Dissertation
Dissertation > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device

Research on Automatic Tag Ranking of Large-scale Images

Author ZhaoRiPeng
Tutor SongZeHai
School Beijing Jiaotong University
Course Computer Science and Technology
Keywords saliency analysis tag saliency ranking tag relevance ranking multi-instance learning salient region detection
CLC TP391.41
Type Master's thesis
Year 2012
Downloads 94
Quotes 0
Download Dissertation

Recent years, with the popularity of photographic electronic products, digital photos have appeared online at an explosive rate. Retrieving images from enormous collections of digital photos has become an important research topic and practical problem. Tag ranking has become a hot research topic due to its importance for image analysis and retrieval. This paper mainly focuses on establish an effective learning model to solve the problem of automatic tag ranking.Existing annotation methods about tag ranking can be roughly classified into two categories:tag relevance ranking and tag saliency ranking. This paper proposes an adaptive tag ranking based on saliency analysis which combines the advantages of tag relevance ranking and tag saliency ranking. In short, given an image and corresponding tags, we first carry out image salient region detection and get its saliency map. Then we carry out image saliency analysis using the saliency map. And finally, if there exist visually salient regions of the given image, the corresponding annotated tags can be ranked according to the saliency property of the corresponding visual content; else tags can be ranked according to the relevance scores to the content of the image.In the process of adaptive tag ranking, the difficulty is how to carry out image saliency analysis. This paper proposes a gray distribution histogram method to analyze saliency of the image. This method utilizes machine learning technologies like LIBSVM to distinguish whether images include salient regions.Experiments conducted on the COREL and MSRC image datasets demonstrate the effectiveness and efficiency of the proposed algorithm.

Related Dissertations
More Dissertations