ABSTRACT
In this paper, a bio-inspired invariant visual feature representation method is proposed. A set of Gabor filters with different parameters and global max operation are performed to improve the adaptability to scale and shift changes. In order to extract rotation-invariant features of images, the K-SVD and SURF algorithms are introduced into the traditional HMAX model. Prototypes (feature templates) are learned by the K-SVD algorithm, while the SURF descriptor of patches aims to enhance the rotation invariance. Experimental results on image classification demonstrate the superiority of the proposed feature representation method.
- Fukushima, K. Neocognitron: A self-organizing neural network model for a mechanism for pattern recognition unaffected by shift in position. Biological Cybernetics, 1980, 36(4): 193--202.Google ScholarCross Ref
- Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex {J}. Nature Neuroscience, 1999, 2(11): 1019--1025.Google ScholarCross Ref
- Olshausen BA, Filed DJ. Emergence of simple-cell receptive filed properties by learning a sparse code for natural images. Nature, 1996, 381:607--609.Google ScholarCross Ref
- Zhong Ji, Jing Wang, Yuting Su, et al. Balance between object and background: Object enhanced features for scene image classification. Neurocomputing, http://dx.doi.org/10.1016/j.neucom.2012.02.054Google Scholar
- Serre T, Wolf L, Bileschi S, et al. Robust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(3):411--426. Google ScholarDigital Library
- Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proc. IEEE, 1998, 86:2278--2324.Google ScholarCross Ref
- Mutch J, Lowe D G. Multiclass object recognition with sparse, localized features. CVPR, 2006:11--18. Google ScholarDigital Library
- Serre T, Oliva A, Poggio T. A feedforward architecture accounts for rapid categorization. PNAS, 2007, 104(15):6423--6429.Google ScholarCross Ref
- Riesenhuber M and Poggio T. Models of object recognition. Nature Neuroscience, 2000, 3(supp):1199--1204Google ScholarCross Ref
- Ungerleider L, Haxby J. 'What' and 'Where' in the human brain. Current Opinion in Neurobiology, 1994, 4:157--165.Google ScholarCross Ref
- A. Benoit, A. Caplier, B. Durette. Using human visual system modeling for bio-inspired low level image processing. Computer Vision and Image Understanding, 2010, 114:758--773. Google ScholarDigital Library
- Daugman J G. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A, 1985, 2: 1160--1169.Google ScholarCross Ref
- Rodieck R W, Stone J J. Analysis of receptive field of cat retina ganglion cells. Journal of Neurophysiology, 1999, 28:833--849.Google ScholarCross Ref
- Serre T, Wolf L, Poggio T. Object recognition with features inspired by visual cortex {C}. Proc. of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, Vol. 2:994--1000. Google ScholarDigital Library
- Bruno A. Olshausen, David J. Field. Sparse coding with an over-complete basis set: A strategy employed by V1? Vision Research, 1997, 37(23):3311--3325.Google ScholarCross Ref
- Eric T. Carlson, et al. A sparse object coding scheme in area V4. Current Biology, 2011, 21(4):288--293.Google ScholarCross Ref
- Mallat S, Zhang Z. Matching pursuits with time-frequency dictionaries. IEEE Transactions on Signal Processing, 1993, 41(12):3397--3415. Google ScholarDigital Library
- Pati Y. C., Rezaiifar R, Krishnaprasad P. S. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. Conference Record of the 27th Asilomar Conference on Signals, System and Computers, 1993:40--44.Google Scholar
- Aharon M, Elad M, Bruckstein A. The K-SVD: an algorithm for designing of over-complete dictionaries for sparse. representation. IEEE Transaction on Image Processing, 2006, 54(11):4311--4322. Google ScholarDigital Library
- Bay H, Tuytelaars T, van Gool L. SURF: Speeded up robust features {J}.Computer Vision and Image Understanding, 2008, 110(3):346--359. Google ScholarDigital Library
- Shiliang Zhang, Qi Tian, Ke Lu, et al. Edge-SIFT: Discriminative binary descriptor for scalable partial-duplicate mobile search, IEEE Transaction on Image Processing, 2013, 22(7):2889--2902.Google ScholarCross Ref
- L. Fei-Fei, R. Fergus, P. Perona. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Working Generative-Model Based Vision, 2004. Google ScholarDigital Library
Index Terms
Bio-inspired invariant visual feature representation based on K-SVD and SURF algorithms
Recommendations
LBP-SURF descriptor with color invariant and texture based features for underwater images
ICVGIP '12: Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image ProcessingIn this paper, we introduce LBP-SURF, a local image descriptor for underwater environment, which is very efficient to extract color invariant and texture based features of underwater images. The current state-of-the-art feature descriptors viz. SIFT, ...
Scale, translation and rotation invariant Wavelet Local Feature Descriptor
AbstractIn this paper is presented a novel scale, translation and rotation (STR)-invariant 1D-descriptor, named Wavelet Local Feature Descriptor (WLFD). The methodology to construct the WLFD locates in three different scale pyramids keypoints ...
Fully affine invariant SURF for image matching
Fast and robust feature extraction is crucial for many computer vision applications such as image matching. The representative and the state-of-the-art image features include Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), ...
Comments