基于深度半监督学习的小样本金属工件表面缺陷分割

Deep semi-supervised learning approach for few-shot segmentation of surface defects on metal workpieces

针对工业应用场景下缺少缺陷样本的问题,提出了一种仅需要极少缺陷样本的金属工件表面缺陷分割方法。该方法结合了图像生成技术和半监督学习策略,通过利用极少缺陷图像提取的小尺寸缺陷图像来训练缺陷生成模型,然后将生成的缺陷图像嵌入到正常图像中以实现数据增广。其次,采用半监督学习策略训练分割网络,以减小生成数据与真实数据分布之间的差异对模型的不良影响。在真实的金属工件机器视觉检测系统上的验证结果表明,半监督的训练策略提高了分割模型对真实缺陷的泛化能力,所提方法能够在仅使用5张缺陷样本图像的条件下取得较高的分割精度。

In response to the scarcity of defect samples in industrial applications,this paper proposed a method for segmenting surface defects in metal workpieces with only a minimal number of required defect samples.The method combined image gene-ration techniques with a semi-supervised learning strategy.It utilized small-sized defect patches,and extracted from a minimal number of defect images to train a defect generation model.Subsequently,the method integrated these generated defect images into normal images to facilitate data augmentation.Additionally,the method applied a semi-supervised learning strategy to train the segmentation network,aiming to mitigate the adverse effects of differences between generated and real data distributions.The experimental phase involved conducting tests on a real-world computer vision detection system for metal workpieces.The results demonstrate that the semi-supervised training strategy significantly enhances the segmentation model’s generalization ability to real defects.The method achieves high segmentation accuracy using only five defect sample images.