Existing applications of deep learning in computational imaging and microscopy mostly depend on supervised learning, requiring large-scale, diverse and labelled training data. The acquisition and preparation of such training image datasets is often laborious and costly, leading to limited generalization to new sample types. Here we report a self-supervised learning model, termed GedankenNet, that eliminates the need for labelled or experimental training data, and demonstrate its effectiveness and superior generalization on hologram reconstruction tasks. Without prior knowledge about the sample types, the self-supervised learning model was trained using a physics-consistency loss and artificial random images synthetically generated without any experiments or resemblance to real-world samples. After its self-supervised training, GedankenNet successfully generalized to experimental holograms of unseen biological samples, reconstructing the phase and amplitude images of different types of object using experimentally acquired holograms. Without access to experimental data, knowledge of real samples or their spatial features, GedankenNet achieved complex-valued image reconstructions consistent with the wave equation in free space. The GedankenNet framework also shows resilience to random, unknown perturbations in the physical forward model, including changes in the hologram distances, pixel size and illumination wavelength. This self-supervised learning of image reconstruction creates new opportunities for solving inverse problemsmore »
Imaging through diffusers presents a challenging problem with various digital image reconstruction solutions demonstrated to date using computers. Here, we present a computer-free, all-optical image reconstruction method to see through random diffusers at the speed of light. Using deep learning, a set of transmissive diffractive surfaces are trained to all-optically reconstruct images of arbitrary objects that are completely covered by unknown, random phase diffusers. After the training stage, which is a one-time effort, the resulting diffractive surfaces are fabricated and form a passive optical network that is physically positioned between the unknown object and the image plane to all-optically reconstruct the object pattern through an unknown, new phase diffuser. We experimentally demonstrated this concept using coherent THz illumination and all-optically reconstructed objects distorted by unknown, random diffusers, never used during training. Unlike digital methods, all-optical diffractive reconstructions do not require power except for the illumination light. This diffractive solution to see through diffusers can be extended to other wavelengths, and might fuel various applications in biomedical imaging, astronomy, atmospheric sciences, oceanography, security, robotics, autonomous vehicles, among many others.
- Award ID(s):
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- Springer Science + Business Media
- Sponsoring Org:
- National Science Foundation
More Like this
Photonics provides a promising approach for image processing by spatial filtering, with the advantage of faster speeds and lower power consumption compared to electronic digital solutions. However, traditional optical spatial filters suffer from bulky form factors that limit their portability. Here we present a new approach based on pixel arrays of plasmonic directional image sensors, designed to selectively detect light incident along a small, geometrically tunable set of directions. The resulting imaging systems can function as optical spatial filters without any external filtering elements, leading to extreme size miniaturization. Furthermore, they offer the distinct capability to perform multiple filtering operations at the same time, through the use of sensor arrays partitioned into blocks of adjacent pixels with different angular responses. To establish the image processing capabilities of these devices, we present a rigorous theoretical model of their filter transfer function under both coherent and incoherent illumination. Next, we use the measured angle-resolved responsivity of prototype devices to demonstrate two examples of relevant functionalities: (1) the visualization of otherwise invisible phase objects and (2) spatial differentiation with incoherent light. These results are significant for a multitude of imaging applications ranging from microscopy in biomedicine to object recognition for computer vision.
Drilling and milling operations are material removal processes involved in everyday conventional productions, especially in the high-speed metal cutting industry. The monitoring of tool information (wear, dynamic behavior, deformation, etc.) is essential to guarantee the success of product fabrication. Many methods have been applied to monitor the cutting tools from the information of cutting force, spindle motor current, vibration, as well as sound acoustic emission. However, those methods are indirect and sensitive to environmental noises. Here, the in-process imaging technique that can capture the cutting tool information while cutting the metal was studied. As machinists judge whether a tool is worn-out by the naked eye, utilizing the vision system can directly present the performance of the machine tools. We proposed a phase shifted strobo-stereoscopic method (Figure 1) for three-dimensional (3D) imaging. The stroboscopic instrument is usually applied for the measurement of fast-moving objects. The operation principle is as follows: when synchronizing the frequency of the light source illumination and the motion of object, the object appears to be stationary. The motion frequency of the target is transferring from the count information of the encoder signals from the working rotary spindle. If small differences are added to the frequency, the objectmore »
Water quality is undergoing significant deterioration due to bacteria, pollutants and other harmful particles, damaging aquatic life and lowering the quality of drinking water. It is, therefore, important to be able to rapidly and accurately measure water quality in a cost-effective manner using e.g., a turbidimeter. Turbidimeters typically use different illumination angles to measure the scattering and transmittance of light through a sample and translate these readings into a measurement based on the standard nephelometric turbidity unit (NTU). Traditional turbidimeters have high sensitivity and specificity, but they are not field-portable and require electricity to operate in field settings. Here we present a field-portable and cost effective turbidimeter that is based on a smartphone. This mobile turbidimeter contains an opto-mechanical attachment coupled to the rear camera of the smartphone, which contains two white light-emitting-diodes to illuminate the water sample, optical fibers to transmit the light collected from the sample to the camera, an external lens for image formation, and diffusers for uniform illumination of the sample. Including the smartphone, this cost-effective device weighs only ~350 g. In our mobile turbidimeter design, we combined two illumination approaches: transmittance, in which the optical fibers were placed directly below the sample cuvette at 180°more »
Diffractive achromats (DAs) promise ultra-thin and light-weight form factors for full-color computational imaging systems. However, designing DAs with the optimal optical transfer function (OTF) distribution suitable for image reconstruction algorithms has been a difficult challenge. Emerging end-to-end optimization paradigms of diffractive optics and processing algorithms have achieved impressive results, but these approaches require immense computational resources and solve non-convex inverse problems with millions of parameters. Here, we propose a learned rotational symmetric DA design using a concentric ring decomposition that reduces the computational complexity and memory requirements by one order of magnitude compared with conventional end-to-end optimization procedures, which simplifies the optimization significantly. With this approach, we realize the joint learning of a DA with an aperture size of 8 mm and an image recovery neural network, i.e., Res-Unet, in an end-to-end manner across the full visible spectrum (429–699 nm). The peak signal-to-noise ratio of the recovered images of our learned DA is 1.3 dB higher than that of DAs designed by conventional sequential approaches. This is because the learned DA exhibits higher amplitudes of the OTF at high frequencies over the full spectrum. We fabricate the learned DA using imprinting lithography. Experiments show that it resolves both fine details and color fidelity ofmore »