Syracuse University

United States of America As Represented by the Secretary of the Air Force

Cornell Research Foundation Inc.

Pramod K Varshney

Renbin Peng

Hao Chen

Anna Scaglione

Yao-Win Hong

James Michels

Liane Ramac-Thomas

Apparatus and method for improving the performance of a threshold-based detector or classifier, or a generic detector or classifier and increasing the probability of detecting at least one object in an image using novel algorithms and stochastic resonance noise is provided, where a suitable dose of noise is introduced to the image data such that the performance of the above-referenced detectors or classifiers is improved without altering the detector's or classifier's parameters. Several stochastic resonance (SR) noise-based detection and classification enhancement schemes are presented. The SR noise-enhanced detection and classification schemes can improve any algorithms and systems. To implement these schemes, the only knowledge that is needed is the original input data (no matter 1D, 2D, 3D or others) and the output (detection results) of the existing algorithms and systems.

Methods of improving detectors and classifiers using optimized stochastic resonance noise

Apparatus and method for detecting micro-calcifications in mammograms using novel algorithms and stochastic resonance noise is provided, where a suitable dose of noise is added to the abnormal mammograms such that the performance of a suboptimal lesion detector is improved without altering the detector's parameters. A stochastic resonance noise-based detection approach is presented to improve suboptimal detectors which suffer from model mismatch due to the Gaussian assumption. Furthermore, a stochastic resonance noise-based detection enhancement framework is presented to deal with more general model mismatch cases.

Optimized stochastic resonance signal detection method

Methods and systems for obtaining data from a number of distributed sources.

Methods and systems for obtaining data from networks of sources

Apparatus and method for improving the detection of signals obscured by noise using stochastic resonance noise. The method determines the stochastic resonance noise probability density function in non-linear processing applications that is added to the observed data for optimal detection with no increase in probability of false alarm. The present invention has radar, sonar, signal processing (audio, image and video), communications, geophysical, environmental, and biomedical applications.

Optimized stochastic resonance method for signal detection and image processing

An image, whether compressed or uncompressed, can be transmitted via a fading communication channel to provide at the receiver an image of good perceptual quality despite the impaired channel. Diversity improves wireless transmission by using highly uncorrelated signal paths to combat channel noise. The apparatus and method of the present invention operates in the wavelet domain by using the properties of the original image or its wavelet transform. For an uncompressed image, one computes the two-dimensional wavelet transform of the source image and scalar quantizes the resulting wavelet coefficients. These coefficients are transmitted as a wireless bit stream with diversity to obtain multiple copies of the decomposed image data. At the receiver, the coefficients of the individual decomposed images are combined to form a composite wavelet transform. The final received image is reconstructed from the composite transform. A compressed image is first error protected and then transmitted by wireless using diversity. Multiple bit streams representing the image are decoded with appropriate channel decoding algorithms followed by image decompression up to the point where the wavelet representations of the multiple images are obtained. Before computing the inverse wavelet transform, the individual wavelet representations are combined using rules based on wavelet transform characteristics. After diversity combining, a composite wavelet representation is obtained, and the received image is reconstructed by performing the inverse wavelet transform on this composite representation.

Growing community of inventors

Fayetteville, NY, United States of America

Pramod K Varshney