【作者】 曾智勇；

【导师】 周利华；

【作者基本信息】 西安电子科技大学 ， 计算机应用技术， 2006， 博士

【摘要】 随着互联网的快速发展及各种数字化设备的普及,现代社会中的多媒体信息的数量在迅猛增长,多媒体信息管理的研究得到了越来越多的关注。图像数据库系统在多媒体信息管理的研究中占有特别重要的地位,因为图像不仅是视频的基础,而且图像数据库技术可广泛应用于:多媒体信息系统、数字图书馆、数字博物馆、医学、地理信息数据库、电影工业、视频点播、公共安全及国防等众多领域。因此,如何有效、快速地从大规模图像数据库中检索出所需的图像是目前一个相当重要又具有挑战性的研究课题。基于内容的图像检索技术研究正是为了解决如何有效地从图像数据库中检索出相关图像的问题。近年来,此项技术已成为国内外广泛关注的研究热点。本文主要围绕基于内容图像库检索中图像特征的提取这一关键技术展开研究,系统地探讨了图像底层视觉特征的提取技术,覆盖的内容主要包括图像的颜色特征、形状特征、纹理特征以及颜色的空间分布特征。研究的内容属于目前图像处理和信息检索领域的研究重点,具有相当的理论意义和实际应用价值。本文的主要研究成果总结如下:1.深入分析和研究了基于内容图像检索领域的一些关键技术,如:颜色、形状和纹理等底层图像特征、图像特征间的相似性度量准则、图像数据库的索引机制以及图像检索算法的评价方法等。并且,通过在同一测试环境下的实验,对一些经典算法进行了比较。2.提出了一种基于显著兴趣点颜色及空间分布的图像检索算法。此算法首先使用自适应滤波器对图像进行平滑,然后使用经典的兴趣点检测算法发现兴趣点。由于自适应滤波器具有平滑细节,增强边缘的功能,因此,这种方法能使兴趣点大多存在于图像的显著边缘上。接着设计了一种基于显著兴趣点的环形颜色直方图,它不但利用了兴趣点周围区域的颜色来代表图像的特征,而且考虑了显著兴趣点的空间分布结构。这样,一方面使图像的形状特征与其周围区域的颜色特征有机地结合起来,另一方面又可使颜色产生空间分布信息。图像的相似性度量就是基于这种特征进行的,实验结果表明,这种算法比文献中的经典算法更加有效。3.为了克服传统角检测器在发现兴趣点时不能完全描述图像全局视觉感兴趣的特征的缺点,提出了一种基于小波突出点的图像检索算法。基本思想是把小波突出点作为图像中用户关注的视点线索,通过它们找到视觉重要的全局区域,利用全局区域的颜色特征及空间分布进行图像检索。该方法具更多还原

【Abstract】 With the rapid development of the Internet and digital equipments,the amount of multimedia information being produced, stored and spread is increased rapidly.Therefore, research on multimedia information management is attracting more and more attention. In this research area, image database system plays an important role because of its foundational status of video applications as well as its abroad employment in many important applications such as: multimedia information system, digital library, digital museum, medicine, geographical information database, movie industry, video on demand, common security and military defense. Currently,rapid and effective searching for desired images from large-scale image databases becomes an important and challenging research topic. Content-based image retrieval (CBIR) is the set of techniques to address the problem of retrieving relevant images from an image database based on automatically derived image features. In recent years,CBIR is a very active research direction.In this dissertation,lots of exploratory research work has been done around some key techniques of image feature extraction of CBIR, the low level visual features extraction of images have been studied systematically, which include color, shape, texture, color spatial distribution features and so on. The presented study is the current research focus of image processing and information retrieval. Thus, its research has both the theory and the application value.The main contributions of this dissertation are summarized as follows:1. Several key techniques and algorithms of CBIR are deeply analyzed and discussed,such as,color model, the low-level feature descriptions including color, shape, and texture,the similarity measure between the features,image database indexing methods and the evaluation methods of image retrieval algorithms. Moreover, by some experiments tested under the same conditions, we report the comparison results of many classical methods.2. An image retrieval approach based on salient interest points is proposed. This algorithm firstly uses an adaptive filter to process the image. Then, the popular way is adopted to detect the interest points. The extracted interest points are always located in the salient edges since the adaptive filter has the ability to smooth the details and enhance the salient edges of the image. Afterwards, an更多还原