Large scale image recognition using global signatures and local feature information

作者: Liwen Lin , Bing Song

DOI:

关键词: Feature detection (computer vision)Feature (computer vision)Ranking (information retrieval)Scale (map)Artificial intelligencePattern recognitionComputer sciencek-nearest neighbors algorithmGeometric verificationComputer visionImage (mathematics)

摘要: Techniques are provided that include receiving one or more global signatures for a query image in response to an recognition query, wherein some of the plurality generated using local descriptors corresponding different cropped versions image. A ranking order is determined document images based on nearest neighbor relations between and each subset selected order. Additional data obtained, search result geometric verification additional

参考文章(42)
Dustin Michael Sargent, Rolf Holger Wolters, Sun Young Park, Ulf Peter Gustafsson, Diagnosis support system providing guidance to a user by automated retrieval of similar cancer images with user feedback ,(2012)
Pengfei Xiong, Bo Chen, Feng Rao, Hailong Liu, Jie Hou, Xiaobo Zhou, Method, system and computer storage medium for visual searching based on cloud service ,(2013)
Gaurav Srivastava, Zhan Ma, Abhishek Nagar, Zhu Li, Felix Carlos Fernandes, Kong Posh Bhat, Xin Xin, Two way local feature matching to improve visual search accuracy ,(2013)
Luis F. Goncalves, Jim Ostrowski, Robert Boman, Systems and methods for object recognition using a large database ,(2011)
Florent Perronnin, Diane Larlus, Efficient document processing system and method ,(2011)
Zhiwei Li, Rui Cai, Qiang Hao, Lei Zhang, Three-dimensional visual phrases for object recognition ,(2012)