.1 前言...14 3.2 離散小波轉換...15 3.3 離散餘弦轉

換...18 第四章 影像合成法 4.1 影像合成方法簡介... 22 4.2 醫學影像及航空輔助...24 4.3 來源失焦模糊的影像...33 第五章 模擬結果與分析 5.1 效果評量方法...39 5.2 來源失焦影像模 擬測試結果和合成圖...40 5.3 醫學與航空輔助影像模擬合成圖與分析...48 第六章 結論與未來展望 6.1 結

論...54 6.2 未來展望...56 參考文獻...57 REFERENCES

[1] Burt, P. J. and Kolczynski, R. J, “Enhanced image capture through fusion,” in: Proc. 4th Intl. Conference on Computer Vision, pp. 173-182, 1993.

[2] M. Pavel, J. Larimer, and A. Ahumada, “Sensor fusion for synthetic vision,” in Proceedings AIAA conference on Computing in Aerospace, Baltimore, MD, Oct. 1991.

[3] Burt, P. J. “The pyramid as structure for efficient computation,” in Multiresolution Image Processing and analysis(A. Rosenfeld, ED.), pp.6-35, springer-Verlag, New York/Berlin, 1984.

[4] Toet, A.; van Ruyen, L. J. and Valenton, J. M. “Merging thermal and visual images by a contrast pyramid,” in: Optical Engineering, Vol.

28, pp. 789-792, No. 7, 1989 [5] Pramod K. Varshney, Hua-Mei Chen, Liane C. Ramac “Registration and fusion of infrared and millimeter wave images for concealed weapon detection,” Dept. of Electrical and Electronics Engineering Hacettepe University, P532-536, 1999 [6]

Dongmei Yan, Zhongming Zhao, “wavelet decomposition applied to image fusion,” Department of Image Processing, The institute of Remote sensing Applications, CAS, 2001 [7] 李朝欽, “應用小波轉換與四分樹切割之影像合成,” 大葉大學電機工程系碩士論文 [8] J. Vaisey, and A.

Gersho, “image compression with variable block size segmentation,” IEEE trans. On signal processing, vol.40, no.8, pp.2040 — 2060, AUG 1992.

[9] C. Y. Teng and D. L. Neuhoff, “a new quadtree predictive image coder,” image processing 1995. Proceeding, international Conference on VOL.2, pp. 73 — 76, 1995 [10] Y. Chibani and A. Houacine, “On the use of the redundant wavelet transform for multisensor image fusion,” in Proc. IEEE Int. Conf. Electronics, Circuits and Systems, pp.442-445, 2000 [11] Abdallah K. Cherri and Mohammad A. Karim, “optical image processing using symbolic subtitution :median filtering and edge detection,” Department of Electrical Engineering & The Center for

Electro-Optics, university of dayton, 1990 [12] Wu. Xiuqing, Zhou. Rong, Xu. Yunxiang, “A method of wavelet-base edge detection with data

(2)

fusion for multiple images,” Processings of 3rd World Congress on Intelligent Control and Automation, June28-July 2, 2000 [13] R. Gonzalez, R.

wood, “Digital Image Procesing,” Addison-wesley, 1992 [14] K. R. Rao, P. Yip, “Discrete Cosine Transform — Algorithms Advantages, Applications,” Academic press, 1990 [15] S. C. Tai, Y. G. Wu, and C. W. Lin, “An adaptive 3-D discrete cosine transform coder for medical image compression,” IEEE Trans. Inform. Tech, Biomed, Vol.4, pp.259-263, 2000 [16] Guihong Qu, Zhang and Yan, “Medical Image Fusion by Wavelet Transform Modulus Maxima,” Optics Express, August 2001 [17] Li, H. ; Manjunath, B. S. and Mitra, S. K. “Multisensor image fusion using the wavelet transform,” in: Graphical Models and Image Processing, Vol.57, pp. 235-245, No.3, 1995 [18] Yian-Leng Chang;

Xiaobo Li. “adaptive image region-growing,” image processing, IEEE trans on VOLUME.36, pp.868 — 872, NOV, 1994 [19] D. A. Yocky,

“Artifacts in wavelet image merging,” Optical enginnering, Vol.35, pp.2094-2101, No7, 1996 [20] L. J. Chipman, T. M. Orr, “wavelets and fusion,” International Congress on Image Processing, pp.248-251, 1995 [21] H. Li, B. S. Manjunath, S. K. Mitra, “Multisensor image fusion using the wavelet transform,” Graphicals models and image processing, Vol.57, pp.235-245, No3, 1995 [22] Gonzalez, R. C. and Wintz, P.

