摘要: 图像低层视觉特征和高层语义间的“语义鸿沟”是图像检索的关键问题。为了进一步提高基于语义的图像检索系统工作效率,以分块权值和视觉词库为基础,结合图像低层特征和高层语义的相关性,提出了一种基于分块权值的语义图像模型,该模型用来反映图像的视觉特性,对图像的高层语义进行有效检测,从而提高语义图像的检索效率。实验结果表明,该方法提高了语义图像检索系统的查全率和查准率。
[1] Hiremath P S,Pujari J.Content based image retrieval using co-lor,texture and shape features[C]∥Advanced Computing and Communication.Gulbarga:Gulbarga University.2007 [2] 周明全,耿国华,韦娜.基于内容图像检索技术[M].北京:清华大学出版社,2007 [3] Duygulu P,Barnard K,De Freitas J F G,et al.Object recognition as machine translation:Learning a lexicon for a fixed image vocabulary[J].Lecture Notes in Computer science,2002(2353):97-112 [4] Spyrou E,Tolias G,Mylonas P,et al.Concept detection and keyframe extraction using a visual thesaurus[J].Multimedia Tools and Applications,2009,41(3):337-373 [5] Manjunath B,Ohm J,Vasudevan V,et al.Color and texture descriptors[J].IEEE Trans Circuits Syst Video Technol,11(6):703-715 [6] Spyrou E,Tolias G,Mylonas P,et al.Concept detection and key-frame extraction using a visual thesaurus[J].Multimedia Tools and Applicationgs,2009(41):337-373 [7] Avrithis Y,Doulamis A,Kollias S.A Stochastic Framework for Optimal Key Frame Extraction from MPEG Video Databases[J].Computer Vision and Image Understanding,1999(75):3-24 [8] Mylonas P,Spyrou E,Avrithis Y,et al.Using Visual Context and Region Semantics for High-Level Concept Detection[J].IEEE Transaxtions on Multimedia,2009,11(2):229 [9] 曹利华,柳伟,李国辉.基于多种主色调的图像检索算法研究与实现[J].计算机研究与发展,1999(36):96-100 [10] 张瑜慧.基于SVM的语义图像检索技术的研究与实现[D].扬州:扬州大学,2007 [11] Chang E,Kingshy G,Sychay,et al.CBSA:content-based softannotation for multimodal image retrieval using Bayes point machines[J].IEEE Transactions on Circuits and Systems for Video Technology,2003(13):26-38 [12] Lowe D G.Object recognition from local scale-invariant features[J].Computer Vision,1999(2):1150-1157 [13] Wang Jun-qiu.Vision-based Global Localization Using a Visual Vocabulary[C]∥Robotics and Automation.Beijing:Peking University,2005 |
No related articles found! |
|