检索结果-内蒙古大学图书馆

International Conference on vLSI Design

作者： P S Babu Snehashri Sivaraman Deepa N Sarma Tripti S Warrier Cochin University of Science and Technology Kochi Kerala India Meenakshi Sundararajan Engineering College Chennai India Indian Institute of Technology Madras Chennai India

With an ever-increasing usage of electronic controllers in various disciplines that could be attributed to Industry 4.0, Internet of Things (IoT) and quick shift in computational paradigms, a demand for high code density and faster controllers are expected at the diversified nodes that improve energy efficiency without performance penalty. RISC-v is an open-source Instruction Set Architecture (ISA) which is designed with modularized extensions, that enables to design processors with a provision of individual extension evaluation helping in the design of low-power and secure embedded controllers. Bit manipulation is one of the key operations performed in domains such as Cryptography, Communication and Networking protocols, Digital Signal processing, Bioinformatics etc., which are currently implemented using RISC-v standard instruction set. This paper implements the `B' extension of RISC-v that hosts instructions specific to operate at bit-level manipulations, which is absent in ratified unprivileged ISA manual. A quantitative analysis is performed to assess the impact of Bit Manipulative Instructions (BMI) in size and speed improvements using the Embench ™ benchmarks against the standard instruction set `IMAC' under the Rv32 configuration. The results show significant improvements, with some programs achieving a speedup of 28 % and size reduction of 20 %.

关键词： image coding Protocols Statistical analysis Instruction sets Signal processing algorithms Benchmark testing very large scale integration

来源：评论

学校读者我要写书评

暂无评论

Model-based reconstruction for enhanced X-ray CT of Tri-structural Isotropic (TRISO) particles

arXiv

引用

arXiv 2021年

作者： venkatakrishnan, Singanallur v. Ziabari, Amirkoushyar Bingham, Philip Helmreich, Grant Multimodal Sensor Analytics Group Oak Ridge National Lab Oak RidgeTN37831 United States Nuclear Fuels Group Oak Ridge National Lab Oak RidgeTN37831 United States

Tri-Structural Isotropic (TRISO) fuel particles are a key component of next generation nuclear fuels. Using X-ray computed tomography (CT) to characterize TRISO particles is challenging because of the strong attenuation of the X-ray beam by the uranium core leading to severe photon starvation in a substantial fraction of the measurements. Furthermore, the overall acquisition time for a high-resolution CT scan can be very long when using conventional lab-based X-ray systems and reconstruction algorithms. Specifically, when analytic methods like the Feldkamp-Davis-Kress (FDK) algorithm is used for reconstruction, it results in severe streaks artifacts and noise in the corresponding 3D volume which make subsequent analysis of the particles challenging. In this article, we develop and apply model-based image reconstruction (MBIR) algorithms for improving the quality of CT reconstructions for TRISO particles in order to facilitate better characterization. We demonstrate that the proposed MBIR algorithms can significantly suppress artifacts with minimal pre-processing compared to the conventional approaches. Furthermore, we demonstrate the proposed MBIR approach can obtain high-quality reconstruction compared to the FDK approach even when using a fraction of the typically acquired measurements, thereby enabling dramatically faster measurement times for TRISO particles. © 2021, CC BY.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Smart CMOS mid-infrared sensor array

引用

OPTICS LETTERS 2019年第17期44卷 4111-4114页

作者： Popa, Daniel Ali, Sped Zeeshan Hoppe, Richard Dai, Ying Udrea, Florin Univ Cambridge Dept Engn Cambridge CB30FA England Ams Sensors UK Ltd Cambridge CB4 0DL England

