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

Image recognition method based on multi-column convolutional neural network fuzzy evaluation

A convolutional neural network, fuzzy evaluation technology, applied in biological neural network models, character and pattern recognition, neural architecture, etc., can solve problems such as image noise, distortion, and difficult to effectively identify

Inactive Publication Date: 2017-05-10
SHENYANG POLYTECHNIC UNIV
View PDF4 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traffic signs have the characteristics of bright colors and obvious shape features. Under normal circumstances, the image information of traffic signs is relatively clear, but the images of traffic signs collected under natural conditions are easily affected by external conditions, resulting in noise in the collected images. and distortion, making it difficult to effectively identify

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 multi-column convolutional neural network fuzzy evaluation
  • Image recognition method based on multi-column convolutional neural network fuzzy evaluation
  • Image recognition method based on multi-column convolutional neural network fuzzy evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0123] refer to Figure 1 to Figure 10 , Table 1 to Table 4, the image recognition method based on multi-column convolutional neural network fuzzy evaluation, the steps are as follows:

[0124] (1) From the standard GTSRB (German Traffic Sign Recognition Benchmark) data set, randomly select 5000 images collected in the real environment, with low resolution, different light intensity, partial occlusion, angle of view tilt, motion blur and other images that are not conducive to classification, and perform Binarization, histogram equalization, adaptive histogram equalization, image adjustment, morphological processing, such as Figure 1-Figure 10 shown.

[0125] (2) Input the image of file 1 into a multi-column convolutional neural network for training to obtain the final network structure and parameters, and input test data that is not repeated with the training set. The recognition effect of each column of convolutional neural network is shown in Table 3. Show.

[0126] (3) ...

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 method based on multi-column convolutional neural network fuzzy evaluation. By combining an image preprocessing technology, a convolutional neural network and a fuzzy mathematical method, interference information in an image sample acquired in the real environment is overcome by adopting different preprocessing technologies from different perspectives respectively, feature information beneficial to recognition is strengthened, the preprocessed image is input to the preprocessed and optimized multi-column convolutional neural networks having different structures respectively, then fuzzy evaluation based on comprehensive affiliation degree and discrete affiliation degree is performed on the output results of the multi-column convolutional neural networks by adopting a fuzzy matrix to determine a fuzzy evaluation manner suitable for the image, and a recognition result is finally accurately obtained.

Description

Technical field: [0001] The invention relates to an image recognition method with interference and deformation, in particular to an image recognition method based on fuzzy evaluation of a multi-column convolutional neural network. Background technique: [0002] The continuous development of computer technology and information technology has made computer intelligent image recognition technology more and more widely used. Computer intelligent image recognition technology can quickly obtain the required information to help people think and make better decisions. Real-scene image recognition, such as traffic sign recognition, face recognition, fire flame recognition, etc., is of great significance, and it is also more uncertain than printed text recognition due to the change of image acquisition conditions at any time. [0003] The present invention provides an image recognition method based on multi-column deep neural network fuzzy evaluation, which does not require complex f...

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): G06K9/62G06N3/04
CPCG06N3/043G06F18/24
Inventor 钟玲张志佳于雅洁张兴坤郭婷许钟子珩王艺潭
Owner SHENYANG POLYTECHNIC UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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