Title :
Enhanced 3-D Modeling for Landmark Image Classification
Author :
Xiao, Xian ; Xu, Changsheng ; Wang, Jinqiao ; Xu, Min
Author_Institution :
Nat. Lab. of Pattern Recognition (NLPR), Inst. of Autom., Beijing, China
Abstract :
Landmark image classification is a challenging task due to the various circumstances, e.g., illumination, viewpoint, zoom in/out and occlusion under which landmark images are taken. Most existing approaches utilize features extracted from the whole image including both landmark and non-landmark areas. However, non-landmark areas introduce redundant and noisy information. In this paper, we propose a novel approach to improve landmark image classification consisting of three steps. First, an attention-based 3-D reconstruction method is proposed to reconstruct sparse 3-D landmark models. Second, the sparse 3-D models are projected onto iconic images in order to identify images of the hot regions. For a landmark, hot regions are parts of a landmark which attract photographers´ attention and are popularly captured in photos. These hot region images are later used to enhance reconstructed sparse 3-D models. Third, the landmark regions are obtained through mapping the enhanced 3-D models to landmark images. A k-dimensional tree (kd-tree) is then constructed for each landmark based on scale invariant feature transform (SIFT) features extracted from the landmark area to classify unlabeled images into pre-defined landmark categories. The proposed method is evaluated using 291 661 images of 51 landmarks. Experiments of comparison indicate that our method outperforms bag-of-words (BoW) based approach 18.5% and method of spatial-pyramid-matching using sparse-coding (ScSPM) 8.4%.
Keywords :
feature extraction; image classification; image enhancement; image reconstruction; lighting; sparse matrices; transforms; trees (mathematics); SIFT; attention-based 3D reconstruction method; feature extraction; hot region image identification; iconic images; illumination; image mapping; k-dimensional tree; kd-tree; landmark categories; landmark image classification; noisy information; nonlandmark areas; occlusion; photo capturing; photographer attention; reconstructed sparse 3D landmark model enhancement; redundant information; scale invariant feature transform; unlabeled image classification; viewpoint; zoom in-out; Computational modeling; Feature extraction; Image classification; Image reconstruction; Solid modeling; Three dimensional displays; Visualization; 3-D model enhancement; Attention analysis; attention-based 3-D reconstruction; landmark image classification;
Journal_Title :
Multimedia, IEEE Transactions on
DOI :
10.1109/TMM.2012.2190384