Title:
CONVOLUTIONAL NEURAL NETWORK MODEL-BASED IMAGE RECOGNITION METHOD AND APPARATUS, AND TERMINAL DEVICE
Document Type and Number:
WIPO Patent Application WO/2024/077781
Kind Code:
A1
Abstract:
The present application is applicable to the technical field of image recognition, and provides a convolutional neural network model-based image recognition method and apparatus, and a terminal device. On the basis of a weight matrix of an image to be recognized, the convolutional neural network performs global feature extraction on the image to be recognized. The image recognition method comprises: inputting the image to be recognized into the trained convolutional neural network model, and by means of the convolutional neural network model, sequentially performing feature extraction and recognition on the image to be recognized to obtain a recognition result. The present application can improve the image recognition effect of the convolutional neural network on images of different sizes.
Inventors:
ZHANG HAOKUI (CN)
YANG TAO (CN)
HU WENZE (CN)
WANG XIAOYU (CN)
YANG TAO (CN)
HU WENZE (CN)
WANG XIAOYU (CN)
Application Number:
PCT/CN2022/142241
Publication Date:
April 18, 2024
Filing Date:
December 27, 2022
Export Citation:
Assignee:
SHENZHEN INTELLIFUSION TECH CO LTD (CN)
International Classes:
G06V10/764
Domestic Patent References:
| WO2022036777A1 | 2022-02-24 |
Foreign References:
| CN112215840A | 2021-01-12 | |||
| CN108229379A | 2018-06-29 | |||
| CN112101318A | 2020-12-18 | |||
| CN109726725A | 2019-05-07 |
Attorney, Agent or Firm:
SHENZHEN YIHANG INTELLECTUAL PROPERTY AGENCY (GENERAL PARTNERSHIP) (CN)
Download PDF: