We present a spectral representation for appearance based image classification and object recognition. Based on a generative process, the representation is derived by partitioning the frequency domain into small disjoint regions. This gives rise to a set of filters and a representation consisting of marginal distributions of those filter responses. We use a neural network, to learn a classifier through training examples. We propose a filter selection algorithm by maximizing the performance over training data. A distinct advantage of our representation is that it can be effectively used for different classification and recognition tasks, which is demonstrated by experiments and comparisons in texture classification, face recognition, and appearance-based 3D object recognition.
[1]
Elie Bienenstock,et al.
Neural Networks and the Bias/Variance Dilemma
,
1992,
Neural Computation.
[2]
Massimiliano Pontil,et al.
Support Vector Machines for 3D Object Recognition
,
1998,
IEEE Trans. Pattern Anal. Mach. Intell..
[3]
David J. Field,et al.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
,
1996,
Nature.
[4]
Trygve Randen,et al.
Filtering for Texture Classification: A Comparative Study
,
1999,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
Narendra Ahuja,et al.
Learning to Recognize 3D Objects with SNoW
,
2000,
ECCV.