應用離散小波轉換之彩色影像顏色轉換技術

Applying Discrete Wavelet Transform to Color Transfer Algorithm for Color Images

陳惠欣(Hui-Hsin Chen)

指導教授 ： 吳憲珠

國立臺中科技大學/資訊與流通學院/資訊工程系碩士班/碩士(2014年)

https://doi.org/10.6826/NUTC.2014.00021

摘要

本研究提出DWTCT(Discrete Wavelet Transform to Color Transfer Algorithm)演算法，利用離散小波轉換進行影像顏色轉換處理，其特性在於不同以往的複雜統計方法來改變影像色彩。本論文提出的方法運用離散小波轉換對數位信號有多重解析的特性，透過計算彩色影像的HSV色彩空間中Hue色相值，經過離散小波三階段轉換後所得到的低頻(LL3)為影像中的重要具有顏色資訊和位置分佈資訊，並運用LL3的平均值與標準差，以計算原始影像與參考影像的權重。讓兩影像的LL3值可依據判斷佔有不同的比例，進而改變原始影像中的Hue值，轉換原始影像的顏色。
根據實驗結果，本研究提出的影像色彩轉換技術DWTCT演算法能有效運用離散小波轉換取得具有代表性的色彩特徵和色彩位置分佈特徵，並有效的將參考影像的特徵轉換到原始影像上，讓即使是差異甚大的影像也能不因顏色改變劇烈而過於怪異、產生色塊或無法轉換。

關鍵字

彩色影像顏色轉換 ； HSV色彩空間 ； 離散小波轉換

並列摘要

This study applied Discrete Wavelet Transform (DWT) to color transform for color images, that is different from the used complex statistical methods to calculate and determine during changing colors for the original image. The multi-resolution digital signals from LL3 values of DWT were applied to calculate the characteristics of Hue channel in HSV color space. As important information, the mean and standard deviation of LL3 are taken to determine the weights for original image and reference image individually. The Hue values of the original image were changed according to the LL3 possession of two images. According to the experimental results, the proposed color transform technology for color images can effectively use wavelet transform to obtain representative features. Even there are great color differences between original image and reference image, the original image could still be color changed without weird or unchangeable color.

並列關鍵字

Color transfer for color images ； HSV color space ； Discrete Wavelet Transform

參考文獻

[2]T. Chang and C. C. J. Kuo, “Texture analysis and classification with tree-structured wavelet transform.” IEEE Transactions on Image Processing, Vol. 2, 1993, pp. 429-441.

[5]E. Reinhard, M. Ashikhmin, B. Gooch and P. Shirley, “Color transfer between images.” IEEE Computer Graphics and Applications, Vol.21, No.5, 2001, pp. 34-41.

[8]C. K. Yang and L. K. Peng, “Automatic mood-transferring between color images.” IEEE Computer Graphics and Applications, Vol. 28, No.2, 2008, pp. 52-61.

[1]M. B. Henke-Reed and S. N. C. Cheng, “Cloth texture classification using the wavelet transform.” Journal of Image Science and Technology, Vol. 27, 1993, pp. 610.

[3]S. C. Tan and J. Kittler, “On colour texture representation and classification.” in Proceedings of the 2nd international conference on Image Processing, 1992, pp. 390-395.