臺灣博碩士論文加值系統

影像對比強化演算法通常設計用來調整對比度以符合人類的視覺感知。而直方圖均衡化在影像對比強化是一個非常廣泛好用並且受歡迎的技術。然而，此方法有時會造成過度強化、失真、或在處理圖像中某些部分細節損失，而使處理後的影像不自然。因此，這篇論文提出了一個新的補償直方圖等化方法。最初直方圖等化是運用計算機率密度函數得到累積分布函數再做亮度映射。而此論文提出的技術是將由本篇論文定義的範圍分布函數作為約束條件，來修改機率密度函數再實行直方圖等化。因此，此影像增強方法在細節上未有任何致命的損失。經由像素亮度值重新映射後，這個方法達到一個方便且有效的方式來控制對比加強的程度。
這個方法可以運用在高動態範圍影像與低動態範圍影像上。為了令本演算法能適用於更多種不同的影像儲存方式，因此結合一個簡單的前處理方法來對高動態範圍影像作處理，使其能應用的更加廣泛。
實驗結果表明，該提出的方法在評測影像品質的IFC值方面比現有的一些基於直方圖等化改進方法可達到更好的結果。另外為了得到一個更理想的結果，採用一個融合演算法使用不同參數去結合處理後的影像。我們相信它是一個值得進一步探討的方法。

Image contrast enhancement algorithms have been designed to adjust contrast conforming to human visual perception. Histogram equalization (HE) is a very widely used and a popular technique for image contrast enhancement. However, it may produce over-enhancement, washed out, and detail loss in some parts of the processed image and thus makes the processed image unnatural. This thesis proposes a novel compensatory histogram equalization method. Originally when applying HE, it needs to map intensities by calculating the cumulative distribution function (CDF) which is derived from the probability density function (PDF). The proposed technique modifies the PDF of an image by using the range distribution function (RDF) which is defined in this thesis as the constraint prior to the process of HE, so that it performs the enhancement on the image without making fatal loss of details. By remapping intensity levels, this approach provides a convenient and effective way to control the enhancement process.
The proposed method can be applied on high dynamic range (HDR) images and low dynamic range (LDR) images. To adapt more different kinds of image store technologies, it combines a simple preprocessing method on HDR images. Therefore, this method can be widely used on more kinds of image formats.
Finally, experimental results show that the proposed method can achieve better results in terms of Information Fidelity Criterion (IFC) values, the image quality evaluation, than some previous modified histogram-based equalization methods. Further, a fusion algorithm is adopted to combine processed images with different parameters for an optimal result. We believe that it is a strategy worthy for further exploration.

Contents i
List of Tables iii
List of Figures iv
Chapter 1 Introduction 1
Chapter 2 Background 3
2.1 Histogram Equalization 3
2.1.1 Histogram 3
2.1.2 Histogram Equalization 4
2.1.3 Weighted Thresholded Histogram Equalization 5
2.1.4 Modified Histogram Equalization 7
2.2 The Color Space 9
2.2.1 HSV color model 10
2.3 Power-Law (Gamma) Transformation 13
2.4 Image Fusion 15
2.5 Image Quality Assessment 19
Chapter 3 The Proposed Algorithm 24
3.1 Framework of the proposed algorithm 24
3.2 Partitioned Dynamic Range Histogram Equalization 26
3.2.1 Histogram Equalization 26
3.2.2 PDRHE 27
3.3 Combined Partitioned Dynamic Range with Histogram Equalization (CPDRHE) 33
3.4 Improvement based on Local Characteristics 38
Chapter 4 Simulation Results and Comparisons 40
4.1 Experimental Results of CPDRHE 40
4.1.1 Parameter discussion 40
4.1.2 Partitioned various bin numbers and parameter α discussion 42
4.2 Comparison with Other Approaches 45
4.3 Experimental Results of Improvement based on Local Characteristics 52
4.4 More Results 55
Chapter 5 Conclusion and Future Work 60
5.1 Conclusion 60
5.2 Future Work 60
Bibliography 62

