基于残差网络和迁移学习的瓶坯表面质量检测研究

Research on Surface Quality Detection of Bottle Preform Based on ResNet and Transfer Learning

提出了一种基于残差网络和迁移学习的瓶坯表面质量检测方法,设计了一种采用ResNet的迁移学习网络模型,通过瓶坯图像采集平台来采集图像样本,通过图像增强方式扩展样本数量,实现瓶坯缺陷分类和识别。实验分析表明,该模型在瓶坯缺陷检测上具有可行性和一定的准确率。

A method for bottle preform surface quality detection based on residual network and transfer learning is proposed,and a transfer learning network model using ResNet is designed.The bottle preform image acquisition platform is used to collect image samples,and the number of samples is expanded through the image enhancement method to realize the classification and identification of bottle preform defects.Experimental analysis shows that the model is feasible and accurate in detecting bottle preform defects.