Title :
Generating representative images for landmark by discovering high frequency shooting locations from community-contributed photos
Author :
Shuhui Jiang ; Xueming Qian ; Yao Xue ; Fan Li ; Xingsong Hou
Author_Institution :
Sch. of Electron. & Inf. Eng., Xi´an Jiaotong Univ., Xi´an, China
Abstract :
Representative images generation offers a comprehensive knowledge for landmark and is a hot research area recent years. This paper presents a representative images generation system by discovering high frequency shooting locations from geo-tagged community-contributed photos. We discover that the views (e.g. far and near, front, back and side) of the photos taken in the same location are usually similar and but different in different shooting locations. Our system is realized by three steps: 1) Landmark dataset is filtered from social media by the combination of tags and geo-tags. 2) High frequency shooting locations are mined by geo-tag cluster. 3) Visual feature is then used for removing irrelevant images and ranking by intra and inter SIFT matching. This work is the first attempt to generate representative images by high frequency shooting locations mining. Evaluating on ten landmarks shows its effectiveness .
Keywords :
Internet; data mining; feature extraction; filtering theory; image matching; image representation; pattern clustering; social networking (online); transforms; Facebook; Flickr; Twitter; Web 2.0 technologies; geo-tag cluster; geo-tagged community-contributed photos; high frequency shooting location discovery; high frequency shooting location mining; inter SIFT matching; intra SIFT matching; irrelevant image removal; landmark dataset; representative image generation system; social media sites; visual feature; Abstracts; Bandwidth; Educational institutions; Noise; Geo-tagged photos; Representative Image Selection; social media;
Conference_Titel :
Multimedia and Expo Workshops (ICMEW), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
DOI :
10.1109/ICMEW.2013.6618374
