Recent years have witnessed the unprecedented progress of deep learning applications in digital holography (DH). Nevertheless, there remain huge potentials in how deep learning can further improve performance and enable new functionalities for DH. Here, we survey recent developments in various DH applications powered by deep learning algorithms. This article starts with a brief introduction to digital holographic imaging, then summarizes the most relevant deep learning techniques for DH, with discussions on their benefits and challenges. We then present case studies covering a wide range of problems and applications in order to highlight research achievements to date. We provide an outlook of several promising directions to widen the use of deep learning in various DH applications.

The observation and detection of the microplastic pollutants generated by industrial manufacturing require the use of precise optical systems. Digital holography is well suited for this task because of its non-contact and non-invasive detection features and the ability to generate information-rich holograms. However, traditional digital holography usually requires post-processing steps, which is time-consuming and may not achieve the final object detection performance. In this work, we develop a deep learning-based holographic classification method, which computes directly on the raw holographic data to extract quantitative information of the microplastic pollutants so as to classify them according to the extent of the pollution. We further show that our method can generalize to the classification task of other micro-objects through cross-dataset validation. Without bulky optical devices, our system can be further developed into a portable microplastics detection system, with wide applicability in the monitoring of microplastic particle pollution in the ecological environment.

Global concern about microplastic (MP) and nanoplastic (NP) particles is continuously rising with their proliferation worldwide. Effective identification methods for MP and NP pollution monitoring are highly needed, but due to different requirements and technical challenges, much of the work is still in progress. Herein, the advanced optical imaging systems that are successfully applied or have the potential for MP identification are focused on. Compared with chemical and thermal analyses, optical methods have the unique advantages of being nondestructive and noncontact and allow fast detection without complex sample preprocessing. Furthermore, they are capable of revealing the morphology, anisotropy, and material characteristics of MP for their quick and robust detection. This review aims to present a comprehensive discussion of the relevant optical imaging systems, emphasizing their operating principles, strengths, and drawbacks. Multiple comparisons and analyses among these technologies are conducted in order to provide practical guidelines for researchers. In addition, the combination of optical and other alternative technologies is described and the representative portable MP detection devices are highlighted. Together, they shed light on the prospects for long‐term MP pollution monitoring and environmental protection.

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.

Volumetric reconstruction of a three-dimensional (3D) particle field with high resolution and low latency is an ambitious and valuable task. As a compact and high-throughput imaging system, digital holography (DH) encodes the 3D information of a particle volume into a two-dimensional (2D) interference pattern. In this work, we propose a one-stage network (OSNet) for 3D particle volumetric reconstruction. Specifically, by a single feed-forward process, OSNet can retrieve the 3D coordinates of the particles directly from the holograms without high-fidelity image reconstruction at each depth slice. Evaluation results from both synthetic and experimental data confirm the feasibility and robustness of our method under different particle concentrations and noise levels in terms of detection rate and position accuracy, with improved processing speed. The additional applications of 3D particle tracking are also investigated, facilitating the analysis of the dynamic displacements and motions for micro-objects or cells. It can be further extended to various types of computational imaging problems sharing similar traits.

The veiling effect caused by the scattering and absorption of suspending particles is a critical challenge of underwater imaging. It is possible to combine the image formation model (IFM) with the optical polarization characteristics underwater to effectively remove the veiling effect and recover a clear image. The performance of such methods, to a great extent, depends on the settings of the global parameters in the application scenarios. Meanwhile, learning-based methods can fit the underwater image information degradation process nonlinearly to restore the images from scattering. Here, we propose for the first time a method for full scene underwater imaging that synergistically makes use of an untrained network and polarization imaging. By mounting a Stokes mask polarizer on the CMOS camera, we can simultaneously obtain images with different polarization states for IFM calculation and optimize the imaging automatically by an untrained network without requiring extra training data. This method makes full use of the nonlinear fitting ability of a neural network and corrects the undesirable imaging effect caused by imperfect parameter settings of the classical IFM in different scenes . It shows good performance in removing the impact of water scattering and preserving the object information, making it possible to achieve clear full scene underwater imaging.