检索结果-内蒙古大学图书馆

Elimination of stripe artifacts in light sheet fluorescence microscopy using an attention-based residual neural network

引用

BIOMEDICAL OPTICS EXPRESS 2022年第3期13卷 1292-1311页

作者： Wei, Zechen Wu, Xiangjun Tong, Wei Zhang, Suhui Yang, Xin Tian, Jie Hui, Hui CAS Key Lab Mol Imaging Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Key Lab Mol Imaging Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China Beihang Univ Sch Med & Engn Beijing Adv Innovat Ctr Big Data Based Precis Med Beijing 100083 Peoples R China Peoples Liberat Army Gen Hosp Med Ctr 6 Dept Cardiol Beijing 100853 Peoples R China Jinan Univ Zhuhai Peoples Hosp Zhuhai Precis Med Ctr Jinan 519000 Zhuhai Peoples R China

Stripe artifacts can deteriorate the quality of light sheet fluorescence microscopy (LSFM) images. Owing to the inhomogeneous, high-absorption, or scattering objects located in the excitation light path, stripe artifacts are generated in LSFM images in various directions and types, such as horizontal, anisotropic, or multidirectional anisotropic. These artifacts severely degrade the quality of LSFM images. To address this issue, we proposed a new deep-learning based approach for the elimination of stripe artifacts. This method utilizes an encoder-decoder structure of UNet integrated with residual blocks and attention modules between successive convolutional layers. Our attention module was implemented in the residual blocks to learn useful features and suppress the residual features. The proposed network was trained and validated by generating three different degradation datasets with different types of stripe artifacts in LSFM images. Our method can effectively remove different stripes in generated and actual LSFM images distorted by stripe artifacts. Besides, quantitative analysis and extensive comparison results demonstrated that our method performs the best compared with classical image-based processing algorithms and other powerful deep-learning-based destriping methods for all three generated datasets. Thus, our method has tremendous application prospects to LSFM, and its use can be easily extended to images reconstructed by other modalities affected by the presence of stripe artifacts. (c) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Acoustooptical deflectors Fast Fourier transforms image processing algorithms image quality Neural networks Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

PCIe-based FPGA- GPU heterogeneous computation for real-time multi-emitter fitting in super-resolution localization microscopy

引用

BIOMEDICAL OPTICS EXPRESS 2022年第6期13卷 3401-3415页

作者： Gui, Dan Chen, Yunjiu Kuang, Weibing Shang, Mingtao Zhang, Yingjun Huang, Zhen-li Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Britton Chance Ctr Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect MoE Key Lab Biomed Photon Sch Engn Sci Wuhan 430074 Peoples R China Wuhan Vocat Coll Software & Engn Sch Elect Engn Wuhan 430205 Peoples R China Hainan Univ Sch Biomed Engn Key Lab Biomed Engn Hainan Prov Haikou 570228 Hainan Peoples R China

Real-time multi-emitter fitting is a key technology for advancing super-resolution localization microscopy (SRLM), especially when it is necessary to achieve dynamic imaging quality control and/or optimization of experimental conditions. However, with the increase of activation densities, the requirements in the computing resources would increase rapidly due to the complexity of the fitting algorithms, making it difficult to realize real-time multi-emitter fitting for emitter density more than 0.6 mol/mu m(2) in large field of view (FOV), even after acceleration with the popular Graphics processing Unit (GPU) computation. Here we adopt the task parallelism strategy in computer science to construct a Peripheral Component Interconnect Express (PCIe) based all-in-one heterogeneous computing platform (AIO-HCP), where the data between two major parallel computing hardware, Field Programmable Gate Array (FPGA) and GPU, are interacted directly and executed simultaneously. Using simulated and experimental data, we verify that AIO-HCP could achieve a data throughput of up to similar to 1.561 GB/s between FPGA and GPU. With this new platform, we develop a multi-emitter fitting method, called AIO-STORM, under big data stream parallel scheduling. We show that AIO-STORM is capable of providing real-time image processing on raw images with 100 mu mx 100 mu m FOV, 10 ms exposure time and 5.5 mol/mu m(2) structure density, without scarifying image quality. This study overcomes the data throughput limitation of heterogeneous devices, demonstrates the power of the PCIe-based heterogeneous computation platform, and offers opportunities for multi-scale stitching of super-resolution images. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Capacity limits image display image processing image processing algorithms image quality Point spread function

