Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image identification method based on Spiking neural network

A neural network and image recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of inaccurate image recognition, low network recognition accuracy, low image recognition efficiency, etc., and achieve simple and clear model structure, The effect of reducing complexity and improving efficiency

Inactive Publication Date: 2017-09-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF2 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned prior art, the purpose of the present invention is to provide a kind of image recognition method based on Spiking neural network, to solve the problem that the prior art has low image recognition efficiency, can not accurately recognize the features of the image, and the sequence learned by the neuron has a bias. Technical problems such as low network recognition accuracy caused by migration

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 identification method based on Spiking neural network
  • Image identification method based on Spiking neural network
  • Image identification method based on Spiking neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] (1) For example Figure 5 The three sample images shown are processed separately, the images are uniformly sized, and converted into grayscale images;

[0053] (2) Set the relevant parameters of the entire calculation model as shown in Table 1

[0054] Table 1 Parameter settings of the calculation model

[0055]

[0056] (3) Select a 16×16 receptive field to perform feature extraction on a 256×256 image, and the Gaussian difference weight product is as follows image 3 The original image in (a) will be converted to image 3 Feature image shown in (b);

[0057] (4) Use 2×2 maximum pooling to sample the obtained feature image, and get as follows image 3 The sampled image shown in (c);

[0058] (5) Align and adjust the obtained feature intensity information using delayed phase encoding, such as Figure 4 shown. The image information is re-arranged into the subthreshold membrane voltage oscillation function, and the time series is adjusted and then compressed to ...

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 an image identification method based on a Spiking neural network, belongs to the technical field of image processing, and aims to solve the problems of low image identification efficiency and incapability of accurately identifying image features in the prior art. The method comprises the following steps: separating the image features on the basis of a Gaussian differential filtering thought; performing coding with a phase retardation method; and after coding is finished, learning an obtained feature sequence with a Spiking neural network learning algorithm to obtain an identification output result finally. Compared with a conventional Spiking image identification method, the method has the advantages that the image features are refined, local characteristics of images are specifically optimized by means of dimension reduction, integration, separation, extraction and the like, and the Spiking neural network learning algorithm based on a membrane voltage is used, so that the efficiency and accuracy of an identification process are increased. The image identification method is applied to image identification, image classification, image feature extraction and Spiking learning algorithm application, and relates to the fields of machine learning, Spiking neural networks, phase retardation coding and the like.

Description

technical field [0001] The invention relates to the technical fields of machine learning, Spiking neural network and delayed phase encoding, in particular to an image recognition method based on Spiking neural network. Background technique [0002] The sensitivity of the Spiking neural network to image processing makes it frequently appear in the simulation of the transformation of image information by simulated retinal neurons. Its spatio-temporal encoding characteristics of data enable the Spiking neural network to identify and process image content of different sizes and angles in image processing problems, and have shown good results. [0003] In traditional image recognition problems, the computer performs a feature index on the image and then queries it. The reusability of this kind of method is not high, and the operation is complicated in practical application, and the certain effect can only be achieved after several times of debugging. Some algorithms even use th...

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): G06K9/62G06K9/46
CPCG06V10/443G06F18/214
Inventor 屈鸿陈珊马琳垚张马路曾志陈一
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
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