- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Deep learning in imaging
摘要： Machine learning approaches that include deep learning are moving beyond image classification to change the way images are made. Computers are powerful tools for carrying out tasks such as image classification or identification as well as or better than human experts. Conventional machine learning approaches are widely used for segmentation and phenotyping in fluorescence microscopy. These tools are now being largely outperformed by their deep-learning-based counterparts, some of which are available as user-friendly tools. But a perhaps more astonishing wave of developments has recently come about through the use of deep learning not for image analysis but for image transformation. In these cases, deep convolutional networks are trained to transform one type of image into another. For example, two studies have shown the power of deep learning for the creation of fluorescence micrographs of cells directly from bright-field or phase images, to facilitate multiplexed and longitudinal imaging. Researchers have also used deep learning to go from low signal-to-noise images to high-quality images, which opens the door to extended imaging of even very light-sensitive living organisms. Deep learning can similarly overcome obstacles associated with super-resolution microscopy. Two approaches, ANNA-PALM and DeepSTORM, were developed to improve the speed of localization microscopy, which is one of the major hurdles of the technique. Deep learning can also enable cross-modality imaging, where applications such as a shift from confocal images to stimulated-emission-depletion-microscopy-resolution images could democratize super-resolution imaging. As with any method, the caveats associated with deep learning in such applications, such as the potential for artifacts, must be carefully considered and analyzed. Nevertheless, we think we have seen only the tip of the iceberg, and that deep learning stands to improve all aspects of imaging, from acquisition to analysis.
关键词： image transformation,machine learning,fluorescence microscopy,deep learning,super-resolution microscopy,imaging
更新于2025-09-04 15:30:14
-
[IEEE 2018 3rd International Conference for Convergence in Technology (I2CT) - Pune (2018.4.6-2018.4.8)] 2018 3rd International Conference for Convergence in Technology (I2CT) - Towards Designing an Adaptive Framework for Facial Image Quality Estimation at Edge
摘要： This paper proposes a framework for facial image quality estimation in order to address the limitation of real-time applicability of facial recognition. This framework determines whether an image is suitable for facial recognition. We ?rst exploit machine learning algorithms to map the relationship between image quality features and performance of facial recog- nition. We extract a variety of features (like focus measure, brightness, obscured face) and study their in?uence on the accuracy of face recognition. After examining the results of this approach, we then used deep learning to build a binary classi?er which accepts or rejects images before sending them for actual facial recognition. This decision is taken based on the probability of the facial recognition framework correctly matching a face from the image. We used images from the Chokepoint dataset, and OpenFace- an open source facial recognition software, for building our framework.
关键词： Classi?cation,Deep Learning,Edge Computing,Convolutional Neural Networks,Machine Learning
更新于2025-09-04 15:30:14
-
[IEEE 2018 20th International Conference on Transparent Optical Networks (ICTON) - Bucharest (2018.7.1-2018.7.5)] 2018 20th International Conference on Transparent Optical Networks (ICTON) - Elastic Networks Thematic Network Results I: Planning and Control of Flex-Grid/SDM
摘要： This paper overviews the approach of the Elastic Networks research network to address different issues of planning and control of Flex-Grid/SDM optical networks. Firstly, we present the Net2Plan open-source planning tool capabilities to model Flex-Grid/SDM networks; secondly a PCE-based Transport-SDN controller for packet over flex-grid optical networks is described. Finally results on machine-learning-based QoT classification techniques useful in planning and control tasks are reported.
关键词： space division multiplexing,elastic optical networks,network planning,control,machine-learning
更新于2025-09-04 15:30:14
-
An Open-Source Artificial Neural Network Model for Polarization-Insensitive Silicon-on-Insulator Subwavelength Grating Couplers
摘要： We present an open-source deep artificial neural network (ANN) model for the accelerated design of polarization-insensitive subwavelength grating (SWG) couplers on the silicon-on-insulator platform. Our model can optimize SWG-based grating couplers for a single fundamental-order polarization, or both, by splitting them counter-directionally at the grating level. Alternating SWG sections are adopted to reduce the reflections (loss) of standard, single-etch devices—further accelerating the design time by eliminating the need to process a second etch. The model of this device is trained by a dense uniform dataset of finite-difference time-domain (FDTD) optical simulations. Our approach requires the FDTD simulations to be made up front, where the resulting ANN model is made openly available for the rapid, software-free design of future standard photonic devices, which may require slightly different design parameters (e.g., fiber angle, center wavelength, polarization) for their specific application. By transforming the nonlinear input–output relationship of the device into a matrix of learned weights, a set of simple linear algebraic and nonlinear activation calculations can be made to predict the device outputs 1,830 times faster than numerical simulations, within 93.2% accuracy of the simulations.
关键词： subwavelength devices,machine learning,Silicon photonics,polarization insensitivity,grating couplers,artificial neural networks
更新于2025-09-04 15:30:14
-
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
摘要： We describe here a protocol for the label-free identification of lymphocyte subtypes using quantitative phase imaging and machine learning. Identification of lymphocyte subtypes is important for the study of immunology as well as diagnosis and treatment of various diseases. Currently, standard methods for classifying lymphocyte types rely on labeling specific membrane proteins via antigen-antibody reactions. However, these labeling techniques carry the potential risks of altering cellular functions. The protocol described here overcomes these challenges by exploiting intrinsic optical contrasts measured by 3D quantitative phase imaging and a machine learning algorithm. Measurement of 3D refractive index (RI) tomograms of lymphocytes provides quantitative information about 3D morphology and phenotypes of individual cells. The biophysical parameters extracted from the measured 3D RI tomograms are then quantitatively analyzed with a machine learning algorithm, enabling label-free identification of lymphocyte types at a single-cell level. We measure the 3D RI tomograms of B, CD4+ T, and CD8+ T lymphocytes and identified their cell types with over 80% accuracy. In this protocol, we describe the detailed steps for lymphocyte isolation, 3D quantitative phase imaging, and machine learning for identifying lymphocyte types.
