检索结果-内蒙古大学图书馆

Demonstration of shift, scale, and rotation invariant target recognition using the hybrid opto-electronic correlator

引用

OPTICS EXPRESS 2019年第12期27卷 16507-16520页

作者： Gamboa, Julian Fouda, Mohamed Shahriar, Selim M. Northwestern Univ Dept EECS Evanston IL 60208 USA Northwestern Univ Dept Phys & Astron Evanston IL 60208 USA

Previously, we had proposed a hybrid opto-electronic correlator (HOC), which can achieve the same functionality as that of a holographic optical correlator but without using any holographic medium. Here, we demonstrate experimentally that the HOC is capable of detecting objects in a scale, rotation, and shift invariant manner. First, the polar Mellin transformed (PMT) versions of two images are produced, using a combination of optical and electronic signal processing. The PMT images are then used as the reference and the query inputs for the HOC. The observed correlation signal is used to infer, with high accuracy, the relative scale and angular orientation of the original images. We also discuss practical constraints in reaching a high-speed implementation of such a system. In addition, we describe how these challenges may be overcome for producing an automated version of such a correlator. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Application specific integrated circuits Diode pumped lasers image processing image recognition algorithms Joint transform correlators Optical components

来源：评论

学校读者我要写书评

暂无评论

3-D face registration solution with speckle encoding based spatial-temporal logical correlation algorithm

引用

OPTICS EXPRESS 2019年第15期27卷 21004-21019页

作者： Zhou, Pei Zhu, Jiangping You, Zhisheng Sichuan Univ Sch Aeronaut & Astronaut Chengdu 610065 Sichuan Peoples R China Sichuan Univ Natl Key Lab Fundamental Sci Synthet Vis Chengdu 610065 Sichuan Peoples R China

3-D information acquisition (registration) of whole face plays a significant role in 3-D human face recognition application. In this paper, we develop a prototype of 3-D system consisting of two binocular measurement units that allows a full 3-D reconstruction by utilizing the advantages of a novel correlation algorithm. In this system, we use optical modulation to produce temporally and spatially varying high-density binary speckle patterns to encode the tested face, then propose a spatial-temporal logical correlation (STLC) stereo matching algorithm to fast determine the accurate disparity with a coarse and refined strategy. Finally the 3-D information of whole face from left- and right ear (similar to 180 degrees) can be obtainable by fusing the data from two measurement units. Comparative researches are performed to test a plastic model and a real human face by simulating real application situations. The results verify the feasibility and good performances of our computational frameworks and experimental configuration in terms of accuracy and time cost, which show a good application prospect in our future 3-D human face recognition research. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement1.

关键词： High power lasers image processing image recognition algorithms Speckle patterns Stereo matching Time division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Optofluidic refractive index sensor based on asymmetric diffraction

引用

OPTICS EXPRESS 2019年第13期27卷 17809-17818页

作者： Tu, Xin Luo, Yingdong Huang, Tianye Gan, Jinqiang Song, Chaolong China Univ Geosci Sch Mech Engn & Elect Informat Wuhan 430074 Hubei Peoples R China

A novel optofluidic refracrtive index (RI) sensor was proposed based on asymmetric Fraunhofer diffraction. In-plane optofluidic lens, light source, slit, diffraction pattern visualization zone and optical path were integrated into the microfluidic networks to avoid the manual alignment of the optical components as well as to reduce the cost of external bulky components. Unlike the conventional RI sensor, this device visualizes the bulk refractive index change of the liquid through a diffraction image, which is readily read-out for clinical diagnosis right at the point-of-care or on-site security check. In the experiment, the device can measure a RI change of as low as similar to 10(-5) RIU. A low noise-equivalent detection limit (NEDL) of similar to 10(-6) refractive index unit (RIU) and high sensitivity of similar to 1.1 x 10(4)/RIU were achieved. The new device is practical and suitable to be extended for high throughput applications by simultaneously reading multiple chips with an 2D-array image sensor. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Far field diffraction Finite element method image recognition algorithms Ptychography Stray light Surface plasmon resonance

来源：评论

学校读者我要写书评

暂无评论

Remote Control of a Robot Rover Combining 5G, AI, and GPU image Processing at the Edge

Remote Control of a Robot Rover Combining 5G, AI, and GPU Im...

引用

Optical Fiber Communication (OFC) Conference

作者： F. Civerchia F. Giannone K. Kondepu P. Castoldi L. Valcarenghi A. Bragagnini F. Gatti A. Napolitano Justine Cris Borromeo Scuola Superiore Sant’Anna Pisa Italy Department of Excellence in Robotics & A.I. Scuola Superiore Sant’Anna Pisa Italy TIM Italy

The demo shows the effectiveness of a low latency remote control based on 5G and image processing at the edge exploiting artificial intelligence and GPUs to make a robot rover slalom between posts.

