Evaluation Methodology for Image Testbed and Content-Based Retrieval

该项目旨在为基于内容的图像检索开发一种评估方法。研究内容包括：(1)测量图像试验台的复杂度，定量地确定从图像试验台检索图像的难易程度；(2)比较不同检索方法的性能，定量地给出检索方法性能的客观排名。本课题设计了图像特征表示的总体框架，并以此为载体对图像进行统计分析，为评价方法的建立奠定基础。利用该框架，评价方法可以通过图像数据库的交叉熵来衡量图像数据库的复杂性，并根据图像数据库的交叉熵对检索方法进行排序。因此，在支持图像查询方面，可以比较不同的图像测试平台的复杂度。此外，在不使用查询的情况下，检索技术可以相互比较，从而避免了人为的主观性。在这个项目中开发的算法将为社区最终建立基于内容的图像检索研究的评估方法的一般理论提供宝贵的资产。

The project aims at developing an evaluation methodology for content-based image retrieval. The research involves: (1) Measurement of the complexity of image testbeds which can be used to quantitatively determine the degree of difficulty in retrieving images from the image testbeds, and (2) Comparison of the performance of different retrieval approaches which can quantitatively give an objective ranking of the performance of the retrieval approaches. The project designs a general framework of image feature representations which can be used as a vehicle to conduct statistical analysis on images and forms a basis for establishing the evaluation methodology. Using this framework,the evaluation method can measure the complexity of the image databases by their cross entropy and rank the retrieval approaches by their cross entropy with respect to a particular testbed. The image testbeds can thus be compared with each other on their complexity in supporting image querying. Furthermore, the retrieval techniques can be compared with each other without using queries so the human subjectivity is avoided. The algorithms developed in this project will be a valuable asset for the community to eventually establish a general theory of the evaluation methodology for content-based image retrieval research.