来源：评论

学校读者我要写书评

暂无评论

Method for the generation and visualization of cross-sectional images of three-dimensional point spread functions for rotationally symmetric intraocular lenses

引用

BIOMEDICAL OPTICS EXPRESS 2022年第2期13卷 1087-1101页

作者： Sievers, Jan Elsner, Ricardo Bohn, Sebastian Schuenemann, Melanie Stolz, Heinrich Guthoff, Rudolf F. Stachs, Oliver Sperlich, Karsten Rostock Univ Dept Ophthalmol Med Ctr D-18057 Rostock Germany Univ Rostock Dept Life Light & Matter D-18055 Rostock Germany Martin Luther Univ Halle Wittenberg Inst Phys D-06120 Halle Germany Univ Rostock Inst Phys D-18055 Rostock Germany

Cross-sectional images of three-dimensional point spread functions of intraocular lenses are used to study their image formation. To obtain those, light sheet-based methods are established. Due to the non-negligible thicknesses of the light sheets, the image quality of the cross-sectional images is constrained. To overcome this hurdle, we present a dedicated evaluation algorithm to increase image quality in the post-processing step. Additionally, we compare the developed-with the light sheet method based on our own investigations of a multifocal diffractive intraocular lens conducted in an in-house designed optical bench. The comparative study showed the clear superiority of the newly developed method in terms of image quality, fine structure visibility, and signal-to-noise ratio compared to the light sheet based method. However, since the algorithm assumes a rotationally symmetrical point spread function, it is only suitable for all rotationally symmetrical lenses.

关键词： Diffractive lenses image processing algorithms image quality Modulation transfer function Point spread function Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

LuckyProfiler: an imageJ plug-in capable of quantifying FWHM resolution easily and effectively for super-resolution images

引用

BIOMEDICAL OPTICS EXPRESS 2022年第8期13卷 4310-4325页

作者： Li, Mengting Song, Qihang Xiao, Yinghao Wu, Junnan Kuang, Weibing Zhang, Yingjun Huang, Zhen-Li Huazhong Univ Sci & Technol Britton Chance Ctr Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Engn Sci Wuhan Natl Lab Optoelect MoE Key Lab Biomed Photon Wuhan 430074 Peoples R China Hainan Univ Sch Biomed Engn Key Lab Biomed Engn Hainan Prov Haikou 570228 Hainan Peoples R China

Quantifying the resolution of a super-resolution image is vital for biologists trying to apply super-resolution microscopy in various research fields. Among the reported image resolution estimation methods, the one that calculates the full width at half maximum (FWHM) of line profile, called FWHM resolution, continues the traditional resolution criteria and has been popularly used by many researchers. However, quantifying the FWHM resolution of a super-resolution image is a time-consuming, labor-intensive, and error-prone process because this method typically involves a manual and careful selection of one or several of the smallest structures. In this paper, we investigate the influencing factors in FWHM resolution quantification systematically and present an imageJ plug-in called LuckyProfiler for biologists so that they can have an easy and effective way of quantifying the FWHM resolution of super-resolution images. (c) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image processing image processing algorithms image reconstruction image resolution Light wavelength Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Design and demonstration of a six-channel multiresolution imaging system

引用

APPLIED OPTICS 2022年第10期61卷 2683-2689页

作者： Belay, Gebirie Yizengaw Bollhorst, Rolf Vervaeke, Michael Thienpont, Hugo Van Erps, Juergen Vrije Univ Brussel & Flanders Make Fac Engn Dept Appl Phys & Photon TONA Brussels Photon B PHOT Pleinlaan 2 B-1050 Brussels Belgium Imaging Source Europe GmbH Uberseetor 18 D-28217 Bremen Germany

