Patent · US Active

Parameter training method for a convolutional neural network

US11599788B2 · kind B2 · utility

1Cited by
0References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 13, 2019
Grant dateMar 7, 2023
Priority date
Expiry dateJan 5, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/70
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A parameter training method for a convolutional neural network (CNN) for classifying image type data representative of a biometric trait. The method includes the implementation, by a data processor of a server, the steps of (a) for at least one data item from an already classified training database, generation of several alternate versions of this data each by application of at least one transformation chosen from a set of reference transformations satisfying a statistical distribution of transformations observed in the training database and (b) training the parameters of the CNN, from the already classified training database augmented with said alternate versions of the data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.