Object recognition method and device and storage medium

A technology for object recognition and object classification, which is applied in the computer field to reduce the number of models, improve model performance, and reduce the number of comparisons.

Active Publication Date: 2020-11-13
SUZHOU KEDA TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides an object recognition method, device and storage medium, which can solv

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
  • Object recognition method and device and storage medium
  • Object recognition method and device and storage medium
  • Object recognition method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0050] First, some terms involved in this application are introduced.

[0051]Learning Rate: A way to guide the hyperparameters for tuning the weights of the network through the gradient of the loss function. The lower the learning rate, the slower the loss function changes. Although, using a low learning rate ensures that local minima are not missed, it will take longer for the model to converge.

[0052] Additive Angular Margin Loss (ArcFace loss): On the basis of SphereFace, it improves the normalization of feature vectors and additive angle intervals, improves the inter-class separability and strengthens the intra-class tightness and inter-class Difference loss function.

[0053] Trip...

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 object recognition method and device and a storage medium, and belongs to the technical field of computers. The method comprises the steps: inputting a target image into anobject recognition model, and obtaining the object features and attribute classification results of the target image; wherein the object recognition model is obtained by using multiple groups of sample data to perform multi-stage training on a neural network model, and each group of sample data comprises a sample image, and a category label and an attribute label of the sample image; searching template features matched with the object features in a target feature library corresponding to the attribute classification result to obtain object category information corresponding to the template features; as the object recognition model learns two tasks of object features and object attributes together, the object features and the object attributes can assist each other to improve the model performance during training; sharing of two task network parameters can reduce the number of models and improve the feature extraction speed; and the template features are searched from the target feature library, so that the comparison frequency can be reduced, and the matching efficiency is improved.

Description

technical field [0001] The present application relates to an object recognition method, device and storage medium, belonging to the field of computer technology. Background technique [0002] Face recognition realizes the detection, analysis and comparison of faces in images or videos, including service modules such as face detection and positioning, face feature extraction and face comparison. [0003] Existing face recognition methods include using deep learning-based face recognition models to perform face recognition on images. Under the control and cooperation conditions of this recognition method, face recognition can achieve a relatively high recognition rate, but in scenarios where there are huge changes in motion, lighting, posture, etc., and the definition is low, the recognition accuracy rate drops sharply. Contents of the invention [0004] The present application provides an object recognition method, device and storage medium, which can solve the problem of ...

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
CPCG06N3/08G06V40/168G06V40/172G06V10/751G06N3/045G06F18/2415
Inventor 史晓丽晋兆龙张震国
Owner SUZHOU KEDA TECH
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