Recognition via high-dimensional data classification

US8406525B2 · kind B2 · utility

Assignees

• The Regents of the University of California · US
• The Board of Trustees of the University of Illinois · US

Inventors

• Yi-Hui Ma · New York, US
• Allen Yang Yang · Cambridge, US
• John N. Wright · Urbana, US
• Andrew William Wagner · Urbana, US

Key dates

• Filing date: Jan 29, 2009
• Grant date: Mar 26, 2013
• Expiry date: Oct 31, 2029

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/7715
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method is disclosed for recognition of high-dimensional data in the presence of occlusion, including: receiving a target data that includes an occlusion and is of an unknown class, wherein the target data includes a known object; sampling a plurality of training data files comprising a plurality of distinct classes of the same object as that of the target data; and identifying the class of the target data through linear superposition of the sampled training data files using l1 minimization, wherein a linear superposition with a sparsest number of coefficients is used to identify the class of the target data.