針對不同色彩空間之一致性色彩量化法

A universal color quantization for different color spaces

游佳惠(Chia-Hui Yu)

指導教授 ： 陳淑媛

元智大學/資訊學院/資訊工程學系/碩士(2002年)

摘要

本篇論文主要是針對各種不同的色彩空間，提出一致性的色彩量化法。首先，針對一般常用的色彩空間，如：RGB、YCrCb、YIQ、I1I2I3、HSV、L*a*b*及L*u*v*，比較分析不同色彩空間之差異性，並分析實際彩色影像色彩使用分布情形。再根據這些分析資料，設計一以檢索為目的且適用於不同色彩空間的一致性色彩量化法。最後將所提方法應用於各不同色彩空間進行色彩檢索，以評估其效能。實驗結果證實所提色彩量化法不只是對於各不同色彩空間之色彩檢索確實有效，而且優於其他現有彩色量化法。

關鍵字

影像檢索 ； 色彩空間 ； 色彩量化法

並列摘要

This study proposes a universal color quantization for different color spaces. First, we analyze and compare the differences between common used color spaces, for example, RGB, YCrCb, YIQ, I1I2I3, HSV, L*a*b* and L*u*v*. Second, we analyze the distributions of colors used for real color images. On the basis of the analysis, a universal color quantization is proposed for color image retrieval in various color spaces. Experimental results show that that the proposed color quantization is effective for color image retrieval and superior to other methods.

並列關鍵字

image retrieval ； color space ； color quantization

參考文獻

[1] D.A. Adjeroh and M.C. Lee, “An occupancy model for image retrieval and similarity evaluation,” IEEE Transactions on Image Processing, vol. 9, pp. 120-131, 2000.

[2] D. Androutsos, K.N. Plataniotis, and A.N. Venetsanopoulos, “A novel vector-based approach to color image retrieval using a vector angular-based distance measure,” Computer Vision and Image Understanding, vol. 75, pp. 46-58, 1999.

[4] A.P. Berman and L.G. Shapiro, “A flexible image database system for content-based retrieval,” Computer Vision and Image Understanding, vol. 75, pp. 175-195, 1999.

[5] A.D. Bimbo, M. Mugnaini, P. Pala and F. Turco, “Visual querying by color perceptive regions,” Pattern Recognition, vol. 31, pp. 1241-1253, 1998.

[6] E. Boldrin and R. Schettini, “Faithful cross-media color matching using neural networks,” Pattern Recognition, vol. 32, pp. 465-476, 1999.