摘要
为了能够在建筑彩画数据库系统中自动找出与所给事例彩画相似的彩画及各种相关数据资料,需要进行彩画图像检索。给出了一种基于形状和颜色特征的建筑彩画检索方法,第一步是对彩画基本类型进行检测识别,先对彩画图像进行边缘检测,再利用先验模板对边缘图像进行匹配,然后根据匹配结果来识别彩画的基本类型。第二步是在相同的基本类型中进行相似性匹配,主要是在HSV空间中统计颜色直方图特征矢量,以同类型彩画之间颜色直方图矢量的相似度大小作为检索依据,最后给出检索结果。实验表明,本方法的检索结果更符合人眼对相似性的感知。
Image retrieval technology can be used to find the color painting similarities related to the project and to make full use of relevant data and images from the architectural color paintings database. A retrieval method for architectural color paintings based on shape and color features is set up. The first step is to classify the basic types of architectural color paintings. Then the edges of the color painting image are recorded. Then the detected image is matched by the pre - defined template and the image is classified as to one of the basic types of color paintings according to the matching result. The second step is to calculate the similarity within the same type of the images. The color histograms of the color paintings in HSV space are statistically calculated and the search is carried out by the similarity of the histograms within the same type of the color paintings. Experiments show that the retrieval results reached by the method are similar to that made by the perception of human eyes.
出处
《文物保护与考古科学》
2010年第1期1-7,共7页
Sciences of Conservation and Archaeology
基金
国家科技支撑计划项目资助(2006BAK31B01)