关键词： lymphocyte identification,machine learning,holotomography,immune cell,immunology,Immunology and Infection,Quantitative phase imaging,optical diffraction tomography,holographic microscopy,label-free imaging
更新于2025-09-04 15:30:14
-
A generalized shapelet-based method for analysis of nanostructured surface imaging
摘要： The determination of quantitative structure-property relations is a vital but challenging task for nanostructured materials research due to the presence of large-scale spatially varying patterns resulting from nanoscale processes such as self-assembly and nano-lithography. Focusing on nanostructured surfaces, recent advances have been made in automated quanti?cation methods for orientational and translational order using shapelet functions, originally developed for analysis of images of galaxies, as a reduced-basis for surface pattern structure. In this work, a method combining shapelet functions and machine learning is developed and applied to a representative set of images of self-assembled surfaces from experimental characterization techniques including scanning electron miscroscopy, atomic force microscopy and transmission electron microscopy. The method is shown to be computationally ef?cient and able to quantify salient pattern features including deformation, defects, and grain boundaries from a broad range of patterns typical of self-assembly processes.
关键词： machine learning,self-assembly,nanostructure,image processing,surfaces,shapelets
更新于2025-09-04 15:30:14
-
Rapid tracking of extrinsic projector parameters in fringe projection using machine learning
摘要： In this work, we propose to enable the angular re-orientation of a projector within a fringe projection system in real-time without the need for re-calibrating the system. The estimation of the extrinsic orientation parameters of the projector is performed using a convolutional neural network and images acquired from the camera in the setup. The convolutional neural network was trained to classify the azimuth and elevation angles of the projector approximated by a point source through shadow images of the measured object. The images used to train the neural network were generated through the use of CAD rendering, by simulating the illumination of the object model from di?erent directions and then rendering an image of its shadow. The accuracy to which the azimuth and elevation angles are estimated is within 1 classi?cation bin, where 1 bin is designated as a ± 10° patch of the illumination dome. To evaluate use of the proposed system in fringe projection, a pyramidal additively manufactured object was measured. The point clouds generated using the proposed method were compared to those obtained by an established fringe projection calibration method. The maximum dimensional error in the point cloud generated when using the convolutional network as compared to the established calibration method for the object measured was found to be 1.05 mm on average.
关键词： real-time tracking,convolutional neural network,fringe projection,machine learning,projector calibration
更新于2025-09-04 15:30:14
-
A Hierarchical Multi-Classifier System for Automated Analysis of Delayered IC Images
摘要： A robust and accurate machine learning based hierarchical multi-classifier system is proposed to automate the retrieval of interconnection information from delayered Integrated Circuits (IC) images. The proposed system replaces labor-intensive manual annotation process and provides an effective approach for automated analysis of state-of-the-art deep sub-micron IC chips.
关键词： machine learning,delayered IC images,hierarchical multi-classifier system,automated analysis
更新于2025-09-04 15:30:14
-
Feature-based Classification of Protein Networks using Confocal Microscopy Imaging and Machine Learning
摘要： Fluorescence imaging has become a powerful tool to investigate complex subcellular structures such as cytoskeletal filaments. Advanced microscopes generate 3D imaging data at high resolution, yet tools for quantification of the complex geometrical patterns are largely missing. Here we present a computational framework to classify protein network structures. We developed a machine-learning method that combines state-of-the-art morphological quantification with protein network classification through morphologically distinct structural features enabling live imaging–based screening. We demonstrate applicability in a confocal laser scanning microscopy (CLSM) study differentiating protein networks of the FtsZ (filamentous temperature sensitive Z) family inside plant organelles (Physcomitrella patens).
关键词： FtsZ,machine learning,classification,protein networks,confocal microscopy
更新于2025-09-04 15:30:14
-
Enhancement of Localization Systems in NLOS Urban Scenario with Multipath Ray Tracing Fingerprints and Machine Learning
摘要： A hybrid technique is proposed to enhance the localization performance of a time difference of arrival (TDOA) deployed in non-line-of-sight (NLOS) suburban scenario. The idea was to use Machine Learning framework on the dataset, produced by the ray tracing simulation, and the Channel Impulse Response estimation from the real signal received by each sensor. Conventional localization techniques mitigate errors trying to avoid NLOS measurements in processing emitter position, while the proposed method uses the multipath fingerprint information produced by ray tracing (RT) simulation together with calibration emitters to refine a Machine Learning engine, which gives an extra layer of information to improve the emitter position estimation. The ray-tracing fingerprints perform the target localization embedding all the reflection and diffraction in the propagation scenario. A validation campaign was performed and showed the feasibility of the proposed method, provided that the buildings can be appropriately included in the scenario description.
关键词： time difference of arrival localization,machine learning,cooperative positioning,multipath exploitation,hybrid positioning,ray tracing fingerprints,wireless positioning
更新于2025-09-04 15:30:14