Two-Stream Convolutional Neural Network Based on Gradient Image for Aluminum Profile Surface Defects Classification and Recognition

Abstract

In this paper, a novel two-stream convolutional neural network based on gradient image is performed to effectively classify and identify aluminum profiles defects for the first time. Recent feature fusion methods based on two-stream network prove promising performance for defects classification and recognition. In this paper, we use data enhancement methods to obtain a large number of samples to prevent the over fitting phenomenon in deep learning. The image gradient is calculated with the Sobel operator, and normalized to transform the data between zero and one under the same dimension. We design a two-stream convolutional neural network model adopting Wavelet transform fusion strategy to realize feature fusion on the ReLU6 layer, which uses the original RGB image of aluminum profile and the gradient image corresponding to the original RGB image as inputs to extract features through two sub-networks and fuses features on a concatenate layer to be input into SVM classifier for classification and recognition. Using Bayesian Optimization function and computing the cross-validation classification error to optimize the hyperparameters to choose the best performance configuration is performed. A series of experimental data, which include accuracy and estimated generalized classification errors of single-stream and two-stream networks with different feature fusion strategies on different fusion layers, are conducted and show that the current model has good convergence, accuracy, stability and generalization. On this basis, this paper also proposes a series of innovative methods for the future research of other defects. INDEX TERMS Aluminum profile surface defects, two-stream network, gradient image, convolutional neural network, SVM.

Lightweight strip steel defect detection algorithm based on improved YOLOv7

“…The projection coefficients of each frame image on the principal components were input into an SVM model for classification, facilitating surface defect detection in steel-strip products. Duan et al 21 utilized a novel two-stream convolutional neural network to extract features from original RGB images and gradient images for the first time. Afterwards, the wavelet transform was used for feature fusion, which was then fed into the SVM classifier to classify and identify the surface defects of the aluminum profiles.…”

Dual-branch information extraction and local attention anchor-free network for defect detection

“…With advances in computer technology, there is a growing interest in using convolutional neural networks (CNNs) for defect detection and fault diagnosis. These methods can be mainly divided into two categories: those that classify defect images based on extracted information 12 , 13 and those that simultaneously determine the position and size of the defects during classification. The former typically uses deep belief networks to analyze images and obtain fault classifications.…”

Research on aluminum defect classification algorithm based on deep learning with attention mechanism

“…With the increasing demand, the quality of industrial products is becoming more and more demanding, however, no matter the process of production or transportation, there is no way to avoid the defects on the surface of the products [1]. For example, due to the complexity of the production environment and the limitations of the processing equipment, the surface of aluminum profiles, as a basic material in industrial manufacturing, is prone to cracks, abrasions, peeling, pits, scratches, miscellaneous colors, dirty spots, and other defects during production and transportation, which can seriously affect the quality of aluminum profiles [2]. Therefore, it is important to automate the classification and identification of defects in aluminum profiles.…”

“…The existing defect recognition classification methods are the manual recognition method, single mechanism recognition method, infrared recognition method, magnetic particle recognition method, eddy current recognition method, magnetic leakage recognition method, machine vision recognition method [3][4][5][6][7], and other seven methods. However, the first six methods mentioned above have the shortcomings of low efficiency and accuracy due to the limitation of the principle.…”