[1]Grokking the GIMP by Carey Bunks,
http://gimp-savvy.com/BOOK/
[2]Digital Tones and Exposure Zones,
http://www.rags-int-inc.com/PhotoTechStuff/TonesnZones/
[3]A. K. Jain, Fundamentals of Digital Image Processing, Englewood Cliffs, NJ: Prentice-Hall, 1989.
[4]A. Vanmali, S. Deshmukh, and Vikram M. Gadre ,Low Complexity Detail Preserving Multi-Exposure Image Fusion for Images with Balanced Exposure, Communications (NCC), 2013 National Conference on , Page(s): 1-5
[5]B. Liu, W. in, Y. Chen, C. Liu, and L. Li ,“Contrast Enhancement using Non-overlapped Sub-blocks and Local Histogram Projection, IEEE Transactions on Consumer Electronics, Vol. 57, No. 2, May 2011
[6]C. H. Ooi and N. A. M. Isa, “Quadrants Dynamic Histogram Equalization for Contrast Enhancement, IEEE Transactions on Consumer Electronics, Vol. 56, No. 4, November 2010
[7]D. Sheet, H. Garud, A. Suveer, M. Mahadevappa, and J. Chatterjee, “Brightness Preserving Dynamic Fuzzy Histogram Equalization, IEEE Transactions on Consumer Electronics, Vol. 56, No. 4, November 2010
[8]I. R. Khan*, Z. Huang, F. Farbiz, and C. M. Manders, “HDR Image Tone Mapping Using Histogram Adjustment Adapted to Human Visual System, ICICS 2009
[9]J. Duan and G. Qiu Fast Tone Mapping for High Dynamic Range Images, IEEE Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04) 2004 , Page(s): 847- 850 Vol.2 [sparse region]
[10]K. Wongsritong, K. Kittayaruasiriwat, F. Cheevasuvit, K. Dejhan, and A. Somboonkaev, Contrast Enhancement Using Multi-Peak Histogram Equalization With Brightness Preserving, in Proceedings of IEEE Asia-Pacific Conference on Circuits and Systems, Chiangmai, Taiwan, pp. 455-458, Nov 1998.
[11]M. Hanmandlu, O. P. Verma, N. K. Kumar and M. Kulkarni, A Novel Optimal Fuzzy System for Color Image Enhancement Using Bacterial Foraging, IEEE Transactions on Instrumentation and Measurement, 2009, Vol. 58, Issue. 8, Page(s): 2867-2879
[12]M. M. Naushad Ali and M. Abdullah-Al-Wadud, “Image Enhancement Using a Modified Histogram Equalization, T.-h. Kim et al. (Eds.): SIP/WSE/ICHCI 2012, CCIS 342, pp. 17–24, 2012
[13]M. Abdullah-Al-Wadud, A Modified Histogram Equalization for Contrast Enhancement Preserving the Small Parts in Images, IJCSNS International Journal of Computer Science and Network S 2 ecurity, VOL.12 No.2, February 2012
[14]P. Shanmugavadivu, K. Balasubramanian and K. Somasundaram, “Modified Histogram Equalization For Image Contrast Enhancement Using Particle Swarm Optimization, International Journal of Computer Science, Engineering and Information Technology (IJCSEIT), Vol.1, No.5, December 2011
[15]Q. Tian and J. Duan, Local Histogram Modification Based Contrast Enhancement, ICALAP, IEEE 2012
[16]Q. Wang and R. Ward, Fast image/video contrast enhancement based on weighted thresholded histogram equalization, Consumer Electronics, IEEE Transactions on, 53(2):757–764, May 2007.
[17]R. C. Gonzalez, R. E. Woods, Digital Image Processing, 2nd ed. Reading, MA: Addison-Wesley, 1992.
[18]S. K. Naik and C. A. Murthy, “Hue-preserving color image enhancement without gamut problem, IEEE Trans. Image Process., vol. 12, no. 12, Page(s): 1591–1598, Dec. 2003.
[19]S. D. Chen, A. R. Ramli, “Contrast Enhancement using Recursive Mean-Separate Histogram Equalization for Scalable Brightness Preservation, IEEE Transactions on Consumer 1302 Electronics, Vol. 49, No. 4, NOVEMBER 2003
[20]S. C. Pei, Y. C. Zeng, and C. H. Chang, Virtual restoration of ancient Chinese paintings using color contrast enhancement and lacuna texture synthesis, IEEE Trans. Image Processing, vol. 13, pp. 416–429, 2004.
[21]H. R. Sheikh, A. C. Bovik, G. de Veciana, “An Information Fidelity Criterion for Image Quality Assessment Using Natural Scene Statistics, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 14, NO. 12, DECEMBER 2005
[22]T. L. Qian, S. Shafie, M. I. Saripan, A Local Tone Mapping Operator for High Dynamic Range Images, Modeling, Simulation and Applied Optimization (ICMSAO), 2011 4th International Conference
[23]Y. T. Kim, Contrast enhancement using brightness preserving bihistogram equalization, IEEE Trans. Consumer Electronics, vol. 43, no. 1, pp. 1–8, Feb 1997.
[24]Y. K. Kim, J. K. Paik, and B. S. Kang, Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering, IEEE Trans. Consumer Electronics, vol. 44, no. 1, pp. 82–86, Feb 1998.