A weakly supervised learning pipeline for profiled fibre inspection

Automatic profiled fibre recognition and analysis can accelerate quality inspection and contributes to the upgrade of the textile industry. However, these tasks often require significant manual effort to generate instance-level annotations for fully supervised training. In this paper, the authors propose a weakly supervised pipeline for profiled fibre inspection using electron-microscopic (EM) images with only image-level annotations. It automatically identifies fibre instances and estimates shape factors to facilitate fibre quality inspection. As the core of the pipeline, the weakly supervised network (WesNet) is designed to localize hundreds of crowded fibre samples by raw patch generation and fibre sample sifting. Particularly, the composite similarity measurement integrates different patch-wise similarities, enabling the network to distinguish fibre from background robustly. For quality inspection, the pipeline further analyzes the fibre instances, utilizing several efficient techniques to estimate the shape factors. Experiments on the real fibre electron-microscopic images demonstrate the efficacy and efficiency of the pipeline. Results show that WesNet outperforms several supervised and weakly supervised methods, including two state-of-the-art weakly supervised networks. This paper proposes a novel weakly supervised pipeline for profiled fibre recognition and inspection. A weakly supervised network (WesNet) is designed to localize fibre instances in electron-microscopic images with only image-level annotations. The framework automatically measures shape factors to provide reference for fibre quality inspection.image