Xerox Corporation

Rochester Institute of Technology

Hewlett-packard Development Company, L.p.

Genetic Innovations, Inc.

Sohail A Dianat

Lalit Keshav Mestha

Lingappa K Mestha

Yao Rong Wang

Tracy Eugene Thieret

Survi Kyal

Gary Walker Skinner

Eric Jackson

Gill Rafael Tsouri

Michael J Rice

Daniel E Koditschek

Pramod P Khargonekar

Francesca G Polo

Beilei Xu

Mark Edward Shaw

R Enrique Viturro

Mark A Scheuer

Jeffrey N Yu

Edward Blair Caruthers

Ranjit Bhaskar

Daniel Edgardo Viassolo

Douglas A Kreckel

Eli S Saber

Sreenath Rao Vantaram

Perry Y Li

Bharathi Venkitaraman

Lalit K Mestha

Systems and methods for medical imaging and spectroscopy analysis are disclosed. Some embodiments relate to digital staining. Some embodiments relate to digital staining using hyperspectral or multispectral imaging. Some embodiments relate to digital staining using RGB imaging. Some embodiments relate to analysis of other types of medical imaging and spectroscopy. Some embodiments relate to platform for performing analysis of medical imaging and spectroscopy data.

Medical spectroscopy and imaging analysis

A system and method include contactless detecting and tracking cardiac activity by making use of a feedback control system, such as a Phase Locked Loop (PLL), in real-time or from a prerecorded signal stream.

Method and system for contactless detection of cardiac activity

A system and method for rendering an image provide for segmenting the image into a plurality of segments based on image content and, for each identified segment, identifying a rendering profile from a set of rendering profiles. The rendering profile may include a look up table for converting pixels from a first color space, such as a device independent color space, e.g., RGB, to second color space, such as a device dependent color space, e.g., CMYK. The identified rendering profile is applied to the respective segment and the segments to which the profiles have been applied are combined into a print job for rendering on print media by an associated color output device or otherwise output. The system allows different segments in the image to be processed through different rendering profiles most suited to the objects that the segments contain.

Image indexed rendering of images for tuning images from single or multiple print engines

What is disclosed is a novel video processing system and method wherein a plurality of image frames of a video captured using a video camera with a spatial resolution of (M&#xd7;N) in the (x, y) direction, respectively, and a temporal resolution (T) in frames per unit of time. A first and second magnification factor f, fare selected for spatial enhancement in the (x, y) direction. A third magnification factor fis selected for a desired temporal enhancement in (T). The video data is processed using a dictionary comprising high and low resolution patch cubes which are used to induce spatial and temporal components in the video where no data exists. A high resolution course video Xis generated which has an enhanced spatial resolution of (f*M)&#xd7;(f*N) and an enhanced temporal resolution of (f*T) frames. The course high resolution video is then smoothed, when found required, to generate a smoothed high resolution video.

Processing a video for spatial and temporal magnification with minimized image degradation

What is disclosed is a system and method for recovering a patient's cardiac pulse rate from a sequence of video images recording of that patient. In one embodiment, a reference signal of a particular frequency is generated at predetermined frequency intervals and a constrained source separation is performed on the source data to obtain an estimation of the source signal intended to be recovered. The reference signal is updated and constrained source separation is again performed. These operations are repeated for all frequencies of the reference signal. The frequency at which a minimum error is achieved is determined to be the subject's recovered cardiac pulse frequency. In such a manner, the source signal is extracted and recovered reliably from captured multi-channel RGB signals or multispectral signals. The teachings hereof find their uses in a variety of medical solutions including various military, security and telemedicine applications. Various embodiments are disclosed.

Estimating cardiac pulse recovery from multi-channel source data via constrained source separation

What is provided are a novel system and method for generating a sensitivity matrix for adaptive color control in a color marking device. In one embodiment, a first and second color space is identified. A total of N intermediate components are identified. Component sensitivity matrices are calculated and a sensitivity matrix is generated using a chain rule of differentiation over each successive component sensitivity matrix. The present method facilitates calibration of dynamically varying color reproduction devices.

Sensitivity matrix determination via chain rule of differentiation

A multi-resolution color image segmentation algorithm which takes advantage of gradient information in an adaptive and progressive framework is described. A gradient-based segmentation method is initiated with a dyadic wavelet decomposition scheme of an arbitrary input image, accompanied by a vector gradient calculation of its color converted counterpart. The resultant gradient map is used to automatically and adaptively generate thresholds for segregating regions of varying gradient densities, at different resolution levels of the input image pyramid. In combination with a confidence map and non-linear spatial filtering techniques, regions of high confidence are passed from one resolution level to another until the final segmentation at highest (original) resolution is achieved.

