检索结果-内蒙古大学图书馆

Inherent limitation of digital imagery: spatial-phase vacillations and the ambiguity function

JOURNAL OF PHYSICS-PHOTONICS 2020年第3期2卷

作者： Johnson, R. Barry Heidary, Kaveh Alabama A&M Univ Dept Elect Engn & Comp Sci 4900 Meridian St Normal AL 35762 USA Alabama A&M Univ Dept Phys Chem & Math 4900 Meridian St Normal AL 35762 USA

The spatial relationship of a scene image upon a pixilated focal-plane-array can temporally change due to scene or camera motion, microjitter of camera line-of-sight, etc. It was found that degradation caused by subpixel spatial-phase vacillations (SPV) upon the performance of matched filters was unexpectedly significant. Subpixel spatial-phase vacillations can cause degradations in matched filter performance to detect desired objects and discriminate other objects. SPV appear to be an inherent limitation of digital imagery when processed using matched filter methodology and can negatively impact the performance of systems. Mitigation of this degradation was found to be possible by utilizing one of several matched filter constructions such as a multi-filter enhanced matched filter (EMF) bank and a single-filter EMF. A significant conclusion of this investigation is that, for automatic target recognition applications, improved overall task performance should be realized by the use of an EMF bank. Dramatic reduction in computational resources for image matching multispectral imagery was accomplished by spectrally-collapsing multispectral imagery to form pseudoimages with the spectral information appearing as a texture in a grayscale image. The pattern recognition ambiguity function, which sets the fundamental performance limit of an image processing system, is introduced.

关键词： digital image processing image enhancement image recognition devices image recognition algorithms and filters image reconstruction techniques pattern recognition target tracking

来源：评论

学校读者我要写书评

暂无评论

Quadratic divergence regularized SVM for optic disc segmentation

引用

BIOMEDICAL OPTICS EXPRESS 2017年第5期8卷 2687-2696页

作者： Cheng, Jun Tao, Dacheng Wong, Damon Wing Kee Liu, Jiang ASTAR Inst Infocomm Res Singapore Singapore Univ Sydney Sydney NSW Australia Chinese Acad Sci Cixi Inst Biomed Engn Beijing Peoples R China

Machine learning has been used in many retinal image processing applications such as optic disc segmentation. It assumes that the training and testing data sets have the same feature distribution. However, retinal images are often collected under different conditions and may have different feature distributions. Therefore, the models trained from one data set may not work well for another data set. However, it is often too expensive and time consuming to label the needed training data and rebuild the models for all different data sets. In this paper, we propose a novel quadratic divergence regularized support vector machine (QDSVM) to transfer the knowledge from domains with sufficient training data to domains with limited or even no training data. The proposed method simultaneously minimizes the distribution difference between the source domain and target domain while training the classifier. Experimental results show that the proposed transfer learning based method reduces the classification error in super-pixel level from 14.2% without transfer learning to 2.4% with transfer learning. The proposed method is effective to transfer the label knowledge from source to target domain, which enables it to be used for optic disc segmentation in data sets with different feature distributions. (C) 2017 Optical Society of America

关键词： (100.2960) Image analysis (100.3008) Image recognition algorithms and filters (100.0100) Image processing

来源：评论

学校读者我要写书评

暂无评论

Cytopathological image analysis using deep-learning networks in microfluidic microscopy

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2017年第1期34卷 111-121页

作者： Gopakumar, G. Babu, K. Hari Mishra, Deepak Gorthi, Sai Siva Subrahmanyam, Gorthi. R. K. Sai Indian Inst Space Sci & Technol Dept Earth & Space Sci Thiruvananthapuram 695547 Kerala India Indian Inst Space Sci & Technol Dept Avion Thiruvananthapuram 695547 Kerala India Indian Inst Sci Dept Instrumentat & Appl Phys Bangalore 560012 Karnataka India

Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings. (C) 2016 Optical Society of America.

