Meng Di
ABSTRACT
In this paper, we introduce a novel model for embedding image spatial information into a feature vector based on an extension of spatial pyramid model (SPM). Our novel model considers the spatial distributions of both visual words and visual word combinations, extending the original SPM with a new explanation. The popular combination "spatial pyramid + max pooling + linear SVMs" for image classification and some existing works can be seen as simple implementations of our novel model, and we propose another one for better illustration. Three simple implementations are contrastively analyzedon Caltech 101, 15 Scenes and UIUC-Sports datasets, and our proposed one slightly outperforms the others.
- Y. Huang, Z. Wu, L. Wang, and T. Tan, "Feature Coding in Image Classification: A Comprehensive Study," IEEE TPAMI, vol. 36, no. 3, pp. 493--506, 2014. Google Scholar
Digital Library
- D. G. Lowe, "Distinctive image features from scale-invariant keypoints," IJCV, vol. 60, pp. 91--110, 2004. Google ScholarDigital Library
- J. Yang, K. Yu, and T. Huang, "Supervised Translation-Invariant Sparse Coding," in CVPR, 2010, pp. 3517--3524.Google Scholar
- J. Feng, B. Ni, Q. Tian, and S. Yan, "Geometric lp-norm Feature Pooling for Image Classification," in CVPR, 2011, pp. 2697--2704. Google ScholarDigital Library
- Y.L. Boureau, F. Bach, Y. LeCun, and J. Ponce, "Learning Mid-Level Features For Recognition," in CVPR, 2010, pp. 2559--2566.Google Scholar
- T. Harada, Y. Ushiku, Y. Yamashita, and Y. Kuniyoshi, "Discriminative Spatial Pyramid," in CVPR, 2011, pp. 1617--1624. Google ScholarDigital Library
- S. Lazebnik, C. Schmid, and J. Ponce, "Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories," in CVPR, 2006, pp. 2169--2178. Google ScholarDigital Library
- Y. Huang, Z. Wu, L. Wang, and C. Song, "Multiple spatial pooling for visual object recognition," Neurocomputing, vol. 129, no. 4, pp. 225--231, 2014. Google ScholarDigital Library
- V. Viitaniemi and J. Laaksonen, "Spatial extensions to bag of visual words," in CIVR, 2009, pp. 1--8. Google ScholarDigital Library
- F. Sadeghi and M.F. Tappen, "Latent Pyramidal Regions for Recognizing Scenes," in ECCV, 2012, pp. 228--241. Google ScholarDigital Library
- Y. Jia, C. Huang and T. Darrell, "Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features," in CVPR, 2012, pp. 3370--3377. Google ScholarDigital Library
- M. Dammak, M. Mejdoub, and C.B. Amar, "Histogram of dense subgraphs for image representation," IET Image Processing, vol. 9, no. 3, pp. 184--191, 2015.Google ScholarCross Ref
- S. Zhang, Q. Tian, G. Hua, Q. Huang, and W. Gao, "Generating Descriptive Visual words and Visual Phrases for Large-Scale Image Applications," IEEE TIP, vol. 20, no. 9, pp. 2664--2667, 2011. Google ScholarDigital Library
- T. Chen, K. Yap, and L. Chau, "From Universal Bag-of-Words to Adaptive Bag-of-Phrases for Mobile Scene Recognition," in ICIP, 2011, pp. 825--828.Google Scholar
- S. Yan, D. Xu, B. Zhang, H. Zhang, Q. Yang, and S. Lin,"Graph embedding and extensions: A general framework for dimensionality reduction,"IEEE TPAMI, vol. 29, no. 1, pp. 40--51, 2007. Google ScholarDigital Library
- J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong, "Locality-Constrained Linear Coding for Image Classification," in CVPR, 2010, pp. 3360--3367.Google Scholar
Recommendations
Random interest regions for object recognition based on texture descriptors and bag of features
In this work we propose a novel method for object recognition based on a random selection of interest regions, texture features (local binary/ternary patterns and local phase quantization) for describing each region, a bag-of-features approach for ...
Image Classification Using Spatial Difference Descriptor Under Spatial Pyramid Matching Framework
MMM 2016: Proceedings, Part I, of the 22nd International Conference on MultiMedia Modeling - Volume 9516Spatial pyramid matching SPM model is an extension of the bag-of-visual words BoW model for local feature encoding. It firstly partitions the image into increasingly fine sub-regions, and then concatenates the histograms within each sub-region. However, ...
A New Bag of Words LBP BoWL Descriptor for Scene Image Classification
CAIP 2013: Proceedings, Part I, of the 15th International Conference on Computer Analysis of Images and Patterns - Volume 8047This paper explores a new Local Binary Patterns LBP based image descriptor that makes use of the bag-of-words model to significantly improve classification performance for scene images. Specifically, first, a novel multi-neighborhood LBP is introduced ...
Comments