Stochastic models for capturing image variability

IEEE Signal Processing Magazine - Tập 19 Số 5 - Trang 63-76 - 2002
A. Srivastava1
1Department of Statistics, Florida State University (FSU)

Tóm tắt

We review a result in modeling lower order (univariate and bivariate) probability densities of pixel values resulting from bandpass filtering of images. Assuming an object-based model for images, a parametric family of probabilities, called Bessel K forms, has been derived (Grenander and Srivastava 2001). This parametric family matches well with the observed histograms for a large variety of images (video, range, infrared, etc.) and filters (Gabor, Laplacian Gaussian, derivatives, etc). The Bessel parameters relate to certain characteristics of objects present in an image and provide fast tools either for object recognition directly or for an intermediate (pruning) step of a larger recognition system. Examples are presented to illustrate the estimation of Bessel forms and their applications in clutter classification and object recognition.

Từ khóa

#Stochastic processes #Band pass filters #Gabor filters #Object recognition #Pixel #Filtering #Histograms #Infrared imaging #Matched filters #Laplace equations

Tài liệu tham khảo

srivastava, 2001, spectral probability models for infrared images and their applications to ir face recognition, Proc Workshop Computer Vision Beyond Visual Spectrum cutler, 1996, Face recognition using infrared images and eigenfaces cooper, 1997, accommodating geometric and thermodynamic variability for forward-looking infrared sensors, Proc SPIE Algorithms for Synthetic Aperture Radar IV, 3070, 162, 10.1117/12.281553 10.1117/1.601302 mumford, 2000, empirical investigations into the statistics of clutter and the mathematical models it leads to, A Lecture for the Review of ARO Metric Pattern Theory Collaborative 10.1006/acha.2000.0350 10.1364/JOSAA.4.002379 10.1088/0954-898X/7/2/014 silverman, 1985, Density Estimation for Statistics and Data Analysis 10.1145/218380.218446 10.1162/neco.1997.9.8.1627 10.1364/JOSAA.11.002350 10.1023/A:1026553619983 10.1023/A:1011109015675 10.1016/S0042-6989(97)00121-1 billingsley, 1995, Probability and Measure cover, 1991, Elements of Information Theory, 10.1002/0471200611 10.1016/0165-1684(94)90029-9 10.1109/34.598228 10.1109/18.850712 10.1016/S0042-6989(97)00169-7 srivastava, 2000, bayesian automated target recognition, Handbook of Image and Video Processing, 869 10.2307/2001373 10.1109/34.41390 10.1109/34.192463 10.1109/34.917579 10.1088/0954-898X/12/3/308 10.1109/TPAMI.2002.1033212 10.1007/978-3-642-97522-6 marr, 1982, Vision A Computational Investigation into the Human Representation and Processing of Visual Information jahne, 1999, Handbook of Computer Vision and Applications, 2 van hateren, 0, Natural stimuli collection A public database of natural images 10.2307/1402598