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

Image recognition and neural network model training method, device and system

A neural network model and image recognition technology, applied in the field of image processing, can solve the problem of unbalanced performance of traditional models, and achieve the effect of balancing image recognition performance

Active Publication Date: 2019-08-30
MEGVII BEIJINGTECH CO LTD
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In short, for different data sets, the traditional model has the problem of unbalanced performance

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 and neural network model training method, device and system
  • Image recognition and neural network model training method, device and system
  • Image recognition and neural network model training method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0048] The image recognition method provided by this application can be applied, but not limited to, such as figure 1 shown in the application environment. Wherein, the photographing device 12 can obtain the image to be recognized of the object to be recognized, and send the image to be recognized to the computer device 11; the computer device 11 can extract the target image feature from the image to be recognized, and perform image processing according to the target image feature. Image recognition processing such as verification, image search, image clustering, etc. Wh...

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 relates to an image recognition and neural network model training method, device and system and a readable storage medium. The method comprises the steps of obtaining a to-be-identifiedimage; inputting the to-be-identified image into a neural network model, and outputting a target image feature of the to-be-identified image, wherein the neural network model is trained based on eachsample image belonging to a plurality of training data sets, a difference value between data set characteristic distances corresponding to any two training data sets is smaller than a preset thresholdvalue, and the data set feature distance is an inter-data set class feature distance or an intra-data set class feature distance; and performing image recognition processing on the target image features according to a judgment threshold corresponding to the neural network model to obtain an image recognition result of the to-be-recognized image. For different data sets, the method can show relatively balanced image recognition performance.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image recognition and neural network model training method, device, system and readable storage medium. Background technique [0002] At present, face recognition tasks are divided into three categories, face verification (verifying whether multiple face images correspond to the same person), face search (finding the image most similar to the face image to be recognized in multiple face images in the bottom library) ) and face image clustering (classifying multiple face images to be recognized). At present, the popular method is to perform different types of face recognition tasks by training deep network models to convert face images into points in feature space (feature space). On this basis, the face recognition task is equivalent to training a good deep network model, converting the face image to be recognized into points in the feature space, that is, ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/168G06V40/172G06N3/045G06F18/23213G06F18/24
Inventor 王塑王泽荣刘宇赵俊杰杜佳慧肖琳程昌茂
Owner MEGVII BEIJINGTECH CO LTD
Features
  • Generate Ideas
  • 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