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

Integrate Circuit Digital Fingerprinting by Observability Don't Care

In order to solve the problem that intellectual property( IP) core could be forged and illegally copied,a integrate circuit fingerprinting method was proposed. Base on Boolean operation,part of the layout was changed wit...

Vehicle Real Driving Cycle Construction Based on Improved Fuzzy C-means Clustering Algorithm

Since the performance of Fuzzy C-means ( FCM) clustering algorithm depended on the initial clustering center, the iterative was inclined to fall into the local extremum and could not ensure that FCM converges to an optim...

Evolution of A Nonlocal Planar Convex Curve

For the evolution problem of curve influenced by external forces, the evolution of a new nonlocal planar convex curve was studied. The convexity of the evolution curve was kept, and the area of the region surrounded by t...

Ultrasonic Phased Array Testing and Probability of Detection Quantitative Analysis of Polyethylene Pipe Butt Fusion Joints

The customized polyethylene test block was designed with transverse hole defects at depths of 10 mm, 15 mm, 20 mm, 25 mm, 30 mm, 35 mm, 40 mm, whose diameters were 1 mm and 2 mm respectively. Then probability of detectio...

Effect of Urban Road Slope and Speed on Motor Vehicle Emission

To study the impact of urban road gradient change on motor vehicle emissions, based on vehicle emission test platform, the actual road emission data was obtained. Through the vehicle specific power ( VSP) backstepping, t...

Download PDF file
  • EP ID EP478054
  • DOI -
  • Views 98
  • 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