Patent · US Active

Object recognition based on boosting binary convolutional neural network features

US10685262B2 · kind B2 · utility

2Cited by

0References

25Claims

0Family size

Assignee

Intel Corporation · US

Inventors

Anbang Yao · Beijing, CN
Lin Xu · Fremont, US
Jianguo Li · Beijing, CN
Yurong Chen · Beijing, CN

Key dates

Filing date	Mar 20, 2015
Grant date	Jun 16, 2020
Priority date	—
Expiry date	Nov 28, 2035

Classification

Technology area (CPC G)Physics
CPC primaryG06V40/10
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques related to implementing convolutional neural networks for object recognition are discussed. Such techniques may include generating a set of binary neural features via convolutional neural network layers based on input image data and applying a strong classifier to the set of binary neural features to generate an object label for the input image data.

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