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
AI summary Read the abstract
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.
More Papers Like This
Zero-shot learning for holographic context analysis in microplastics probing
AI summary Read the abstract
Researchers developed a zero-shot machine learning method using attribute embedding for holographic image analysis to identify unknown microplastic types without requiring labelled training data for every class. The approach reduces the need for manual dataset annotation and improves practical deployment of microplastic detection systems.
Digital holography with deep learning and generative adversarial networks for automatic microplastics classification
AI summary Read the abstract
Researchers combined digital holography with deep learning and generative adversarial networks to automatically classify microplastic particles in water. The system achieves high accuracy even with limited training images, making it a practical tool for automated marine microplastic monitoring.
Microplastic Identification via Holographic Imaging and Machine Learning
AI summary Read the abstract
Researchers combined holographic imaging with machine learning algorithms to automatically identify and classify microplastics in water samples, achieving accurate particle detection without manual microscopy. This automated approach could significantly speed up microplastic monitoring in environmental samples.
Automatic Detection of Microplastics by Deep Learning Enabled Digital Holography
AI summary Read the abstract
Researchers developed a digital holography system combined with deep learning to automatically detect and identify microplastics in water without manual image analysis. The system processes raw holographic images directly, offering a faster and more scalable approach to microplastic monitoring in environmental samples.
Holographic Classifier: Deep Learning in Digital Holography for Automatic Micro-objects Classification
AI summary Read the abstract
Researchers developed a deep learning system using digital holography to automatically classify micro-objects such as microplastics and pollutant particles without manual image processing. The system achieved fast, accurate identification, offering a promising automated tool for environmental pollution monitoring.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.