Object recognition model establishment method and object recognition method

A technology for object recognition and establishment of methods, applied in biological neural network models, neural learning methods, character and pattern recognition, etc., and can solve problems such as complex elastic deformation of objects, posture changes, and visual changes

Active Publication Date: 2017-04-19
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above problems in the prior art, that is, to solve the technical problems of complex elastic deformation, attitude changes and visual cha

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 model establishment method and object recognition method
  • Object recognition model establishment method and object recognition method
  • Object recognition model establishment method and object recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.

[0051] The core idea of ​​the embodiment of the present invention is to propose a new structural network layer in the deep learning algorithm, and use the mean field algorithm to perform fast structural reasoning on it, and use a structural network layer to model the intrinsic structural properties of objects, thereby expressing Different appearance changes of objects, and use the deep learning algorithm to train the deep structure model end-to-end, so as to learn effective structural parameters, and finally obtain the structural expression of the object.

[0052] An embodiment of the present invention provides a method for establishing an obj...

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 present invention relates to an object recognition model establishment method and an object recognition method. The object recognition model establishment method includes the following steps that: an input image is obtained; the depth feature of the input image is extracted; structuralization modeling is performed for an object in the input image based on a random field structure model, so that the structuralized expression of the object can be obtained; and structural parameters are learned through using a gradient back-propagation algorithm based on the structuralized expression of the object, and a gradient is calculated, and learning and training are performed through suing a stochastic gradient descent algorithm, so that an object recognition model can be obtained. With the object recognition model establishment method and the object recognition method provided by the embodiments of the invention adopted, the technical problems of complex elastic deformation, attitude change and visual change of an object in a visual task can be solved, and the structural expression ability of a deep network model is improved. The object recognition model establishment method and the object recognition method provided by the embodiments of the present invention can be applied to a plurality of fields involving object recognition, such as object classification, object detection and face recognition fields.

Description

technical field [0001] Embodiments of the present invention relate to the technical fields of pattern recognition, machine learning and computer vision, and in particular to a method for establishing an object recognition model and an object recognition method. Background technique [0002] Since the beginning of the 21st century, with the rapid development of Internet technology and the popularization of mobile phones, cameras, and personal computers, image data has shown explosive growth. Google+ has uploaded 3.4 billion pictures within 100 days of its launch, and the picture data of the famous social networking site Facebook has exceeded 10 billion. On the other hand, with the need to build a safe city, the number of surveillance cameras is increasing. According to incomplete statistics, the number of surveillance cameras in Beijing alone exceeds 400,000, and the number of surveillance cameras in the country has reached 2,000. More than 10,000, and still growing by 20% p...

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): G06K9/62G06K9/46G06N3/08
CPCG06N3/084G06V10/462G06F18/214
Inventor 黄凯奇刘康伟
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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