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

Image recognition method and device and electronic equipment

An image recognition device and image recognition technology, applied in the field of image processing, can solve problems such as no more research on images

Pending Publication Date: 2020-04-03
BEIJING DIDI INFINITY TECH & DEV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no more research on the combination of images in the prior art

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
  • Image recognition method and device and electronic equipment
  • Image recognition method and device and electronic equipment
  • Image recognition method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0120] see figure 2 , is the application provided by the embodiment of the present invention figure 1 The flow chart of the image recognition method of the electronic device is shown. The following will be figure 2 The specific process shown will be described in detail.

[0121] In step S201, the image to be recognized is detected, and the recognition candidate results of each target recognition area in the image to be recognized are obtained.

[0122] In this embodiment, the detection of the image can be identified using a neural network model; other image recognition methods can also be used for identification, for example, by extracting SIFT features, SURF features, and Haar features to identify features to identify images.

[0123] In one embodiment, the image to be recognized is input into a detection model based on a neural network for detection, and a recognition candidate result of each target recognition area in the image to be recognized is obtained.

[0124] I...

Embodiment 2

[0163] In an application scenario, the image recognition method in this embodiment can be used on a car to recognize the images collected by the driving recorder, so as to effectively obtain the obstacles that appear during the driving of the car, and can also obtain the The surrounding environment, thereby improving the safety of the car, can also improve the safety of driving. In this embodiment, it is applied to an electronic device, and the electronic device may be a vehicle-mounted device, and the vehicle-mounted device is connected with an image acquisition device. The electronic device may be a driving computer, and the driving computer may be communicatively connected with the driving recorder to further acquire image or video data collected by the driving recorder.

[0164] In another application scenario, the image processing method in this embodiment may be used in an image processing server, and the image processing server is communicatively connected with the vehi...

Embodiment 3

[0178] The image language model can be obtained by training a neural network model. In an implementation manner, the image language training process may be executed by the same device as that in Embodiment 1 and Embodiment 2. For example, Embodiment 1, Embodiment 2, and Embodiment 3 may all be executed by an image processing server. In another implementation manner, the first embodiment, the second embodiment and the third embodiment may all be executed by different devices. For example, the steps in Embodiment 1 or Embodiment 2 can be executed on a vehicle-mounted device, and the steps in Embodiment 3 can be executed in a server.

[0179] For this example, see Figure 6 , the image language model is obtained by training in the following manner.

[0180] Step S401, converting each image word in the training image set into a graph vector, the training image set includes image words obtained in advance, and each image word is an image set.

[0181] In this embodiment, before ...

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 embodiment of the invention provides an image recognition method and device and electronic equipment. The image recognition method comprises the steps of detecting a to-be-recognized image to obtain a recognition candidate result of each target recognition area in the to-be-recognized image; combining the identification candidate results of all the target identification areas to obtain a plurality of prediction target sequences; calculating the plurality of prediction target sequences by using a pre-trained image language model to obtain a combination probability of each prediction targetsequence; and obtaining an identification result of the to-be-identified image according to the combination probability of each prediction target sequence.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an image recognition method, device and electronic equipment. Background technique [0002] In speech recognition or machine translation, a correction model can be used to further correct the recognition results. Since there are fixed collocations and combinations between words, words, and phrases in natural language, the final result can be improved through correction. Match the collocation and combination between words, words and phrases. However, there is no more research on the combination of images in the prior art. Contents of the invention [0003] In view of this, the purpose of the embodiments of the present invention is to provide an image recognition method, device and electronic equipment. [0004] In the first aspect, an image recognition method provided by an embodiment of the present invention includes: [0005] Detecting the image to be recognized to o...

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): G06K9/00G06K9/32G06K9/34G06K9/62
CPCG06V20/52G06V10/25G06V30/153G06F18/24G06F18/2415G06F18/214
Inventor 赵元
Owner BEIJING DIDI INFINITY TECH & DEV
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