外文翻译原文-提取颜色特征和动态匹配的图像数据库检索.pdf

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. 9, NO. 3, APRIL 1999 501 Extracting Color Features and Dynamic Matching for Image Data-Base Retrieval Soo-Chang Pei, Senior Member, IEEE, and Ching-Min Cheng Abstract— Color-based indexing is an important tool in image On the contrary, color, unlike image irradiance, can be data-base retrieval. Compared with other features of the image, used to compute image statistics independent of geometrical color features are less sensitive to noise and background compli- variations in the scene [4]. With the help of color-based cation. Based on the human visual system’s perception of color information, this paper presents a dependent scalar quantization features, Swain and Ballard have presented a color index approach to extract the characteristic colors of an image as color method [5], called the histogram intersection method. In features. The characteristic colors are suitably arranged in order their method, they use the color histograms to create three- to obtain a sequence of feature vectors. Using this sequence of dimensional (3-D) histogram bins for each query image. The feature vectors, a dynamic matching method is then employed to 3-D bins are then matched with those of data-base images match the query image with data-base images for a nonstationary identification environment. The empirical results show that the by using the histogram match value. Although this approach characteristic colors are reliable color features for image data- is useful in many situations, performance