Deep learning in food science: An insight in evaluating Pickering emulsion properties by droplets classification and quantification via object detection algorithm

Understanding the complicated emulsion microstructures by microscopic images will help to further elaborate their mechanisms and relevance. The formidable goal of the classification and quantification of emulsion microstructure appears difficult to achieve. However, object detection algorithm in deep learning makes it feasible. This paper reports a new technique for evaluating Pickering emulsion properties through classification and quantification of the emulsion microstructure by object detection algorithm. The trained neural network models characterize the emulsion droplets by distinguishing between different individual emulsion droplets and morphological mechanisms from numerous microscopic images. The quantified results of the emulsion droplets presented in this study, provide details of statistical changes at different concentrations of the Pickering interface and storage temperatures enabling elucidation of the mechanisms involved. This methodology provides a new quantitative and statistical analysis of emulsion microstructure and properties. [Display omitted] •Quantitative determination and classification of emulsion microstructures via object detection algorithm become available.•Complicated morphological characteristics can be classified, such as flocculation, coalescence.•Fully quantitative, reproducible, automatic and visualized methodology in determining emulsion properties from a mass of microscopic images.•Higher-level analysis can be processed statistically with experimental results.