Three-dimensional distortion-tolerant object recognition using photon-counting integral imaging.

This paper addresses three-dimensional distortion-tolerant object recognition using photon-counting integral imaging (II). A photon-counting linear discriminant analysis (LDA) is proposed for classification photonlimited images. In the photon-counting LDA, classical irradiance images are used to train the classifier. The unknown objects used to test the classifier are labeled by the number of photons detected. The optimal solution of the Fisher's LDA for photon-limited images is found to be different from the case when irradiance values are used. This difference results in one of the merits of a photon-counting LDA, namely that the high dimensionality of the image can be handled without preprocessing. Thus, the singularity problem of the Fisher's LDA encountered in the use of irradiance images can be avoided. By using photon-counting II, we build a compact distortiontolerant recognition system that makes use of the multiple-perspective imaging of II to enhance the recognition performance. Experimental and simulation results are presented to classify out-of-plane rotated objects. The performance is analyzed in terms of mean-squared distance (MSD) between the irradiance images. It is shown that a low level of photons is sufficient in the proposed technique.

[1]  J. Rarity,et al.  Single-photon counting for the 1300-1600-nm range by use of peltier-cooled and passively quenched InGaAs avalanche photodiodes. , 2000, Applied optics.

[2]  Pedro E. López-de-Teruel,et al.  Nonlinear kernel-based statistical pattern analysis , 2001, IEEE Trans. Neural Networks.

[3]  Philippe Réfrégier,et al.  Maximum-likelihood estimation of an astronomical image from a sequence at low photon levels , 1998 .

[4]  G. Michael Morris,et al.  Image classification at low light levels , 1986 .

[5]  B Javidi,et al.  Real-time three-dimensional object recognition with multiple perspectives imaging. , 2001, Applied optics.

[6]  J Arai,et al.  Real-time pickup method for a three-dimensional image based on integral photography. , 1997, Applied optics.

[7]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[8]  Juyang Weng,et al.  Using Discriminant Eigenfeatures for Image Retrieval , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Bahram Javidi,et al.  Digital three-dimensional image correlation by use of computer-reconstructed integral imaging. , 2002, Applied optics.

[10]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[11]  Bahram Javidi,et al.  Photon counting passive 3D image sensing for automatic target recognition. , 2005, Optics express.

[12]  G M Morris,et al.  Image correlation at low light levels: a computer simulation. , 1984, Applied optics.

[13]  G M Morris,et al.  Photon-limited image classification with a feedforward neural network. , 1995, Applied optics.

[14]  Laurent Duraffourg,et al.  Photon counting in the 1540-nm wavelength region with a germanium avalanche photodiode , 2001 .

[15]  Abhijit Mahalanobis,et al.  Methods for automatic target recognition by use of electro-optic sensors: introduction to the feature issue , 2004 .

[16]  Bahram Javidi,et al.  Three-dimensional distortion-tolerant object recognition using integral imaging. , 2004, Optics express.

[17]  Bahram Javidi,et al.  Multifacet structure of observed reconstructed integral images. , 2005, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[19]  John G. Rarity,et al.  Photon counting for quantum key distribution with peltier cooled InGaAs/InP APDs , 2001 .

[20]  Heesung Kwon,et al.  Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Robert D. Nowak,et al.  Multiscale Modeling and Estimation of Poisson Processes with Application to Photon-Limited Imaging , 1999, IEEE Trans. Inf. Theory.

[22]  Bahram Javidi,et al.  Improved resolution 3D object sensing and recognition using time multiplexed computational integral imaging. , 2003, Optics express.

[23]  A. Walker,et al.  Performance and design of InGaAs /InP photodiodes for single-photon counting at 1.55 microm. , 2000, Applied optics.

[24]  Philippe Réfrégier,et al.  Photon-noise effect on detection in coherent active images. , 2004, Optics letters.

[25]  B. Javidi,et al.  Time- multiplexed integral imaging: For 3D sensing and display , 2004 .

[26]  Jing-Yu Yang,et al.  Optimal fisher discriminant analysis using the rank decomposition , 1992, Pattern Recognit..

[27]  E A Watson,et al.  Imaging thermal objects with photon-counting detectors. , 1992, Applied optics.

[28]  George Michael Morris.  Scene matching using photon-limited images , 1984 .

[29]  K. Strimmer,et al.  Statistical Applications in Genetics and Molecular Biology A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics , 2011 .

[30]  Edward A. Watson,et al.  Comparison of infrared upconversion methods for photon-limited imaging , 1990, Annual Meeting Optical Society of America.