Methods for adaptive and progressive gradient-based multi-resolution color image segmentation and systems thereof

The present disclosure provides for an imaging machine having an imaging member including a method for maintaining a toner concentration. The method for maintaining the toner concentration comprises: determining a toner concentration (TC) measurement using a sensor; computing a state estimator output from the TC measurement and a pre-stored estimator gain matrix, K; computing an estimated target state from the state estimator and a pre-stored controller gain matrix, K; computing a duty cycle from the estimated target state, pixel count data, and pre-stored target decomposer output; and, updating the duty cycle by repeating the above method for the next TC cycle.

Toner concentration system control with state estimators and state feedback methods

The computer algorithm described which indexes and retrieves images. A query in the form of an image object or an image facilitates image retrieval in order to retrieve several images close to user's request. A thumbnail form of rank ordered images is provided for viewing. The user selects the images and down loads the images for inclusion in the job. The images are then ripped and printed.

Accurate content-based indexing and retrieval system

To determine spectra, integrated multiple illuminant measurements from a non-fully illuminant populated color sensor may be converted into a fully populated spectral curve using a reference database. The reference database is partitioned into a plurality of clusters, and an appropriate centroid is determined for each cluster by, for example, vector quantization. Training samples that form the reference database may be assigned to the clusters by comparing the Euclidean distance between the centroids and the sample under consideration, and assigning each sample to the cluster having the centroid with the shortest Euclidean distance. When all training samples have been assigned, the resulting structure is stored as the reference database. When reconstructing the spectra for new measurements from the sensor, the Euclidean distances between actual color samples under measurement and each cluster centroid are measured. The spectra are then reconstructed using only the training samples from the cluster corresponding to the shortest Euclidean distance, resulting in improved speed and accuracy.

Reference database and method for determining spectra using measurements from an LED color sensor, and method of generating a reference database

What is provided are a novel system and method for determining a sensitivity matrix for adaptive color control in a color marking device capable of performing device independent color correction. In one embodiment, a determination is made as to what control operation the color marking device is being characterized for. Nominal CMYK values are then selected based on the determined control operation. If the control operation is a gray balancing operation, the nominal CMYK values are selected using C=M=Y=L* and K*=0 values. Otherwise, the nominal CMYK values are selected using a CMYK to L*a*b* printer map. Color parameters are determined for the CMYK values based on the selected nominal CMYK values. A sensitivity matrix is then generated from the color parameters and CMYK values. The method facilitates calibration of dynamically varying color reproduction devices.

Sensitivity matrix determination for adaptive color control

Printing occurs when a marking engine deposits ink on a substrate to produce a pattern. The printed pattern can differ from the desired pattern when the marking engine is out of adjustment, the substrate and ink do not interact optimally, or for other reasons. A tone reproduction curve can be used to adjust the pattern or the marking engine so the printed pattern and desired pattern are similar. Another effect of printing is that contours can appear. Contouring can be reduced if a smooth tone reproduction curve is used. Aspects of the embodiments address limitations and flaws in the prior art by using a smoothing parameter and a smoothing matrix to produce TRCs that minimize contours.

TRC smoothing algorithm to improve image contours in 1D color controls

Spectrally matched color outputs are obtained using data from a real-time sensor, such as, for example, a spectrophotometer on the output trays of a marking devices to determine the output spectra of a reproduced image. The output spectra of the reproduced image is compared with an output spectra of a target spectra stored in a computer memory to produce a mapping table that will spectrally match all subsequently reproduced color images in real-time. Thus, output color spectra are matched between displays and prints, scans and prints, scans and displays, or copies and prints.

methods for producing device and illumination independent color reproduction

An LED-based spectrophotometer uses a reconstruction algorithm, based on spectral information of an illumination source and a reference spectrophotometer, to convert integrated multiple illuminant measurements from a non-fully illuminant populated color sensor into a fully populated spectral curve using a reference database. A dynamic, Least Squares-based spectral reconstruction algorithm, used to reconstruct spectra, gives greater importance to the data from the reference database in the neighborhood of the color sample under measurement. This is done using linear operators.

Growing community of inventors

Pittsford, NY, United States of America

Sohail A Dianat