关键词： Digital image processing Image recognition algorithms and filters Pattern recognition neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive optics stochastic optical reconstruction microscopy (AO-STORM) by particle swarm optimization

引用

BIOMEDICAL OPTICS EXPRESS 2017年第11期8卷 5087-5097页

作者： Tehrani, Kayvan F. Zhang, Yiwen Shen, Ping Kner, Peter Univ Georgia Coll Engn Athens GA 30602 USA Univ Georgia Dept Cellular Biol Athens GA 30602 USA Univ Georgia Regenerat Biosci Ctr Athens GA 30602 USA

Stochastic optical reconstruction microscopy (STORM) can achieve resolutions of better than 20nm imaging single fluorescently labeled cells. However, when optical aberrations induced by larger biological samples degrade the point spread function (PSF), the localization accuracy and number of localizations are both reduced, destroying the resolution of STORM. Adaptive optics (AO) can be used to correct the wavefront, restoring the high resolution of STORM. A challenge for AO-STORM microscopy is the development of robust optimization algorithms which can efficiently correct the wavefront from stochastic raw STORM images. Here we present the implementation of a particle swarm optimization (PSO) approach with a Fourier metric for real-time correction of wavefront aberrations during STORM acquisition. We apply our approach to imaging boutons 100 mu m deep inside the central nervous system (CNS) of Drosophila melanogaster larvae achieving a resolution of 146 nm. (C) 2017 Optical Society of America.

关键词： (220.1080) Active or adaptive optics (180.2520) Fluorescence microscopy (010.7350) Wave-front sensing (110.7348) Aberration compensation (100.3008) Image recognition algorithms and filters

来源：评论

学校读者我要写书评

暂无评论

Data-driven background representation method to video surveillance

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2017年第2期34卷 193-202页

作者： Li, Zhihui Xia, Yingji Qu, Zhaowei Jilin Univ Sch Transportat Changchun 130022 Peoples R China

Background subtraction is the fundamental step of moving object detection. As current methods use specific data-based or data learning methods to represent background, this will induce the problem of model distortion while the scenarios cannot meet their assumptions or model conditions. A novel data-driven framework is proposed to represent the background using the intrinsic characteristics of the background. In the framework, the model-free adaptive control method is used as an instance to analyze the background by its status of the nearest time instants, and linearize them dynamically from a pure data perspective. To overcome the occlusion of foreground objects, the selective update method is employed to satisfy the background update. Experiments are carried out under different video conditions to compare algorithm performance with state-of-the-art background models. The results show that the proposed method has reached over 95% in F-measure and percentage of correct classification in most cases, which is better than other state-of-the-art methods. Furthermore, the proposed method shows better robustness in severe video conditions, including bad weather and night cases, and its simplified data-driven control laws make it suitable for outdoor video surveillance. (C) 2017 Optical Society of America

关键词： Digital image processing Image recognition algorithms and filters Machine vision algorithms

来源：评论

学校读者我要写书评

暂无评论

Effective Reduction of the Phase Error for Gamma Nonlinearity in Phase Measuring Profilometry by BLPF

Effective Reduction of the Phase Error for Gamma Nonlinearit...

引用

International Conference on Optical Instruments and Technology - Optoelectronic Devices and Optical Signal Processing

作者： Zhao, Xiaxia Mo, Rong Chang, Zhiyong Lu, Jin Northwestern Polytech Univ Key Lab Contemporary Design & Integrated Mfg Tech Educ Minist 127 West Youyi Rd Xian 710072 Shaanxi Peoples R China

ISBN: (数字)9781510617469

ISBN: (纸本)9781510617469;9781510617452

In phase measuring profilometry, the system gamma nonlinearity makes the captured fringe patterns non-sinusoidal, which causes the computed phase to exist a non-ignorable error and seriously affects the 3D reconstruction accuracy. Based on the detailed study of the existing gamma nonlinearity compensation and phase error reduction technique, a method based on low-pass frequency domain filtering is proposed. It mainly filters out higher than one-order harmonic components induced by the gamma nonlinearity in conditions of holding as much power as possible in the power spectrum, thus improves sinusoidal waveform of the fringe images. Compared to other compensation methods, the complex mathematic model is not needed in the proposed method. The simulation and experiments confirm that the higher-order harmonic components are significantly reduced, the phase precision can be effectively improved and a certain accuracy requirement can be reached.

关键词： Phase measurement Fringe analysis Image recognition algorithms and filters

来源：评论

学校读者我要写书评

暂无评论

Enhanced manifold regularization for semi-supervised classification

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2016年第6期33卷 1207-1213页

作者： Gan, Haitao Luo, Zhizeng Fan, Yingle Sang, Nong Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China

