Texas Instruments Corporation

Raytheon Bbn Technologies Corp.

Manasvi Tickoo

Vinay Sharma

Pradeep Natarajan

Xiaodan Zhuang

Devansh Arpit

Walter Andrews

A method for feature transformation of a data set includes: receiving a data set including original feature samples with corresponding class labels; splitting the data set into a direction optimization set and a training set; using the direction optimization set to calculate an optimum transformation vector that maximizes inter-class separability and minimizes intra-class variance of the feature samples with respect to corresponding class labels; using the optimum transformation vector to transform the rest of the original feature samples of the data set to new feature samples with enhanced discriminative characteristics; and training a classifier using the new feature samples, wherein the method is performed by one or more processors.

Class discriminative feature transformation

A mobile device, such as a smart phone, is provided with a camera and a projector. A user may select a still image or a video sequence and project it onto a viewing surface using the mobile device. Once the viewer selects a preferred perspective view frame, the image frame may be pinned to the viewing surface. After that, the viewer may move the projector to different positions while holding the projector, or sit the projector on a table and the viewed image will be maintained in the same perspective view frame as the initial selected view.

Maintaining distortion-free projection from a mobile device

Growing community of inventors

Cambridge, MA, United States of America

Manasvi Tickoo