ISBN: (数字)9781943580712

ISBN: (纸本)9781728167626

The demo shows the effectiveness of a low latency remote control based on 5G and image processing at the edge exploiting artificial intelligence and GPUs to make a robot rover slalom between posts.

关键词： image processing image recognition image recognition algorithms image transmission Neural networks Object detection

来源：评论

学校读者我要写书评

暂无评论

Classification of water contamination developed by 2-D Gabor wavelet analysis and support vector machine based on fluorescence spectroscopy

引用

OPTICS EXPRESS 2019年第4期27卷 5461-5477页

作者： Huang, P. Mao, T. Yu, Q. Cao, Y. Yu, J. Zhang, G. Hou, D. Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China

The identification of the specific categories of pollutants in the urban water supply system is necessary. Traditional detection methods are based mainly on common water quality indicators. However, inspecting these water quality indicators is made difficult by issues such as long analysis time, insufficient sensitivity, need for reagents, and generation of waste liquid. These problems hinder high-frequency water detection and monitoring. In this study, three-dimensional (3D) fluorescence spectroscopy is adopted as a monitoring method for water quality. An identification method based on two-dimensional (2D) Gabor wavelets and support vector machine (SVM) multi-classification is also proposed. The Delaunay triangulation method for interpolation is used to pre-process 3D fluorescence spectra and thereby eliminate Rayleigh scattering and Raman scattering. A 2D Gabor wavelet function generated by filters of different scales and rotation angles is proposed to extract the features of the spectra. The block statistics method, based on Gabor feature description, is employed to enhance the efficiency in describing spectra features. Then, multiple SVM classifiers are used in pollutant classification and recognition. By comparing the proposed method with principal component analysis, which is a commonly used feature extraction method, this study finds that the application of 2D Gabor wavelets and block statistics can effectively describe the characteristics of 3D fluorescence spectra. Moreover, 2D Gabor wavelets achieve high classification accuracy, especially for substances with closely positioned or overlapping characteristic peaks. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： Diffuse reflectance spectroscopy Fluorescence spectroscopy image recognition algorithms Raman scattering Ultraviolet radiation Visible light

来源：评论

学校读者我要写书评

暂无评论

Hybrid sensing face detection and registration for low-light and unconstrained conditions

引用

APPLIED OPTICS 2018年第1期57卷 69-78页

作者： Zhou, Mingyuan Lin, Haiting Young, S. Susan Yu, Jingyi Univ Delaware Newark DE 19716 USA US Army Res Lab 2800 Powder Mill Rd Adelphi MD 20783 USA

The capability to track, detect, and identify human targets in highly cluttered scenes under extreme conditions, such as in complete darkness or on the battlefield, has been one of the primary tactical advantages in military operations. In this paper, we propose a new collaborative, multi-spectrum sensing method to achieve face detection and registration under low-light and unconstrained conditions. We design and prototype a novel type of hybrid sensor by combining a pair of near-infrared (NIR) cameras and a thermal camera (a long-wave infrared camera). We strategically surround each NIR sensor with a ring of LED IR flashes to capture the "red-eye," or more precisely, the "bright-eye" effect of the target. The "bright-eyes" are used to localize the 3D position of eyes and face. The recovered 3D information is further used to warp the thermal face imagery to a frontal-parallel pose so that additional tasks, such as face recognition, can be reliably conducted, especially with the assistance of accurate eye locations. Experiments on real face images are provided to demonstrate the merit of our method. (C) 2017 Optical Society of America

关键词： Computational imaging Face recognition image detection systems image recognition algorithms Infrared radiation Visible light

来源：评论

学校读者我要写书评

暂无评论

Observation of laser-induced elastic waves in agar skin phantoms using a high-speed camera and a laser-beam-deflection probe

引用

BIOMEDICAL OPTICS EXPRESS 2018年第4期9卷 1893-1905页

作者： Lalos, Jernej Gregorcic, Peter Jezersek, Matija Univ Ljubljana Fac Mech Engn Askerceva Cesta 6 Ljubljana 1000 Slovenia