Manifold regularization (MR) has become one of the most widely used approaches in the semi-supervised learning field. It has shown superiority by exploiting the local manifold structure of both labeled and unlabeled data. The manifold structure is modeled by constructing a Laplacian graph and then incorporated in learning through a smoothness regularization term. Hence the labels of labeled and unlabeled data vary smoothly along the geodesics on the manifold. However, MR has ignored the discriminative ability of the labeled and unlabeled data. To address the problem, we propose an enhanced MR framework for semi-supervised classification in which the local discriminative information of the labeled and unlabeled data is explicitly exploited. To make full use of labeled data, we firstly employ a semi-supervised clustering method to discover the underlying data space structure of the whole dataset. Then we construct a local discrimination graph to model the discriminative information of labeled and unlabeled data according to the discovered intrinsic structure. Therefore, the data points that may be from different clusters, though similar on the manifold, are enforced far away from each other. Finally, the discrimination graph is incorporated into the MR framework. In particular, we utilize semi-supervised fuzzy c-means and Laplacian regularized Kernel minimum squared error for semi-supervised clustering and classification, respectively. Experimental results on several benchmark datasets and face recognition demonstrate the effectiveness of our proposed method. (C) 2016 Optical Society of America

关键词： Pattern recognition Image recognition algorithms and filters algorithms

来源：评论

学校读者我要写书评

暂无评论

Recognizing blurred, nonfrontal, illumination, and expression variant partially occluded faces

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2016年第9期33卷 1887-1900页

作者： Punnappurath, Abhijith Rajagopalan, Ambasamudram Narayanan Indian Inst Technol Madras Dept Elect Engn Chennai 600036 Tamil Nadu India

The focus of this paper is on the problem of recognizing faces across space-varying motion blur, changes in pose, illumination, and expression, as well as partial occlusion, when only a single image per subject is available in the gallery. We show how the blur, incurred due to relative motion between the camera and the subject during exposure, can be estimated from the alpha matte of pixels that straddle the boundary between the face and the background. We also devise a strategy to automatically generate the trimap required for matte estimation. Having computed the motion via the matte of the probe, we account for pose variations by synthesizing from the intensity image of the frontal gallery a face image that matches the pose of the probe. To handle illumination, expression variations, and partial occlusion, we model the probe as a linear combination of nine blurred illumination basis images in the synthesized nonfrontal pose, plus a sparse occlusion. We also advocate a recognition metric that capitalizes on the sparsity of the occluded pixels. The performance of our method is extensively validated on synthetic as well as real face data. (C) 2016 Optical Society of America

关键词： Image processing Pattern recognition Image recognition algorithms and filters Machine vision

来源：评论

学校读者我要写书评

暂无评论

Frapid: achieving full automation of FRAP for chemical probe validation

引用

BIOMEDICAL OPTICS EXPRESS 2016年第2期7卷 422-441页

作者： Yapp, Clarence Rogers, Catherine Savitsky, Pavel Philpott, Martin Mueller, Susanne Univ Oxford Target Discovery Inst NDMRB Oxford OX3 7FZ England Univ Oxford Botnar Res Ctr NDORMS Oxford OX3 7LD England Univ Oxford ORCRB Struct Genom Consortium Oxford OX3 7DQ England

Fluorescence Recovery After Photobleaching (FRAP) is an established method for validating chemical probes against the chromatin reading bromodomains, but so far requires constant human supervision. Here, we present Frapid, an automated open source code implementation of FRAP that fully handles cell identification through fuzzy logic analysis, drug dispensing with a custom-built fluid handler, image acquisition & analysis, and reporting. We successfully tested Frapid on 3 bromodomains as well as on spindlin1 (SPIN1), a methyl lysine binder, for the first time. (C) 2016 Optical Society of America

关键词： (150.0150) Machine vision (100.3008) Image recognition algorithms and filters (150.5758) Robotic and machine control (170.1530) Cell analysis (170.1790) Confocal microscopy (170.2520) Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

Recognition of wall materials through active thermography coupled with numerical simulations

引用

APPLIED OPTICS 2016年第25期55卷 6821-6828页

作者： Pietrarca, Francesca Mameli, Mauro Filippeschi, Sauro Fantozzi, Fabio Univ Pisa DESTEC Largo L Lazzarino 2 I-56121 Pisa Italy

In the framework of historical buildings, wall thickness as well as wall constituents are not often known a priori, and active IR thermography can be exploited as a nonintrusive method for detecting what kind of material lies beneath the external plaster layer. In the present work, the wall of a historical building is subjected to a heating stimulus, and the surface temperature temporal trend is recorded by an IR camera. A hybrid numerical model is developed in order to simulate the transient thermal response of a wall made of different known materials underneath the plaster layer. When the numerical thermal contrast and the appearance time match with the experimental thermal images, the material underneath the plaster can be qualitatively identified. (C) 2016 Optical Society of America

关键词： Numerical approximation and analysis Image recognition algorithms and filters Materials Spectroscopy infrared

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：