本篇論文所提出兩種改良式的影像增強方法，主要是能夠解決影像亮度偏暗與對比過低的影像。在灰階影像中，提出兩種方法，一種是自動可調整亮度變化的適應性三分直方圖均化法（Adaptive Trichotomy Histogram Equalization），另外一種是利用影像增強中Gamma校正的概念，設計出一種自動可調整亮度變化的適應性三分Gamma校正法（Adaptive Trichotomy Gamma Correction），兩者皆可以達到特別增強昏暗影像的效果。

此兩種方法，也適合應用在彩色影像中，本篇論文直接在色彩RGB模型中，個別做適應性三分直方圖均化法以及適應性三分Gamma校正法，此兩種方法皆能夠降低色彩失真的可能性，且適應性三分Gamma校正法則是用查表的方式來進行影像增強，所以速度較快，很適合用在即時性系統。

This thesis presents two approaches of refinement image enhancements, primarily aiming to improve the brightness and low contrast images. We first propose two methods for gray images. One is Adaptive Trichotomy Histogram Equalization that can automatically adjust brightness change. The other is a design of Adaptive Trichotomy Gamma Correction that can automatically adjust brightness change by using the concept of Gamma correction in image enhancement. Both approaches can enhance very dark images.

These two approaches can also be applied to color images. Specifically, we use the approaches of Adaptive Trichotomy Histogram Equalization and Adaptive Trichotomy Gamma Correction directly in color RGB model. Both approaches can reduce the possibility of color uncorrected. The approach of Adaptive Trichotomy Gamma Correction adopts look-up table to enhance images, and therefore is very efficient in performance and is ideal for real-time applications.

[1] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Aaddison-Wesley, New York, 2nd ed., 1992.
[2] T. Y. Ma,“A Novel Approach for Enhancing Color Images Using Dichotomy Histogram Equalization and Weighted RGB”, M.S. Thesis, Yuan-Ze University, 2001.
[3] W. B. Liu,“A Fast Approach for Enhancing Sequence of Images Using Dichotomy Histogram Equalization”, M.S. Thesis, Yuan-Ze University, 2002.
[4] Y. T. Kim,“Contrast enhancement using brightness preserving bi-histogram equalization,”IEEE Transaction on Consumer Electronics, Vol. 43, No. 1, pp. 1-8, 1997.
[5] Y. Wang, Q. Chen and B. Zhang,“Image enhancement based on equal area dualistic sub-image histogram equalization method,”IEEE Transaction on Consumer Electronics, Vol. 45, No. 1, pp. 68-75,1999.
[6] S. Y. Kim, D. Han, S. J. Choi, and J. S. Park,“Image contrast enhancement based on the piecewise-linear approximation of CDF,” IEEE Transaction on Consumer Electronics, Vol. 45, No. 3, pp. 828-834, 1999.
[7] T. K. Kim, J. K. Paik and B. S. Kang, “Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering,” IEEE Transactions on Consumer Electronics, Vol. 44, No.1, pp.82-87, 1998.
[8] R. Gordon, A. P. Dhawan, and G. Buelloni,“Enhancement of mammographic feature by optimal adaptive neighborhood image processing,”IEEE Transaction on Medical Image, Vol. MI-5, No. 1. pp. 8-15, 1986.
[9] A. F. Laine, S. Schuler, J. Fan, and W. Huda,“Mammographic feature enhancement by multiscale analysis,” IEEE Transaction on Medical Image, Vol. 57, No. 4, pp. 725-740, 1994.
[10] A. Laine and S. Song,“Multiscale wavelet representations for mammography,” Proc. SPIE Conf. Math. Methods in Medical Image, pp.306-316, 1992.
[11] A. Laine and S. Song,“Wavelet processing techniques for digital mammography,” Proc. SPIE Conf. Visualization in Biomed. Comput., pp. 610-624, 1992.
[12] M. S. Shyu and J. J. Leou,“A Genetic algorithm approach to color image enhancement,” Pattern Recognition, Vol. 31, No. 7, pp. 871-880, 1998.
[13] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, Brooks/Cole, C.A., 1999.
[14] P. E. Trahanias and A. N. Venetsanopoulous,“Color image enhancement through 3-D histogram equalization,” IEEE 11th IAPR Int. Conference on Pattern Recognition, Canada, Vol. III, pp. 545-548, 1992.
[15] J. Y. Kim, L. S. Kim, and S. H. Hwang, “An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization,” IEEE Transaction on Circuits and Systems for Vedio Technology, Vol. 11, No. 4, April 2001.
[16] R. Gordon, A. P. Dhawan, and G. Buelloni,“Enhancement of mammographic feature by optimal adaptive neighborhood image processing,” IEEE Transaction on Medical Image, Vol. MI-5, No. 1. pp. 8-15, 1986.
[17] J. G. Leu,“Image contrast enhancement based on the intensities of edge pixels,” CVGIP: Graphical Models and Image Processing, Vol. 54, No. 6, pp. 497-506, 1992.
[18] S. Benabdelkader and M. Boulemden, “Recursive algorithm based on fuzzy 2-partition entropy for 2-level image thresholding,” Pattern Recognition, Vol. 38, No. 8, pp.1289-1294, 2005.
[19] B. T. Chen, Y. S. Chen, and W. H. Hsu, “Automatic histogram specification based on fuzzy set operations for image enhancement,” IEEE Signal Process. Letters, Vol.2, No.2, pp.37-40, 1995.
[20] R. Gordon and A. P. Dhawan, “Relay to comments on enhancement of mammographic feature by optimal adaptive neighborhood image processing,” IEEE Transaction on Medical Image, Vol. MI-6, No. 1, pp. 82-83, 1987.
[21] G. Aviram and S. R. Rotman, “Analyzing the improving effect of modeled histogram enhancement on human target detection performance of infrared images,” Infrared Physics & Technology, Vol. 41, No. 3, pp. 163-168, 2000.