Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for recognizing picture by combining text and picture

A picture recognition and picture technology, which is applied in the computer field, can solve the problems of large DNN models and massive data, and achieve the effects of improved accuracy, strong recognition ability, and easy utilization

Inactive Publication Date: 2018-03-30
广州唯品会研究院有限公司
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The deep learning model has greatly improved the accuracy of image recognition. At the same time, it also has a well-known problem. The DNN model is very large, and training this model requires a large amount of data with reference standards.

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
  • Method and device for recognizing picture by combining text and picture
  • Method and device for recognizing picture by combining text and picture
  • Method and device for recognizing picture by combining text and picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] like figure 1 As shown, the embodiment of the present invention provides a method for combining text and pictures for picture recognition, the method mainly includes the following steps:

[0057] 101. Acquire a first tag in the text information.

[0058] Specifically, the text information here is mainly the text information related to the picture, including the text information related to the picture input by the user when searching, the text information corresponding to the picture (that is, the text information of the additional introduction related to the picture) and Descriptive text information displayed directly on or existing on the image. Therefore, the above step 101 may include: identifying the tags included in the text information input by the user; identifying the tags included in the text information corresponding to the pictures input by the user; and identifying the tags included in the explanatory text information on the pictures input by the user Labe...

Embodiment approach

[0070] 1. When it is desired to search or query new pictures based on existing attribute label data, under the user's search command, the recognition system will identify the multiple searched pictures based on the first label data and the second label data of the label library, Get more accurate recognition results. The tag library here may be a tag library after performing conventional data processing on the first tag data and the second tag data, and the data processing includes function calculation, sorting, screening, etc.;

[0071] 2. It is hoped that after performing in-depth processing on the first tag data and the second tag data, the recognition is performed according to the processing results, and then the recognition results are output. The in-depth processing here includes: adding the first label data and the second label data to the original label library to form a larger and more comprehensive image label data, and then using the preset neural network recognitio...

Embodiment 2

[0079] like figure 2 As shown, the embodiment of the present invention provides a method for combining text and pictures for picture recognition, the method mainly includes the following steps:

[0080] 201. Identify the tags included in the text information input by the user; and / or identify the tags included in the text information corresponding to the picture input by the user; and / or identify the tags included in the explanatory text information on the picture input by the user .

[0081]Specifically, the tags included in the text information are determined according to the tag rules predefined by the recognition system and the text information input by the user. The text information corresponding to the input picture here refers to the text information determined by the system according to the type of the input picture or the known picture-related information (such as additional picture introduction), and the corresponding text information can also be determined accordi...

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 a method and device for recognizing a picture by combining a text and the picture, belonging to the technical field of computers. The method comprises a step of acquiring a first tag in text information, a step of identifying and acquiring a second tag indicated by a plurality of picture elements contained in the picture, and a step of outputting a recognition result according to the first tag and the second tag. The extraction is carried out by combining related text information and image information of the picture, corresponding tags are added to a tag library, training data of the tag library is increased, a neural network recognition model with stronger recognition ability is obtained, a basis is provided for enriching knowledge maps of people or goods, commodities and the like in a laster stage, a new object is identified on the above basis, finally, the accuracy of recognition is greatly improved, and the method and the device can be well utilized in the field of network search engines or commodity shopping platforms.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for recognizing pictures by combining text and pictures. Background technique [0002] The existing image recognition-based scheme mainly uses a large number of marked pictures as a training set, and then learns an image recognition model based on the training set, uses the learned model to identify and analyze newly published pictures, and recognizes the characters in the pictures , animals, objects and other information, and then map the identified information with content tags. Due to the rapid development of Deep Neural Network (DNN) in the field of image recognition, the accuracy of image recognition has been greatly improved, and image recognition has also been widely used in the industry. The deep learning model has greatly improved the accuracy of image recognition. At the same time, it also has a well-known problem. The DNN model is very large, and...

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
IPC IPC(8): G06K9/00G06K9/32G06F17/30G06N3/04
CPCG06F16/5866G06V30/413G06V20/62G06N3/045
Inventor 张智祺徐然郭安琪黄惠燕
Owner 广州唯品会研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com