Multichannel imaging systems consist of multiple channels that have different imaging characteristics (fields-of-view and angular resolutions). We design and demonstrate a six-channel multiresolution imaging system that can achieve a relative magnification ratio of up to 10 times between the channels and, at the same time, result in different depths-of-field. The imaging system consists of two double-sided lens arrays made of PMMA material, a baffle to eliminate possible cross talk between neighboring channels, and a Sony full-frame image sensor. The imaging system was tested by capturing images of stationary and moving objects. The acquired images exhibit different resolutions, fields-of-view, and levels of blur proving our concept. (C) 2022 Optica Publishing Group

关键词： image processing algorithms image quality Imaging systems Lens arrays Medical imaging Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

Hilbert phase microscopy based on pseudo thermal illumination in the Linnik configuration

引用

OPTICS LETTERS 2022年第22期47卷 5793-5796页

作者： Rogalski, Mikolaj Cywinska, Maria Ahmad, Azeem Patorski, Krzysztof Mico, Vicente Ahluwalia, Balpreet S. Trusiak, Maciej Warsaw Univ Technol Inst Micromech & Photon 8 Sw A Boboli St PL-02525 Warsaw Poland UiT Arctic Univ Norway Dept Phys & Technol NO-9037 Tromso Norway Univ Valencia Dept Opt & Optometria & Ciencias Vis C Doctor Moliner 50 E-46100 Burjassot Spain

Quantitative phase microscopy (QPM) is often based on recording an object-reference interference pattern and its further phase demodulation. We propose pseudo Hilbert phase microscopy (PHPM) where we combine pseudo ther-mal light source illumination and Hilbert spiral transform (HST) phase demodulation to achieve hybrid hardware -software-driven noise robustness and an increase in reso-lution of single-shot coherent QPM. Those advantageous features stem from physically altering the laser spatial coherence and numerically restoring spectrally overlapped object spatial frequencies. The capabilities of PHPM are demonstrated by analyzing calibrated phase targets and live HeLa cells in comparison with laser illumination and phase demodulation via temporal phase shifting (TPS) and Fourier transform (FT) techniques. The performed studies verified the unique ability of PHPM to combine single-shot imag-ing, noise minimization, and preservation of phase details.(c) 2022 Optica Publishing Group

关键词： Fourier transforms High numerical aperture optics image processing algorithms Phase retrieval Phase shift Spatial frequency

来源：评论

学校读者我要写书评

暂无评论

Multimodal visual image processing of mobile robot in unstructured environment based on semi-supervised multimodal deep network

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2020年第12期11卷 6349-6359页

作者： Li, Yajia Hohhot Vocat Coll Dept Comp Informat Hohhot 010051 Mongolia Peoples R China

With the continuous development of computer technology, machine vision and image processing algorithms, people's research on mobile robots with vision systems is becoming deeper and deeper. This paper studies the related problems of visual image processing of mobile robots in outdoor unstructured environments. In this work, we propose a new approach that integrates heterogeneous features through a well-designed Semi-supervised multimodal deep network (SMMDN). For each modality, there is a multi-layer sub-neural network with a separate structure corresponding to it, which is used to transform features in different modes into the same modal features. At the same time, through a network layer common to all modes above these sub-neural networks, a connection is established between these different modes, and finally a plurality of heterogeneous modes is converted into the same mode and a plurality of them are extracted from fusion characteristics of data modalities. The simulation results prove that SMMDN improves the perception and recognition ability of mobile robots for outdoor complex environments.

