We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Microplastic pollution assessment with digital holography and zero-shot learning
Summary
Researchers developed a digital holography system combined with zero-shot machine learning to identify and characterize microplastics in environmental samples without requiring labeled training data, offering a promising automated tool for large-scale microplastic monitoring.
Microplastic (MP) pollution poses severe environmental problems. Developing effective imaging tools for the identification and analysis of MPs is a critical step to curtail their proliferation. Digital holographic imaging can record the morphological and refractive index information of such small plastic fragments, yet due to the heterogeneous sampling environments and variations in the MP shapes, traditional supervised learning methods are of limited use. In this work, we pioneer a zero-shot learning method that combines the holographic images with their semantic attributes to identify the MPs in heterogeneous samples, even if they have not appeared in the training dataset. It makes use of the attention mechanism for image feature extraction and the Kullback–Leibler divergence both to alleviate the domain shift problem and to guide the training of the mapping function. Experimental results demonstrate the effectiveness of our approach and the potential use in a wide variety of environmental pollution assessments.