Image Recognition Method of Multi-channel Convolutional Neural Network

Journal Title: 河南科技大学学报(自然科学版) - Year 2017, Vol 38, Issue 3

Abstract

To make better use of the feature information implied in the image database,a multi-channel convolutional neural network image recognition method based on image gradients was proposed by making the multi-directional gradients information as basic expression of edge information. Firstly,four gradient images of horizontal,vertical,and two diagonal directions were obtained by processing the image through Sobel operation.Then,four multi-channel convolutional neural network was built to learn the features of gradient images of four different directions,and the features of four different directions were fused by stochastic feature fusion. Finally,the classification results were obtained through the classifier after batch normalization process for the features of samples. The proposed model was verified on database Cifar-10 and MNIST. The results show that the proposed model has better generalization ability,and its recognition error rates are reduced by 9. 85% and 0. 38%respectively compared to single-channel convolution neural network in the two databases.

Authors and Affiliations

Chaoren YI, Yanni DENG

Keywords

Related Articles

Design of Gear Flowmeter Transmitter Based on CPLD + ARM

To improve the measurement precision of gear flowmeter effectively, and eliminate the original pulse signal error, a gear flowmeter transmitter based on complex programmable logic device ( CPLD) and advanced RISC machine...

Effects of Additive Concentration on Pool Nucleate Boiling Heat Transfer of Lithium Bromide Solution

The effects of additive concentration on pool nucleate boiling heat transfer of 10%,20% and 30%mass fraction lithium bromide solution was studied with additives Triton X-100. The measurement results show that this additi...

Effect of Different Holding Time on Tribological Properties of AT13 Coating

Plasma spraying technology was utilized to deposit Al2 O3-Ti O2 coatings on 20 steel samples. The prepared coating was heat-treated at 500 ℃ for 1 h, 3 h and 5 h. The friction and wear performance of coatings were tested...

Application of Sensitivity Analysis to Optimization of Vehicle Interior Noise

In view of the noise problem of sport utility vehicle ( SUV) , an acoustic structure coupling model for the vehicle body was established. The acoustic response of the vehicle under the steady stimulation on the left engi...

Construction Disturbance Analysis of Existing Bridge Piles Traversed by Interval Subsurface Excavation Tunnel

The construction disturbance of existing bridge piles traversed by interval subsurface excavation tunnel was analyzed by 3D numerical analysis and site measurement. The results show that the spatial effect of existing br...

Download PDF file
  • EP ID EP478054
  • DOI -
  • Views 90
  • Downloads 0

How To Cite

Chaoren YI, Yanni DENG (2017). Image Recognition Method of Multi-channel Convolutional Neural Network. 河南科技大学学报(自然科学版), 38(3), -. https://europub.co.uk/articles/-A-478054