We present an optical study of elastic wave propagation inside skin phantoms consisting of agar gel as induced by an Er: YAG (wavelength of 2.94 mu m) laser pulse. A laserbeam- deflection probe is used to measure ultrasonic propagation and a high-speed camera is used to record displacements in ablation-induced elastic transients. These measurements are further analyzed with a custom developed image recognition algorithm utilizing the methods of particle image velocimetry and spline interpolation to determine point trajectories, material displacement and strain during the passing of the transients. The results indicate that the ablation-induced elastic waves propagate with a velocity of 1 m/s and amplitudes of 0.1 mm. Compared to them, the measured velocities of ultrasonic waves are much higher, within the range of 1.42-1.51 km/s, while their amplitudes are three orders of magnitude smaller. This proves that the agar gel may be used as a rudimental skin and soft tissue substitute in biomedical research, since its polymeric structure reproduces adequate soft-solid properties and its transparency for visible light makes it convenient to study with optical instruments. The results presented provide an insight into the distribution of laser-induced elastic transients in soft tissue phantoms, while the experimental approach serves as a foundation for further research of laser-induced mechanical effects deeper in the tissue. (c) 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： image recognition algorithms Laser systems Laser velocimetry Optical devices Visible light Wave propagation

来源：评论

学校读者我要写书评

暂无评论

New perspectives in face correlation research: a tutorial

引用

ADVANCES IN OPTICS AND PHOTONICS 2017年第1期9卷 1-78页

作者： Wang, Q. Alfalou, A. Brosseau, C. Guangdong Univ Technol Sch Phys & Optoelect Engn Guangzhou 510006 Guangdong Peoples R China ISEN Brest Vis Lab L bISEN 20 Rue Cuirasse BretagneCS 42807 F-29228 Brest 2 France Univ Brest Lab STICC 6 Ave Le GorgeuCS 93837 F-29238 Brest 3 France

In recent years, correlation-filter (CF)-based face recognition algorithms have attracted increasing interest in the field of pattern recognition and have achieved impressive results in discrimination, efficiency, location accuracy, and robustness. In this tutorial paper, our goal is to help the reader get a broad overview of CFs in three respects: design, implementation, and application. We review typical face recognition algorithms with implications for the design of CFs. We discuss and compare the numerical and optical implementations of correlators. Some newly proposed implementation schemes and application examples are also presented to verify the feasibility and effectiveness of CFs as a powerful recognition tool. (C) 2017 Optical Society of America

关键词： Edge detection Holographic optical elements image recognition algorithms Joint transform correlators Power spectral density Synthetic discrimination functions

来源：评论

学校读者我要写书评

暂无评论

High-throughput imaging of zebrafish embryos using a linear-CCD-based flow imaging system

引用

BIOMEDICAL OPTICS EXPRESS 2017年第12期8卷 5651-5662页

作者： Liu, Lifeng Yang, Guang Liu, Shoupeng Wang, Linbo Yang, Xinbin Qu, Huiming Liu, Xiaofen Cao, Le Pan, Weijun Li, Hui Nanjing Univ Sci & Technol Sch Elect Engn & Optoelect Technol Nanjing 210094 Jiangsu Peoples R China Chinese Acad Sci Jiangsu Key Lab Med Opt CAS Ctr Excellence Mol Cell Sci Suzhou Inst Biomed Engn & Technol Suzhou 215163 Peoples R China Chinese Acad Sci Shanghai Inst Biol Sci Shanghai 200233 Peoples R China

High-throughput imaging and screening is essential for biomedical research and drag discovery using miniature model organisms such as zebrafish. This study introduces a high-speed imaging system which illuminates zebrafish embryos flowing through a capillary tube with a sheet of light and captures them using a linear charge-coupled device (CCD). This system can image dozens of zebrafish embryos per second. An image algorithm was developed to recognize each embryo and to perform automatic analysis. We distinguished dead and living embryos according to the gray level distribution and conducted statistics of morphological characteristics of embryos at different growing stages. (C) 2017 Optical Society of America

关键词： High speed imaging High speed photography image processing image recognition algorithms Imaging systems Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

Face recognition: a novel deep learning approach

引用

JOURNAL OF OPTICAL TECHNOLOGY 2015年第4期82卷 237-245页

作者： Pang, Sh. Ch. Yu, Zh. Zh. Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

We propose a novel and robust deep learning method for face recognition, which uses effective image representations learned automatically to handle big data. There are two stages of the deep learning architecture in real-time application. First, in the offline training procedure, we train a stacked denoising autoencoder to learn generic image features from 80 million images from the Tiny images Dataset used as auxiliary offline training data. Second, in the supervised object recognition procedure, we construct five layers as a feature extractor to produce an image representation and an additional classification layer, which we can use to further tune generic image features to adapt to specific object recognition by online training of the corresponding objects. Comparison with the state-of-the-art face recognition methods shows that our deep learning algorithm in face recognition is more accurate and it is a perfect processing tool for the big data problem. (C) 2015 Optical Society of America.

关键词： Edge detection Face recognition image analysis image processing image recognition algorithms Neural networks

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：