We present a novel single-chip thermopile sensor array for mid-infrared room temperature imaging. The array is fabricated on a single complementary metal-oxide-semiconductor (CMOS) dielectric membrane, composed of single-crystal silicon (Si) p(+) and n(+) elements, and standard CMOS tungsten metal layers for thermopile cold junction heatsinking, significantly reducing the chip size and simplifying its processing. We demonstrate a 16 x 16 pixel device with 34 v/W responsivity and enhanced optical absorption in the 8-14 mu m waveband, with a suitable performance for gesture recognition and people-counting applications. Our simple, low-cost sensor is an attractive on-chip array for a variety of applications in the mid-infrared spectral region. (C) 2019 Optical Society of America

关键词： Fourier transform infrared spectroscopy image processing image processing algorithms image sensors Infrared sensors Optical systems

来源：评论

学校读者我要写书评

暂无评论

Canonical saliency maps: Decoding deep face models

arXiv

引用

arXiv 2021年

作者： John, Thrupthi Ann Balasubramanian, vineeth N. Jawahar, C.v. The International Institute of Information Technology Hyderabad India The Indian Institute of Technology Hyderabad India

As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may have far-reaching consequences. We need methods to build trust in deployed systems by making their working as transparent as possible. Existing visualization algorithms are designed for object recognition and do not give insightful results when applied'to the face domain. In this work, we present 'Canonical Saliency Maps', a new method which highlights relevant facial areas by projecting saliency maps onto a canonical face model. We present two kinds of Canonical Saliency Maps: image-level maps and model-level maps. image-level maps highlight facial features responsible for the decision made by a deep face model on a given image, thus helping to understand how a DNN made a prediction on the image. Model-level maps provide an understanding of what the entire DNN model focuses on in each task, and thus can be used to detect biases in the model. Our qualitative and quantitative results show the usefulness of the proposed canonical saliency maps, which can be used on any deep face model regardless of the architecture. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Sclera Segmentation using Spatial Kernel Fuzzy Clustering Methods 9th

Sclera Segmentation using Spatial Kernel Fuzzy Clustering Me...

引用

9th International Conference on Pattern Recognition Applications and Methods (ICPRAM)

作者： Maheshan, M. S. Harish, B. S. Kumar, S. v. Aruna JSS Sci & Technol Univ Dept Informat Sci & Engn Mysuru Karnataka India Univ Beira Interior Socia Lab Covilha Portugal

ISBN: (纸本)9789897583971

Biometrics is one of the domain that is gaining lot of importance in the present digital industry. Biometrics are getting integrated in different devices and reaching the end users at a very affordable cost. Among various biometric traits, Sclera is one such trait that is getting popular in the research community for its distinct nature of authenticating and identification of individuals. The recognition system using sclera trait purely depends on efficient segmentation of sclera image. Segmentation process is considered to be significant in image processing system because of better visualization. The segmentation can be done using region based, edge based, threshold based and also clustering based techniques. This paper concentrates on clustering based technique by proposing a variant of conventional Fuzzy C Means (FCM) algorithm. Though the Fuzzy C Means presents outstanding results in many applications, unfortunately it is sensitive to noise and ignore neighbourhood information. Thus to alleviate these limitations this paper presents Generalized Spatial Kernel Fuzzy C Means (GSK-FCM) clustering algorithms for sclera segmentation. To evaluate the proposed methods, experimentation are conducted on Sclera Segmentation and Recognition Benchmarking Competition (SSRBC 2015) dataset. The result of the experiments reveals that the proposed methods outperform the other variants of FCM.

关键词： Clustering Fuzzy C Means Sclera Segmentation

来源：评论

学校读者我要写书评

暂无评论

Adaptation of parameterized interpolation algorithms of multidimensional signals for hierarchical and interpolation compression methods 6

Adaptation of parameterized interpolation algorithms of mult...

