Light scattering control in transmission and reflection with neural networks

Turpin, Alex; Vishniakou, Ivan; Seelig, Johannes D.

doi:10.1364/oe.26.030911

Cited by 112 publications

(68 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The major benefit includes the flexibility and adaptability in solving complex problems, in which a parametric model is hard to derive and/or prone to errors. Closely related to our work are the learning-based techniques for imaging/focusing through diffusers [16,17,29,33,53]. Unfortunately, all existing networks are only trained and tested on the same diffuser, so the model may still be susceptible to speckle decorrelation.…”

Section: Introductionmentioning

confidence: 99%

Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media

Xue

Tian

2018

Optica

456

236

View full text Add to dashboard Cite

Imaging through scattering is an important, yet challenging problem. Tremendous progress has been made by exploiting the deterministic input-output 'transmission matrix' for a fixed medium. However, this 'one-to-one' mapping is highly susceptible to speckle decorrelations -small perturbations to the scattering medium lead to model errors and severe degradation of the imaging performance. Our goal here is to develop a new framework that is highly scalable to both medium perturbations and measurement requirement. To do so, we propose a statistical 'one-to-all' deep learning technique that encapsulates a wide range of statistical variations for the model to be resilient to speckle decorrelations. Specifically, we develop a convolutional neural network (CNN) that is able to learn the statistical information contained in the speckle intensity patterns captured on a set of diffusers having the same macroscopic parameter. We then show for the first time, to the best of our knowledge, that the trained CNN is able to generalize and make high-quality object predictions through an entirely different set of diffusers of the same class. Our work paves the way to a highly scalable deep learning approach for imaging through scattering media. diffuser

show abstract

Section: Introductionmentioning

confidence: 99%

Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media

Xue

Tian

2018

Optica

456

236

View full text Add to dashboard Cite

show abstract

“…Generally, GA is well-suited for optimization problems where the volume of optimization is enormous and there is a fairly ample time [4], [24], [25]. Therefore, it cannot always be suitable to optimize the phase of the large N input modes in the focusing dynamic target where time limit is very important [26], [27].…”

Section: Appling New Genetic Algorithm (Nga) To Phase Mask Optimizationmentioning

confidence: 99%

Genetic algorithm for feedback-based wavefront shaping in optical imaging

Varnosfaderani

Mozaffarzadeh

Pramanik

2019

Photons Plus Ultrasound: Imaging and Sensing 2019

View full text Add to dashboard Cite

Traditional optical devices rely on light propagation along a straight path. However, when the light propagates through a blurred medium, its direction get scattered by microscopic particles. This inhomogeneous distortion results in a diffused focus point. Light scattering is one of the main limitations for the optical imaging. This limitation decreases the resolution in depth. Therefore, the ability of focusing light at a desired position has a huge worthwhile for applications of optical imaging. Over the past few years, it was shown that light can be focused inside an object even with strong scattering particles, just by shaping the wavefront of the incident beam. The most successful approaches for light focusing at the presence of scattering objects are feedback-based optical wavefront shaping. In this paper, an iterative feedback-based wavefront shaping is proposed. It uses the genetic algorithm. In summary, we aim to obtain a high intensity in the focus point with fewer steps in iteration while increase the signal-to-noise. The simulations results show that both the above mentioned goals are achieved using the proposed method.

show abstract

“…This is an inverse problem, because it may be easy to deduce the consequence of a particular choice of parameters, but difficult to determine which choice will lead to the desired image. There exist already some limited examples that show, for example, how to train a CNN to focus light deep within turbid media 81 . Yet, the true challenge going forward will be to optimise multi-step imaging strategies: the microscope will observe, make moves that change imaging parameters, and thus play a game with the ultimate goal of gaining the most information about the sample (see Fig.2i).…”

Section: Box 3 Deep Learning As Differential Learningmentioning

confidence: 99%

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Belthangady

Royer

2018

Preprint

View full text Add to dashboard Cite

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

show abstract

Light scattering control in transmission and reflection with neural networks

Cited by 112 publications

References 84 publications

Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media

Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media

Genetic algorithm for feedback-based wavefront shaping in optical imaging

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Contact Info

Product

Resources

About