An Image Recognition Method Based on Scene Semantics
Aimed at the image recognition between scenes and objects, we propose a sort of image recognition method based on scene semantics (IRMSS). In IRMSS, the landmark objects of various scenes are collected to form a feature database named Symbolic Objects Database and marked firstly; secondly, the remaining objects in the image could be identified one by one according to scene semantics known from the step forward; and thirdly, the scene of the image would be repeated validated and continuous concreted by using recognition results of each time to form a feedback system for the recognition of image semantics. At final, the simulation experiments showed that IRMSS could sharply promote the accuracy and efficiency of image semantic recognition in the case of strong semantic scene.
KeywordsImage recognition Image semantics Scene semantics
- 2.Fei–Fei, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of IEEE international conference on Computer Vision and Pattern Recognition (CVPR’ 05). USA: IEEE Computer Society 24(2):524–531Google Scholar
- 4.Marcus Hutter (2003) Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet. J Mach Learn Res 4(11):971–1000Google Scholar
- 6.Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE international conference on Computer Vision and Pattern Recognition (CVPR’ 06). USA: IEEE Computer Society 30(2):2169–2178Google Scholar
- 8.Nowak E, Jurie F, Triggs B (2006) Sampling strategies for bag-of feature image classification. Proc of European Conference on Computer Vision (ECCV’ 06). Austria: Springer 12(3):105–122Google Scholar
- 9.Kokkinos I, Yuille A (2009) HOP: hierarchical object parsing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition USA 18(2):802–809Google Scholar