Supercharge Your Innovation With Domain-Expert AI Agents!

Training method and device of image recognition model and image recognition method and device

An image recognition and training method technology, applied in the field of image recognition, can solve the problems of low accuracy, omission of feature information, incompleteness, etc., to achieve the effect of improving the accuracy

Pending Publication Date: 2021-12-31
BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Currently, image recognition for text or mathematical formulas usually uses the seq2seq model. CNN is used to extract a single image feature in the encoder of the model, and then the image feature is input to the decoder of the model for decoding, and a single image feature of the image is extracted in the encoder. Only focus on the feature information of the current scale, which will lead to the omission and incompleteness of feature information, resulting in the omission of information in image recognition, the effect of image recognition is not ideal, and the accuracy rate is not high

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 of image recognition model and image recognition method and device
  • Training method and device of image recognition model and image recognition method and device
  • Training method and device of image recognition model and image recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the present application. Therefore, the present application is not limited by the specific implementation disclosed below.

[0070] Terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only, and are not intended to limit the one or more embodiments of the present application. As used in one or more embodiments of this application and the appended claims, the singular forms "a", "the", and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of th...

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 provides a training method and device of an image recognition model and an image recognition method and device. The image recognition model comprises an encoder and a decoder, and the training method of the image recognition model comprises the steps of obtaining training data, where the training data comprise sample images and sample description information corresponding to the sample images; inputting the sample image into the encoder to obtain at least two image feature vectors corresponding to the sample image; inputting each image feature vector and the sample description information into the decoder to obtain a decoding result output by the decoder; calculating a loss value according to the decoding result and the sample description information; and adjusting parameters of the image recognition model according to the loss value to train the image recognition model. Through the method, the image feature vectors of at least two image features can be fused at a decoder, and the image recognition accuracy is improved by referring to the difference of the image features under each scale.

Description

technical field [0001] The present application relates to the technical field of image recognition, and in particular to a training method and device for an image recognition model, an image recognition method and device, a computing device, and a computer-readable storage medium. Background technique [0002] With the advancement of science and technology and the rapid development of Internet technology, images have become the main way for people to record and share information, and the recognition of text or mathematical formulas recorded in images has become more and more widely used in daily life. [0003] Currently, the seq2seq model is usually used for image recognition of text or mathematical formulas. CNN is used to extract a single image feature in the encoder of the model, and then the image feature is input to the decoder of the model for decoding, and a single image feature of the image is extracted in the encoder. Only focusing on the feature information of the ...

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): G06K9/62G06K9/46
CPCG06F18/2411G06F18/214
Inventor 宋振旗李长亮唐剑波
Owner BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com