“digital image processing,” Addison Wesley, Reading, MA, 1997 [23] S. G. Mallat, “A multiresolution signal decomposition:The wavelet transform,” IEEE Trans. On Pattern analysis and machine intelligence, Vol.11, pp.674-693, No7, 1989 [24] T. Ranchin, L. Wald, and M.

Mangolini, “Efficient data fusion using wavelet transform: The case of SPOT satellite images,” in : Proc. SPIE, Vol.2034, S.171-178, 1993 [25]

N. Currie, and et. al., “Infrared and Millimeter wave sensors for military special operations and Law Enforcement Applications,” Int Journ. Of IR and MMW, Vol.17, No.7, 1996.

[26] J. Lu, D. M. Healy, and J. B. Weaver, “Contrast enhancement of medical images using multiscale edge representation,” Opt. Erg, Vol.33, no.7, pp.2151-2161, 1994 [27] H. R. Beom and H. S. Cho, “A sensor based navigation for a mobile robot using fuzzy logic and reinforcing learning,” IEEE Trans. Syst., Man Cybern., vol.25, pp.464-477, Mar. 1995 [28] L. Wald, T. Ranchin, and M. Mangolini, “Fusion of satellite images of different spatial resolutions: assessing the quality of resulting images,” Photogram, Engin. Remote Sensing, Vol.63, no.6, pp.691-699, 1997 [29] Li, Hui; Manjunath, B. S. and Mitra, S. K. “Contour based multisensor image registration,” in Processings 26th Asilomar Confrence on Signal, Systems and Computers, Pacific Grove, CA, pp.182-186, NOV. 1992 [30] Burt, P. J. “The pyramid as a structure for efficient computation,” in: Rosenfeld, A. Multiresolution image processing and analysis, Springer, New York, 1984 [31] K. R. Rao, “Theory and the applications of the discrete cosine transform,” in Jordan, IEEE Eng. conf., Amman, Jordan, pp.259-264, Apr-may 1985 [32] R. C. Reininger and J. D. Gibson, “distributions of the two dimentional DCT coefficients of image,” IEEE trans. On communication, vol. COM-31, pp.835 — 839, JUNE 1983 [33] E. A. Newman and P. H. Hartline, “The infrared vision of snakes,” in Scientific American, Vol.246, p.116-127, No.3, 1982

參考文獻

相關文件

Hence, code for each non zero AC coefficient is composed of a basecode (corresponding to runlength/category) and a code corresponding to offset in.. Standard tables vs

 image processing, visualization and interaction modules can be combined to complex image processing networks using a graphical

In this paper, a novel subspace projection technique, called Basis-emphasized Non-negative Matrix Factorization with Wavelet Transform (wBNMF), is proposed to represent

Lance Williams: Brute Force in image space (shadow maps in 1978, but other similar ideas like Z buffer, bump mapping using textures and so on).. Completely

“A feature re-weighting approach for relevance feedback in image retrieval”, In IEEE International Conference on Image Processing (ICIP’02), Rochester, New York,

Mehrotra, “Content-based image retrieval with relevance feedback in MARS,” In Proceedings of IEEE International Conference on Image Processing ’97. Chakrabarti, “Query

format, Signal acquisition, Wavelet packet analysis , Discrete wavelet transform, Hyperkalemia, Acute myocardial infarction, P wave, QRS complex, T wave, Neural network,

To an accuracy of 3 pixels, 72% of interest points are repeated (have correct position), 66% have the correct position and scale, 64% also have correct orientation, and in total 59%