University of Colorado

Siemens Corporate Research, Inc.

Columbia University

Other

Insurance Services Office, Inc.

King Abdulaziz University

Siemens Corporation

Prince Mohammad Bin Fahd University

Siemens Corporation Research, Inc.

Lot Spot Inc.

Terrance Edward Boult

Visvanathan Ramesh

Thomas J O'Donnell

Alok Gupta

Shree Kumar Nayar

Maneesh Kumar Singh

Aurobrata Ghosh

Zheng Zhong

Xiang Gao

Fahad Alsolami

Binglong Xie

Venkata Subbarao Veeravarasapu

Travis Aaron Ray

Bayan Taha Alzahrani

Abdullah A Albahdal

Steve Cruz

Walter Scheirer

George Wolberg

William Faigen

Gang Zheng

Christopher Kazimierz Malec

Chia-Jiu Wang

A system for improved localization of image forgery. The system generates a variational information bottleneck objective function and works with input image patches to implement an encoder-decoder architecture. The encoder-decoder architecture controls an information flow between the input image patches and a representation layer. The system utilizes information bottleneck to learn useful residual noise patterns and ignore semantic content present in each input image patch. The system trains a neural network to learn a representation indicative of a statistical fingerprint of a source camera model from each input image patch while excluding semantic content thereof. The system can determine a splicing manipulation localization by the trained neural network.

Machine learning systems and methods for improved localization of image forgery

Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.

Computer vision systems and methods for blind localization of image forgery

The present invention is a computer-implemented system and method for transforming video data into directional object counts. The method of transforming video data is uniquely efficient in that it uses only a single column or row of pixels in a video camera to define the background from a moving object, count the number of objects and determine their direction. By taking an image of a single column or row every frame and concatenating them together, the result is an image of the object that has passed, referred to herein as a sweep image. In order to determine the direction, two different methods can be used. Method one involves constructing another image using the same method. The two images are then compared, and the direction is determined by the location of the object in the second image compared to the location of the object in the first image. Due to this recording method, elongation or compression of the objects can occur because of acceleration or deceleration of the objects and can be uniquely utilized to determine the speed or movement path of the objects. The second method of determining direction involves comparing the object in the image to an established marker. The transformations can also be used to produce labeled data for training machine learning models: bounding-boxes provided in sweep image can be transformed to bound boxes in video, and boxes in video can be transformed into boxes in the sweep image.

System and method for transforming video data into directional object count

The invention allows riders to quickly and effortlessly strap in and out of their bindings with only one hand, with embodiments for top-entry bindings, rear-entry bindings and hybrid-bindings. The invention can be integrated into bindings or delivered as after-market add-on products that re-use and adapt the riders existing binding.

Systems and methods for one-handed snowboard strapping

A fingerprint characterizing system and method include receiving a fingerprint image at a fingerprint module; extracting a plurality of minutiae points from the fingerprint image, via a fingerprint image sensor; generating a minutiae file of biometric data according to a corresponding location of the plurality of minutiae points on the fingerprint image; generating a pair table from the minutiae file; dividing the pair table into a plurality of subsets; encrypting, via processing circuitry each of the plurality of subsets; comparing, via the processing circuitry each of the encrypted plurality of subsets against one or more existing encrypted subsets stored across a plurality of data clouds; and generating, via the processing circuitry a match table for each of the encrypted plurality of subsets and a corresponding compatible existing encrypted subset stored in the plurality of data clouds.

Secured biometric systems and methods

This invention is a novel method of gameplay and game apparatus for playing for at least one player. The method of play elicits creativity by having players tell stories using their interpretation of abstract imagery. In one embodiment the game uses playing cards with abstract drawings. The game components may take other forms, such as a board game, or the game may be played in different media, such as electronic games, video games, computer games, and interactive network games. One aspect of novelty here is the use of abstract drawings, which the players can interpret in many different ways to expand the story. The context of the story, and possible side constraints, will prime the player's mind to see different things in each card. In this game of creativity and storytelling, players create and add to a story based on the abstract images. Testing has shown that this method of gameplay can improve players' perception of their creative ability. Various embodiments offer multiple methods of play and scoring, each adaption designed to engage different size of groups. Other embodiments adapt the method and apparatus for ideation and problem-solving.

