University of South Florida

Government of the United States of America, As Represented by the Secretary of Commerce

Unifi Software, Inc.

Sudeep Sarkar

Sanjukta Bhanja

Ravi Panchumarthy

Dinuka K Karunaratne

Miguel A Labrador

Rangachar Kasturi

Pranab Mohanty

Ravichandran Subramanian

Dmitry B Goldgof

Ravikiran Krishnan

Ayush Parashar

Mauricio Pamplona Segundo

Earnest Eugene Hansley

P Jonathon Phillips

Leonid V Tsap

A method and system for generating structured data from semi-structured data are provided. The method includes reading a plurality of records from a data file including semi-structured data. Further, the method includes obtaining aligned delimiters in a list for every record that has been read. The method also includes selecting a most occurring delimiter from the list. The method then includes constructing a regular expression using the selected delimiter to split the records into different fields. The method also includes reconstructing the records for the regular expression to fit and split into fields. In addition, the method includes displaying the records split into the fields.

Automatic generation of structured data from semi-structured data

A system and method for identifying a subject based upon ear recognition using a convolutional neural network (CNN) and handcrafted features, wherein an ear in an image is cropped using ground truth annotations and landmark detection is performed to obtain the information required to normalize pose and scale variations. The normalized images are then described by different feature extractors and matched through distance metrics. Finally, scores are fused and a subject identification decision is made.

Unconstrained ear recognition using a combination of deep learning and handcrafted features

Aspects of gait matching are described herein. In one embodiment, a method of gait matching includes identifying a gait cycle timing in a data sequence captured by an inertial sensor, splitting the data sequence into a gait cycle segment, resampling the gait cycle segment, and estimating a rotation matrix for the resampled gait cycle segment. The rotation matrix, in one embodiment, can be estimated by minimizing a root mean squared deviation between the resampled gait cycle segment and a reference gait cycle segment. The method further includes calculating an aligned gait cycle segment from the resampled gait cycle segment using the rotation matrix, and generating a similarity measure between the aligned gait cycle segment and the reference gait cycle segment.

Orientation invariant gait matching

A magnetic system for solving one or more quadratic optimization problems by associating each of a plurality of variables of a quadratic optimization problem with a nanomagnet subset of a nanomagnet array, driving the nanomagnets of the nanomagnet subset to an excited state, allowing the nanomagnets of the nanomagnet subset to enter a relaxed state after being driven to an excited state, wherein the nanomagnets magnetically couple with one another in the relaxed state to minimize the total magnetic coupling energy of the nanomagnet array, and sensing a magnetic coupling of the nanomagnets of the nanomagnet subset to solve the quadratic optimization problem.

Magnetic coprocessor and method of use

Aspects of gait matching are described herein. In one embodiment, a method of gait matching includes identifying a gait cycle timing in a data sequence captured by an inertial sensor, splitting the data sequence into a gait cycle segment, resampling the gait cycle segment, and estimating a rotation matrix for the resampled gait cycle segment. The rotation matrix, in one embodiment, can be estimated by minimizing a root mean squared deviation between the resampled gait cycle segment and a reference gait cycle segment using the Kabsch algorithm, for example. The method further includes calculating an aligned gait cycle segment from the resampled gait cycle segment using the rotation matrix, and generating a similarity measure between the aligned gait cycle segment and the reference gait cycle segment. The Kabsch algorithm can be used to minimize error and reduce identity authentication errors.

A magnetic system for solving a quadratic optimization problem by associating each of a plurality of variables of a quadratic optimization problem with a nanomagnet of a nanomagnet array, driving the nanomagnets of the nanomagnet array to an excited state, allowing the nanomagnets of the nanomagnet array to enter a relaxed state after being driven to an excited state, wherein the nanomagnets magnetically couple with one another in the relaxed state to minimize the total magnetic coupling energy of the nanomagnet array, and sensing a magnetic coupling of the nanomagnets of the nanomagnet array to solve the quadratic optimization problem.

A system and method for image-processing that will facilitate automatically analyzing and estimating atomic force microscopy (AFM) images and magnetic force microscopy (MFM) images of fabricated nanomagnetic arrays to identify the magnetization states of the nanomagnets in the array. The system and method will automatically estimate the magnetization states of nanomagnetics disks into one of a plurality of energy minimum magnetization state configurations and provide an annotated image of the results of the estimation.

System and method for estimating the magnetization states of a nanomagnet array

A novel, linear modeling method to model a face recognition algorithm based on the match scores produced by the algorithm. Starting with a distance matrix representing the pair-wise match scores between face images, an iterative stress minimization algorithm is used to obtain an embedding of the distance matrix in a low-dimensional space. A linear transformation used to project new face images into the model space is divided into two sub-transformations: a rigid transformation of face images obtained through principal component analysis of face images and a non-rigid transformation responsible for preserving pair-wise distance relationships between face images. Also provided is a linear indexing method using the linear modeling method to perform the binning or algorithm-specific indexing task with little overhead.

Indexing face templates using linear models

A method of reconstructing biometric face image templates of a face recognition system (FRS) using the match scores or distances provided by the FRS. The match scores represent the distance between a image introduced to the FRS and the unknown image template stored in the FRS. The present method uses an affine transformation approximating the unknown algorithm within the FRS and the match scores provided by the FRS to determine the coordinates of the unknown target template. The coordinates of the unknown target template are then applied to a pseudo-inversion of the affine transformation to produce a reconstructed image template of the unknown target. This reconstructed image template can then be used to 'break-in' to the FRS.

Reconstruction of biometric image templates using match scores

The present invention provides a system and method for recovering material properties of non-rigid objects. The method includes, for example, the steps of: establishing a plurality of three-dimensional point correspondences of the non-rigid object in an unstressed and stressed state; from the plurality of point correspondences, generating a finite element model of the non-rigid body having initial material properties and generating a finite element strain distribution; detecting abnormal areas of the non-rigid body by comparing finite element strain levels from the strain distribution; and determining at least one material property of the abnormal areas. The system includes, for example, a general or personal computer with, optionally, one or more digital cameras and range finding devices for acquiring and processing three-dimensional correspondence data associated with the non-rigid object being an unstressed and stressed state. Among the plurality of material properties recoverable by the present invention are material elasticity and geometry. An iterative descent method is utilized to refine the finite element model and recover the missing or estimated material properties.

Growing community of inventors

Tampa, FL, United States of America

Sudeep Sarkar