Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Evaluating bag-of-visual-words representations in scene classification
Proceedings of the international workshop on Workshop on multimedia information retrieval
Content Based Image Retrieval Using Color, Texture and Shape Features
ADCOM '07 Proceedings of the 15th International Conference on Advanced Computing and Communications
Spatial Weighting for Bag-of-Visual-Words and Its Application in Content-Based Image Retrieval
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Descriptive visual words and visual phrases for image applications
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Robust Face Recognition Using Block-Based Bag of Words
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
SIFT Flow: Dense Correspondence across Scenes and Its Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence
Coloring local feature extraction
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
Visual features extraction for large-scale image retrieval is a challenging task. Bag-of-Features (BOF) is one of most popular models and gains attractive performance. However, BOF intrinsically represents an image as an unordered collection of local descriptors based on the intensity information, which provides little insight into the spatial structure of the image. This paper proposes a Spatial Weighting BOF (SWBOF) model to extract a new kind of bag-of-features by using spatial information, which is inspired by the idea that different parts of an image object play different roles on its categorization. Three approaches to measure the spatial information, local variance, local entropy and adjacent blocks distance are extensively studied, respectively. Experimental results show that SWBOF significantly improves the performance of the traditional BOF method, and achieves the best performance on the Corel database to our best knowledge.