文章基本信息

标题：Flickr Distance: A Motion Prediction Approach for Visual Concepts
本地全文：下载
作者：T.Suganya ; B. Anuradha ; B.Chellaprabha 等
期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2014
卷号：14
期号：2
页码：91-96
出版社：International Journal of Computer Science and Network Security
摘要：While image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical ?ow where an image is aligned to its temporally adjacent frame, we propose SIFT ?ow, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes. The SIFT ?ow algorithm consists of matching densely sampled, pixel-wise SIFT features between two images, while preserving spatial discontinuities. The SIFT features allow robust matching across different scene/object appearances, whereas the discontinuity- preserving spatial model allows matching of objects located at different parts of the scene. The proposed approach will robustly aligns complex scene pairs by determining Flickr Distance between the image concepts. The Flickr distance between two concepts is defined as the Jensen-Shannon (J-S) divergence between their LTVLM. Based on SIFT ?ow, we propose an alignment- based large database framework for image analysis and synthesis, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence. This framework can be demonstrated through concrete applications, such as motion field prediction from a single image, motion synthesis via object transfer, satellite image registration and face recognition.
关键词：Artificial Intelligence; Image Analysis; Distance Learning; Machine Vision; Scene alignment; SIFT ?ow; motion prediction for a single image; motion synthesis via object transfer