Method and apparatus for creative story telling games

A secure and scalable data storage system that includes a server and a plurality of clients. The server maintains an access permission file that includes a file-group name, a plurality of client access blocks, a first and second public key, and a signature that is based on a first private key. The signature ensures that only clients who have a certain level of access can modify the contents of the access blocks. Each client access block includes at least one of a first access key, a second access key and a third access key. The access keys are encapsulated within biometric information of the client. The server grants one of a first level of access based on a successful verification of a signed request with the first public key and a second level of access based on a successful verification of the signed request with the second public key.

Secure biometric cloud storage system

Techniques, systems and methods are described relating to combining biometric and cryptographic techniques to support securely embedding data within a token and subsequent biometrically-enabled recovery of said data. Various transformation approaches are described that provide a secure means for transforming a stored or live, secure biometric-based identity token, embedding data into such tokens and biometric-based matching to both verify the user's identity and recover the embedded data. Security enhancements to a range of existing protocols are described using the techniques. Systems using novel protocols based on these techniques are described.

Bio-cryptography: secure cryptographic protocols with bipartite biotokens

A system () for the adaptive imaging of a scene includes a digital light processing apparatus () adapted for controllably reflecting an image of the scene in at least a first direction to thereby reflect an intensity modulated image of the scene along at least the first direction, an image detector () for detecting the intensity modulated image of the scene and generating corresponding image data, and an image data processor () for processing the image data into control data and providing the control data to the digital light processing () apparatus for control thereof.

Adaptive imaging using digital light processing

The present invention provides a technique for automated selection of a parameterized operator sequence to achieve a pattern classification task. A collection of labeled data patterns is input and statistical descriptions of the inputted labeled data patterns are then derived. Classifier performance for each of a plurality of candidate operator/parameter sequences is determined. The optimal classifier performance among the candidate classifier performances is then identified. Performance metric information, including, for example, the selected operator sequence/parameter combination, will be outputted. The operator sequences selected can be chosen from a default set of operators, or may be a user-defined set. The operator sequences may include any morphological operators, such as, erosion, dilation, closing, opening, close-open, and open-close.

Automatic design of morphological algorithms for machine vision

Techniques, systems and methods relating to cryptographically secure revocable biometric signatures and identification computed with robust distance metrics are described. Various biometric cryptographically secure revocable transformation approaches are described that support a robust pseudo-distance computation in encoded form, thereby supporting confidence in verification, and which can provide for verification without identification.

Revocable biometrics with robust distance metrics

Techniques, systems and methods for obtaining biometric signatures and identification are described. Broadly stated, embodiments of the present invention utilize specified geometric principles to provide means for accurate biometric identification using projective invariant features of a subregion of the human body. The present invention provides a means for computing biometric signatures and identification that are projective invariant and hence are not impacted by the viewing angle of the subregion of the human body containing the biometric data. This novel invention removes the restriction, often implicit in the previous work, of the imaging or sensing system being in a fixed repeatable (and generally orthogonal) viewing position. This invention can be applied across a wide range of biometrics, although it is most easily applicable to features that are approximately co-planar. A plurality of such projective invariant features can be used to define a biometric signature to either verify an individual's identity, or recognize an individual from a database of already known persons.

Biometric signatures and identification through the use of projective invariants

A method and system for accurately imaging scenes having large brightness variations. If a particular object in the scene is of interest, the imager exposure setting is adjusted based on the brightness of that object. For high dynamic range imaging of an entire scene, two imagers with different viewpoints and exposure settings are used, or the exposure setting of a single imager is varied as multiple images are captured. An optical flow technique can be used to track and image moving objects, or a video sequence can be generated by selectively updating only those pixels whose brightnesses are within the preferred brightness range of the imager.

Imaging method and system

A system and method for object detection with sudden illumination changes provides a system including a camera model unit for computing a difference map between a first input image and a second input image, an illumination model unit in signal communication with the camera model unit for comparing the sign of the difference between two pixels in a first input image against the sign of the difference between two pixels in a second input image, and a CPU in signal communication with the camera model unit and the illumination model unit for detecting a changed object in accordance with said comparison when said sign of the difference is changed; and a corresponding method including providing a first image having a number of pixels, receiving a second image subsequent to the first image, calculating a difference map between the first and second images, selecting a pair of pixel locations from the first or second images in accordance with the difference map, statistically modeling a camera noise level for the first and second images, computing the likelihood of order inconsistency between a pair of pixel values at the selected locations in the first image and a pair of pixel values at the selected locations in the second image in accordance with the camera noise level; and detecting a changed object in accordance with the computed likelihood.

Growing community of inventors

Monument, CO, United States of America

Terrance Edward Boult