Semantic video and image retrieval

Peter L. Stanchev
2007 Proceedings of the 45th annual southeast regional conference on - ACM-SE 45  
BRIEF SUMMARY In this tutorial we will discuss the history, the state of art, and the future of semantic image and video retrieval. The process of image description consists of extracting the global image characteristics, recognizing the image-objects, and assigning semantics to these objects. The image data can be treated as physical image representation and its meaning as a logical image representation. The logical representation includes methods for describing the image and image-objects
more » ... d image-objects characteristics and the relationships among the image objects. Several visual descriptors exist for representing the physical content of an image, such as the MPEG-7 standard [2]. Historically, semantic retrieval was frequently based on computer vision. To reduce the semantic gap, the low-level content-based media features are frequently being converted to high-level concepts or terms.
doi:10.1145/1233341.1233438 dblp:conf/ACMse/Stanchev07 fatcat:7vwfdt6vobbrxomuxqscg4kuo4