An active learning and deep learning combined aluminum material surface defect detection method

Abstract

The invention discloses an active learning and deep learning combined aluminum material surface defect detection method. The method comprises the steps of performing data enhancement on data in a training set by randomly adjusting image saturation, adjusting image brightness, adjusting image contrast and randomly rotating an image; adopting a Weighted-Entry evaluation standard for active learning,ranking the samples to be labeled according to a Weighted-Entry value in an increasing sequence, selecting K highest samples for labeling, and adding the samples into a training set to serve as training samples; and meanwhile, sequencing the samples to be labeled according to an increasing sequence of Entropy (information entropy) by adopting a pseudo labeling algorithm, selecting the lowest H samples, and taking a prediction result of the model as a pseudo label to serve as additional temporary training data of next training. An SEResNet-152 neural network structure is adopted, the neural network structure is based on a ResNet-152 network model, an SE module is added behind each Resinual module, and the SE module is used for calculating the weight proportion relation between channels ofa feature map.

Description

technical field [0001] The invention relates to the field of detection of surface defects of aluminum materials, in particular to a detection method of surface defects of aluminum materials combined with active learning and deep learning. Background technique [0002] With the rapid development of deep learning and the advancement of technology, deep learning algorithms have made significant progress in the field of computer vision, and have been widely used in many fields such as face recognition, vehicle recognition, and road condition recognition. Deep learning algorithms can use huge training data (such as ImageNet, etc.) to conduct a large amount of training on the algorithm model, so that the trained model can easily complete tasks such as image classification, scene classification, and image segmentation, and achieve an excellent accuracy rate. However, deep learning methods rely heavily on large and high-quality data sets such as ImageNet. In reality, there are no su...

AI Technical Summary

Problems solved by technology

[0008] There are currently two main problems: in the prior art, "Fine-Tuning Convolutional NeuralNetworks for Biomedical Image Analysis: Actively and Incrementally" and "Suggestive annotation: A deep active learning framework for biomedical imagesegmentation" are both aimed at the field of medical images The proposed method for image classification and image segmentation problems, due to the different characteristics of medical images and industrial non-destructive testing images, the accuracy of the method is not ideal when applied to industrial non-destructive testing image data

At the same time, the work of the above two papers is the binary classification of images or pixels, and the model of binary classification in the industrial production environment is far from enough

Images