Image recognition method based on biological vision and precise pulse drive neural network

A biological vision and pulse-driven technology, which is applied in biological neural network models, neural learning methods, character and pattern recognition, etc., can solve the problems that pattern recognition cannot adapt to the needs of society and the current market

Inactive Publication Date: 2017-06-13
HANGZHOU DIANZI UNIV
View PDF2 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These technical difficulties make the development of pattern recognition unable to adapt to the needs of society and the current market

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 based on biological vision and precise pulse drive neural network
  • Image recognition method based on biological vision and precise pulse drive neural network
  • Image recognition method based on biological vision and precise pulse drive neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The present invention will be further described below in conjunction with the accompanying drawings.

[0067] figure 1 In , the system structure diagram of the image recognition method based on biological vision and precise pulse-driven neural network is described, combined below figure 1 Give detailed instructions.

[0068] Step S1, feature extraction

[0069] 1.1 Gabor filter processing

[0070] When the simple cells in the V1 area of ​​the receptive field are matched to the unit, the high-order filter of the sparse coding is used to extract the features, and the calculation model of the sparse coding is established by using the two-dimensional Gabor filter function. The general form of sparse coding is:

[0071]

[0072] SC=AH

[0073] where sc i , a i , h j is the element of the unit sparse block SC, A is the basis function of sparse coding, and H is sparse. The most common expression for A is:

[0074]

[0075]

[0076] ||·|| f is in Frobenius n...

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 provides an image recognition method based on biological vision and a precise pulse drive neural network. The method is enlightened by a biological vision layering system, on a feature extraction part of an image, an HMAX model is adopted for simulating and sensing a wild cell running mechanism, Gabor filtering is firstly utilized for enhancing marginal information of an image, images obtained after Gabor filtering in various directions are subjected to max pooling processing, and the aims of extracting major features and carrying out dimension reduction processing are achieved. According to the feature image data processing method, a phase encoding method is selected, pixel information of the images is converted into a pulse phenomenon, thus, space information of the images is considered, and time information of the images is also considered. The method has certain biological basis, and has good feasibility and robustness, and the accuracy of image recognition and classification, especially in noise images is greatly improved.

Description

technical field [0001] The invention relates to the field of pattern recognition and brain-like computing, in particular to an image recognition method based on biological vision and precise pulse-driven neural network. Background technique [0002] Pattern recognition is one of the hottest topics in the field of artificial intelligence. Its goal is to obtain relevant information of the target scene by processing the collected images. However, academician Tan Tieniu of the Chinese Academy of Sciences pointed out at the 2016 China Conference on Artificial Intelligence (CCAI 2016) that a general pattern recognition system has a long way to go - its main bottleneck lies in three aspects: robustness, adaptability and generalization. These technical difficulties make the development of pattern recognition unable to adapt to the needs of society and the current market. [0003] Brain-like computing not only simulates the human brain, but also integrates other disciplines, includi...

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/24
Inventor 徐小良金昕卢文思
Owner HANGZHOU DIANZI UNIV
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