CBIR论文基于形状的汉画像检索技术研究.docVIP

CBIR论文：基于形状的汉画像检索技术研究 【中文摘要】基于内容的图像检索(Content-based Image Retrieval,简称CBIR)是一种利用图像的视觉特征(颜色、纹理、形状等)进行图像检索的技术。随着计算机科学和数据库技术的发展,CBIR己成为国内外的一个研究热点。论文首先回顾了基于内容的图像检索理论及其应用研究的发展过程,然后对基于内容的图像检索,尤其是基于形状的图像检索领域的技术和现状作了综述,并探讨了其中的一些关键技术。在此基础上,对图像底层的形状特征提取和检索展开详细的研究,其主要工作体现在:1.在分析汉画像实际特点基础上,结合各种图像预处理算法的特点,给出了具体的汉画像预处理过程,特别是汉画像中目标对象区域的获取及像素灰度值调整过程,实验证明是有效的、可行的。2.在利用数学形态学方法提取目标对象并调整了区域像素的灰度值的基础上,以图像的Hu不变矩作为形状特征,构造检索框架,并进行图像检索。3.给出了汉画像图像相似性匹配算法,从图像的形状特征出发,构造相似性匹配函数进行图像的相似度匹配。实验表明该算法有效可行,并具有稳定的检索性能。 【英文摘要】Content-based image retrieval is a kind of image visual features (color, texture and shape, etc.) for image retrieval technologies. Along with the computer science and database technology development, CBIR has become a domestic research hot spot.This paper first reviews the theory of the content-based image retrieval and its development progress .Then,the content-based image retrieval techniques especially the shape retrieval techniques and its current status are reviewed, along with some discussions of the key techniques of image retrieval. On this basis, makes the academic researches on the acquisition and retrieval of low-level contour characteristic.The main contributions of this paper are as follows:1. According to the process and algorithm of image preprocessing, and the characteristics of Han Stone Graving, gives an image pretreatment process, especially detect targets using mathematical morphology and adjust the pixel gray value. The experiment proved that is effective.2. On the base of detecting targets and adjusting pixel gray value, use the invariant moment of image for the shape characteristic and construct the retrieval frame, then realize image retrieval.3. The comparability measurement of the image is given, in which different measurement function of comparability is constructed to match the comparability of the image. The results show that the algorithm is effective and feasible, and hasa stable retrieval performance. 【关键词】CBIR 形状图像检索 不变矩 相似性匹配 【英文关键词】CBIR sha