ABSTRACT
Image representation plays an essential role in image categorization and retrieval applications. Images span on visual and spatial space. Encoding both visual and spatial information for effective and efficient image matching remains a fundamental problem in computer vision. The objective of my research is to construct a robust image representation for efficient recognition and retrieval.
- O. Boiman, E. Shechtman and M. Irani, "In defense of nearest-neighbor based image classification," In Proc. CVPR, 2008.Google ScholarCross Ref
- J. Gemert, J. Geusebroek, C. Veenman, and A. Smeulders, "Kernel codebooks for scene categorization," In proc. ECCV, 2008. Google ScholarDigital Library
- H. Jegou, M. Douze, C. Schmid, and P. Perez, "Aggregating local descriptors into a compact image representation," In Proc. CVPR, 2010.Google ScholarCross Ref
- X. Zhou, K. Yu, T. Zhang, and T. S. Huang, "Image classification using Super-Vector coding of local image descriptors," In Proc. ECCV, 2010. Google ScholarDigital Library
- S. Lazebnik, C. Schmid, and J. Ponce, "Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories," In proc. CVPR, 2006. Google ScholarDigital Library
Index Terms
- Robust image representation for efficient recognition and retrieval
Recommendations
Spatial pooling for transformation invariant image representation
MM '11: Proceedings of the 19th ACM international conference on MultimediaSpatial Pyramid Matching (SPM) [2] has been proposed to extend the Bag-of-Word (BoW) model for object classification. By re-serving the finer level information, it makes image matching more accurate. However, for not well-aligned images, where the ...
Image-blur-based Robust Weed Recognition
AICI '10: Proceedings of the 2010 International Conference on Artificial Intelligence and Computational Intelligence - Volume 01Image motion blur and defocus blur often occur when there is a relative motion between the imaging camera and the detected object. These two blurs will degrade the image quality and will also decrease the subsequent pattern recognition accuracy. In this ...
Comments