Aluminum Plate Surface Defects Classification Based on the BP Neural Network

Qing Hua Li; Di Liu

doi:10.4028/www.scientific.net/AMM.734.543

Paper Titles

The Fractal Interpolating Algorithm of 3D Terrain Surface Reconstruction
p.526

The Study of Ant Colony Algorithm in Hydraulic Breakdown Diagnosis
p.530

Using Kernel Fisher Criterion for Gaussian Kernel Optimization
p.534

Zero-Displacement-Error ITAE Standard Forms Based on Modified Particle Swarm Optimization
p.539

Aluminum Plate Surface Defects Classification Based on the BP Neural Network
p.543

Application of Dynamic Chaos PSO Algorithm in Elevator Configuration
p.548

JPEG Image Encryption Algorithm Based on Three-Dimensional Multi-Chaotic System
p.554

One-Step Weights Updating Back-Propagation Neural Network for Nonlinear System Identification
p.558

Face Recognition by PCA and Improved LBP Fusion Algorithm
p.562

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 734Aluminum Plate Surface Defects Classification...

Aluminum Plate Surface Defects Classification Based on the BP Neural Network

Abstract:

The aluminum plate surface defects recognition method of BP neural network is studied based on target detection .In order to detect the defects, the target image is binaried by adaptive threshold method. After binarizing the target image, three kinds of image feature, including geometric feature, grayscale feature and shape feature, are extracted from the target image and its corresponding binary image. The defects classification model based on back-propagation neural network utilizes three layers neural network structure model and the hyperbolic tangent function of S function as the activation function, the number of neurons in hidden layer is confirmed by experiments. The experimental results show that the classification accuracy of BP neural network classification model as high as 94%, this can meet our requirements.