关键词： Mobile robots image processing algorithms Deep learning Multimodal deep network Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Spatially polarization-modulated ellipsometry based on the vectorial optical field and image processing

引用

APPLIED OPTICS 2020年第18期59卷 5377-5384页

作者： Gao, Chao Lei, Bing Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha 410073 Peoples R China

We report a new (to the best of our knowledge) ellipsometric measurement scheme called spatially polarization-modulated ellipsometry (SPME), which is based on the vectorial optical field and digital image processing. A zero-order vortex half-wave retarder (ZVHR) is employed to generate the vectorial optical field and analyze the elliptically polarized light reflected by a thin film;further, an analyzer is set after the ZVHR to form an hourglass intensity pattern due to the spatially polarization modulation;then, the film's ellipsometric angles can be obtained by processing the hourglass intensity image. By analyzing the working principle of SPME, we have found that the film's ellipsometric angles are determined by the bright areas' azimuth angle and contrast of the modulated images, and their mathematical relationships have been deduced and provided. To reduce the adverse effects of image noise and improve the measurement precision, an improved operation mode of SPME is presented by processing the modulated images with their bright areas' azimuth locating at near 45 degrees or 135 degrees and 0 degrees or 90 degrees. Numerical analyzing studies have been carried out on the SiO2 films to validate the feasibility of SPME, and the simulation experiments indicate that the SPME can operate well, even though obvious noise has been added to the modulated intensity image and the measuring error of film thickness and refractive index were less than 0.1 nm and 0.001, respectively. (C) 2020 Optical Society of America

关键词： Digital image processing image metrics image processing image processing algorithms Optical components Thin film optical properties

来源：评论

学校读者我要写书评

暂无评论

Automatic detection method for BGA defects based on x-ray imaging

引用

APPLIED OPTICS 2022年第21期61卷 6356-6365页

作者： Xiao, Kai Li, Qin Chen, Yang Natl Univ Def Technol Coll Comp Sci & Technol State Key Lab High Performance Comp Changsha 410073 Peoples R China Natl Key Lab Sci & Technol Blind Signal Proc Chengdu 610000 Peoples R China

Ball grid array (BGA) packaging is a high-density surface mount technology with the advantages of small size, good heat dissipation, and electrical properties, and is widely applied in the production of large-scale integrated circuits. With the rapid development of IC integration, devices assembled using BGA technology generally have greater complexity. However, BGA defects can seriously affect device performance and bring difficulties to product quality inspection. More importantly, in the process of BGA defect inspection, the high complexity of the device brings unprecedented challenges to the precise location of defects, which means that corresponding inspection methods should be improved. To this end, this paper proposes an automatic detection method for BGA defects based on x-ray imaging. First, x-ray imaging technology is utilized to achieve non-destructive detection of the BGA area inside the device and generate image data. On this basis, a set of algorithms including threshold separation, detection filling, and closing operation is designed to complete automatic detection of BGA defects. Furthermore, to objectively evaluate the effectiveness and performance of the proposed method, we conduct a series of comparative experiments using simulated and real data, and generate visual outputs. Through these experiments and analyses, we confirm that the proposed method plays an active and effective role and has robust performance in BCA defect detection. In particular, our method shows the expected performance in precisely finding BGA edge defects and subtle defects. (C) 2022 Optica Publishing Group

关键词： Attenuation coefficient Computed tomography Edge detection image processing image processing algorithms X ray imaging

来源：评论

学校读者我要写书评

暂无评论

Depth from axial differential perspective

引用

OPTICS CONTINUUM 2022年第1期1卷 103-112页

作者： Faulhaber, Andreas Kraechan, Clara Haist, Tobias Univ Stuttgart Inst Appl Opt ITO Pfaffenwaldring 9 D-70569 Stuttgart Germany

We introduce an imaging-based passive on-axis technique for measuring the distance of individual objects in complex scenes. Two axially separated pupil positions acquire images (can be realized simultaneously or sequentially). Based on the difference in magnification for objects within the images, the distance to the objects can be inferred. The method avoids some of the disadvantages of passive triangulation sensors (e.g., correspondence, shadowing), is easy to implement and offers high lateral resolution. Due to the principle of operation it is especially suited for applications requiring only low to medium axial resolution. Theoretical findings, as well as follow-up experimental measurements, show obtainable resolutions in the range of few centimeters for distances of up to several meters.

关键词： image processing image processing algorithms Imaging systems Optical flow Plenoptic imaging Structured illumination microscopy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：