Method and system for extracting features in a pattern recognition system

US6178261A · kind A · utility

Assignee

• THE REGENTS OF THE UNIVERSITY OF MICHIGAN · US

Inventors

• William J. Williams, V · Ann Arbor, US
• Eugene J. Zalubas · Ann Arbor, US
• Robert Nickel · Friedrichshafen, DE
• Alfred Hero · Ann Arbor, US
• Jeffrey C. O'Neill · Somerville, US

Key dates

• Filing date: Aug 5, 1997
• Grant date: Jan 23, 2001
• Expiry date: Aug 5, 2017

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V30/10
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Method and system for extracting features from measurement signals obtained from real world, physical signals by first forming an invariant component of the measurement signals and then using a technique based on a noise subspace algorithm. This technique first casts or projects the transformed measurement signals into separate subspaces for each extraneous variation or group of variations. The subspaces have minimal over-lap. The recognition of a particular invariant component within a pertinent subspace is then preferably performed using Singular Value Decomposition (SVD) techniques to generate a pattern recognition signal. A series of transformations can be used to form an invariant component called the Scale and Translation Invariant Representation (STIR). In one embodiment, the first step is to form an appropriate time-frequency representation such as the Reduced Interference Distribution (RID) or other distribution whose properties are covariant with translations in time and frequency and changes in scale. A series of additional transformations including a scale transform yield the STIR representation. Features are then extracted from a set of STIR representations taken as ex…