Training method and device, recognition method and device, equipment and medium

A training method and image recognition technology, applied in the field of artificial intelligence, can solve problems affecting the quality of POI data and image recognition of signboards, and achieve the effects of reducing labeling costs, improving image recognition accuracy, and reducing noise interference

Pending Publication Date: 2021-04-09
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the process of data collection in real life, many occluded, blurred and non-signboard images will be collected, which will affect the recognition of signboard images, thereby affecting the quality of POI data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Training method and device, recognition method and device, equipment and medium
  • Training method and device, recognition method and device, equipment and medium
  • Training method and device, recognition method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0044] figure 1 It is a schematic flow chart of the training method of the image recognition model according to the embodiment of the present application. This embodiment can be applied to the situation of training the image recognition model, for example, a model for recognizing signboard images, which involves the field of artificial intelligence, especially comput...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an image recognition model training method and device, an image recognition method and device, equipment, a medium and a program product, and relates to the field of artificial intelligence, in particular to the computer vision and deep learning technology. According to the implementation scheme, a sample image and annotation information thereof are acquired, and the annotation information comprises initial annotation information annotated according to positive and negative sample dimensions and at least one kind of fine-grained annotation information obtained by dividing positive samples in the sample image according to different fine-grained dimensions; the sample image is input into a pre-built image recognition model, with the image recognition model comprising at least two independent convolution layers, and the different convolution layers being used for extracting feature vectors of a feature map of the sample image from different dimensions; and according to the annotation information of different dimensions of the sample image, supervised training is performed on the image recognition model by using a loss function corresponding to each dimension, and the loss function is used for returning to the convolution layer of the corresponding dimension. The invention can improve image recognition precision.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to computer vision and deep learning technology, and specifically to a training method for an image recognition model, an image recognition method, a device, equipment, media and program products. Background technique [0002] At present, in the process of POI (Point of Information) data production, a large number of signboard images need to be generated through collection and recognition. [0003] However, in the process of data collection in real life, many occluded, blurred and non-signboard images will be collected, which will affect the recognition of signboard images, and then affect the quality of POI data. Contents of the invention [0004] The present application provides a training method for an image recognition model, an image recognition method, a device, a device, a medium, and a program product, so as to improve the accuracy of image recognition. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06V10/44G06N3/045G06F18/214G06F18/241
Inventor 李辉王洪志董青
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap