Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles

Abstract

Holograms of colloidal particles can be analyzed with the Lorenz-Mie theory of light scattering to measure individual particles' three-dimensional positions with nanometer precision while simultaneously estimating their sizes and refractive indexes. Extracting this wealth of information begins by detecting and localizing features of interest within individual holograms. Conventionally approached with heuristic algorithms, this image analysis problem can be solved faster and more generally with machine-learning techniques. We demonstrate that two popular machine-learning algorithms, cascade classifiers and deep convolutional neural networks (CNN), can solve the feature-localization problem orders of magnitude faster than current state-of-the-art techniques. Our CNN implementation localizes holographic features precisely enough to bootstrap more detailed analyses based on the Lorenz-Mie theory of light scattering. The wavelet-based Haar cascade proves to be less precise, but is so computationally efficient that it creates new opportunities for applications that emphasize speed and low cost. We demonstrate its use as a real-time targeting system for holographic optical trapping.

arXiv comment8 pages, 4 figures

References in corpus (7)

• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Characterizing and tracking single colloidal particles with video holographic microscopy
• Using the Discrete Dipole Approximation and Holographic Microscopy to Measure Rotational Dynamics of Non-spherical Colloidal Particles
• Imaging Multiple Colloidal Particles by Fitting Electromagnetic Scattering Solutions to Digital Holograms
• Holographic Measurements of Anisotropic Three-Dimensional Diffusion of Colloidal Clusters
• Holographic characterization of imperfect colloidal spheres
• Stimulus-responsive colloidal sensors with fast holographic readout

Cited by in corpus (19)

• Deep learning in nano-photonics: inverse design and beyond
• Quantitative Digital Microscopy with Deep Learning
• Machine Learning Holography for 3D Particle Field Imaging
• The point spread function in interferometric scattering microscopy (iSCAT). I. Aberrations in defocusing and axial localization
• Extracting quantitative biological information from brightfield cell images using deep learning
• CATCH: Characterizing and Tracking Colloids Holographically using deep neural networks
• Quantitative differentiation of protein aggregates from other subvisible particles in viscous mixtures through holographic characterization
• Machine learning reveals complex behaviours in optically trapped particles
• Quantitative Phase Imaging and Artificial Intelligence: A Review
• Microparticle cloud imaging and tracking for data-driven plasma science
• Above and beyond: Holographic tracking of axial displacements in holographic optical tweezers
• Roadmap for Animate Matter
• Point spread function engineering for spiral phase interferometric scattering microscopy enables robust 3D single-particle tracking
• Identification of particle mixtures using machine-learning-assisted laser diffraction analysis
• Identification of 2D colloidal assemblies in images: a threshold processing method versus machine learning
• Inferring activity from the flow field around active colloidal particles using deep learning
• Digital video microscopy enhanced by deep learning
• Machine learning holography for measuring 3D particle size distribution
• Machine Learning Forecasting of Active Nematics