基于联合媒体相关模型的图像标注及其应用计算机应用技术专业论文.docxVIP

优秀毕业论文 精品参考文献资料 AB AB STRACT Automatic image annotation has been an active research topic in recent years due to its potentially fundamental impact on image understandings and that manuaI image annotation for indexing and then later retrieving image collections is an expensive and labor intensive procedure． In this paper,based Co—occurrence Model and Translation Model．it aims at untangling this problem in a novel automatic image annotation using eross—media relevance models．Given all uncaptioned image，in terms of a training set of images， keywords，and blobs，it is to develop probabilistic models to estimate the conditional probability between words and blobs by statistic data．Based on CMRM techn0109ies． this framework does not only manage a training stage in a large scale but also get a better significantly performance in terms of precision and recall． Comprehensive evaluation conducted on Corel image databases shows the ea宅ctiveness and e衔ciencv of the proposed approach． Further,it still remains unclear how to exploit these auto．annotated concepts in image retrieval．This paper tackles this drawback and proposes probabilistic annotation。based cross‘media relevance model， and direct retrieval cross．media relevance model，taking advantage of fixed annotation．based retrieval model．The first approach lS to annotate each image in datasets using CMRM techniques，index the annotations，and then perform text retrieval in the usual manner．An altemative to fixed —len垂h annotation is to use probabilistic models computing relevant degrees of a given query and datasets to rank images．The last one is to convert the query into the language of blobs and produce the ranked list of images by K-L divergence．Experiments on Corel dataset show that these frameworks Can satisfy diverse users． KEYWORDS：Image Annotation；Image Retrieval；Relevance Models CLASSN0：TP391．41 学位论文版权使用授权书本学位论文作者完全了解北京交通大学有关保留、使用学位论文的规定。特 学位论文版权使用授权书 本学位论文作者完全了解北京交通大学有关保留、使用学位论文的规定。特 授权北京交通大学可以将学位论文的全部或部分内容编入有关数据库进