Stöttinger, Julian and Hanbury, Allan and Sebe, Nicu and Gevers, Theo (2012) Sparse Color Interest Points for Image Retrieval and Object Categorization. Trento : Università di Trento, pp. 1-12.
|PDF - Full Text |
Download (6Mb) | Preview
Interest point detection is an important research area in the field of image processing and computer vision. In particular, image retrieval and object categorization heavily rely on interest point detection from which local image descriptors are computed for image matching. In general, interest points are based on luminance, and color has been largely ignored. However, the use of color increases the distinctiveness of interest points. The use of color may therefore provide selective search reducing the total number of interest points used for image matching. This paper proposes color interest points for sparse image representation. To reduce the sensitivity to varying imaging conditions, light invariant interest points are introduced. Color statistics based on occurrence probability lead to color boosted points which are obtained through a saliency-based feature selection. Further, a PCA-based scale selection method is proposed which gives a robust scale estimation per interest point. From large scale experiments, it is shown that the proposed color interest point detector has a higher repeatability than a luminance-based one. Further, in the context of image retrieval, a reduced and predictable number of color features shows an increase in performance compared to state-of-the-art interest points. Finally, in the context of object recognition, for the Pascal VOC 2007 challenge, our method gives comparable performance to state-of-the-art methods using only a small fraction of the features, reducing the computing time considerably.
|Item Type:||Departmental Technical Report|
|FP7 Grant Agreement Number:||info:eu-repo/grantAgreement/EC/FP7/287704|
|Publisher policy set phrase:||(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.|
|Department or Research center:||Information Engineering and Computer Science|
|Subjects:||Q Science > QA Mathematics > Q360 Information Theory|
Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Q Science > QA Mathematics > QA076 Computer software
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885 Computer Engineering
|Uncontrolled Keywords:||color invariance, local features, object categorization, image retrieval|
|Repository staff approval on:||06 Aug 2012 13:06|
Actions (login required)