Patent · US Active

Sequence transcription with deep neural networks

US9454714B1 · kind B1 · utility

2Cited by
6References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 31, 2014
Grant dateSep 27, 2016
Priority date
Expiry dateJan 3, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V20/63
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods for sequence transcription with neural networks are provided. More particularly, a neural network can be implemented to map a plurality of training images received by the neural network into a probabilistic model of sequences comprising P(S|X) by maximizing log P(S|X) on the plurality of training images. X represents an input image and S represents an output sequence of characters for the input image. The trained neural network can process a received image containing characters associated with building numbers. The trained neural network can generate a predicted sequence of characters by processing the received image.

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