引用

6th International Conference Information Technology and Nanotechnology. Session image processing and Earth Remote Sensing, ITNT-IPERS 2020

作者： Gashnikov, Mikhail Department of GIS ITsec Samara National Research University MMIP Laboratory Image Processing Systems Institute of RAS Branch of the FSRC "Crystallography and Photonics" RAS Samara Russia

We adapt parameterized multidimensional signal interpolators for hierarchical compression methods and interpolation compression methods based on the coding of quantized post-interpolation residues. The considered interpolators automatically select the most appropriate interpolating function at each point of the signal using a parameterized decision rule. We propose a set of interpolation functions for these compression methods. We select the optimization criterion for the proposed interpolator. The optimization criterion is based on minimization the entropy of the quantized post-interpolation residues. We solve the optimization problem of the adaptive parameterized interpolator according to this criterion. We perform computational experiments to study the proposed interpolators in natural multidimensional signals. The experimental results confirm that the use of the adaptive interpolators can significantly increase the effectiveness of the mentioned methods of multidimensional signals compression. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

An Accurate Real-Time License Plate Detection Method Based On Deep Learning Approaches

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2021年第12期35卷 2160008-2160008页

作者： Khazaee, Saeed Tourani, Ali Soroori, Sajjad Shahbahrami, Asadollah Suen, Ching Yee Concordia Univ Ctr Pattern Recognit & Machine Intelligence Montreal PQ Canada Univ Guilan Dept Comp Engn Rasht Iran Concordia Univ Ctr Pattern Recognit & Machine Intelligence Montreal PQ Canada

In vision-driven Intelligent Transportation systems (ITS) where cameras play a vital role, accurate detection and re-identification of vehicles are fundamental demands. Hence, recent approaches have employed a wide range of algorithms to provide the best possible accuracy. These methods commonly generate a vehicle detection model based on its visual appearance features such as license plate, headlights, or some other distinguishable specifications. Among different object detection approaches, Deep Neural Networks (DNNs) have the advantage of magnificent detection accuracy in case a huge amount of training data is provided. In this paper, a robust approach for license plate detection (LPD) based on YOLO v.3 is proposed which takes advantage of high detection accuracy and real-time performance. The mentioned approach can detect the license plate location of vehicles as a general representation of vehicle presence in images. To train the model, a dataset of vehicle images with Iranian license plates has been generated by the authors and augmented to provide a wider range of data for test and train purposes. It should be mentioned that the proposed method can detect the license plate area as an indicator of vehicle presence with no Optical Character Recognition (OCR) algorithm to distinguish characters inside the license plate. Experimental results have shown the high performance of the system with a precision 0.979 and recall 0.972.

关键词： Deep learning intelligent transportation systems automatic number-plate detection image processing

来源：评论

学校读者我要写书评

暂无评论

Challenges encountered in building a fast and efficient surveillance system: An overview 4

Challenges encountered in building a fast and efficient surv...

引用

4th International Conference on IoT in Social, Mobile, Analytics and Cloud, ISMAC 2020

作者： Rama Moorthy, H. Upadhya, vijeth Holla, vidyesh v Shetty, Sunil S Tantry, vinay v Shri Madhwa Vadiraja Institute of Technology and Management Department of Computer Science and Engineering Bantakal India

ISBN: (纸本)9781728154640

Most often a prominent IoT application in a residential area and office spaces for simple surveillance. Challenge wrests in the legal systems nowadays to any developing nations, especially in those nations where the density of populations is more than normal. Here a huge task-force is required to monitor and maintain law and order situations across the loop and corner of the cities and villages. CCTv's is deployed to at-least capture some part of the busy streets and at a server room;it is being monitored by some officials. With a large number of data being produced as part of criminals, suspects, missing profiles, etc., it would be difficult for any officials to keep track of those data sets manually. Hence if a smart system can be used to process the videos as and when it is captured, one can say 90% of the task of monitoring the busy streets can be achieved. In this paper, it is possible to review the works/algorithms based on four categories for building fast, efficient, and accurate Surveillance systems, i.e., face detection, face recognition, video/image processing, pattern matching in a video surveillance system. The investigation in these recent advancements will help one to build a better surveillance system. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection using image processing

Lung Cancer Detection using Image Processing

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Taiwo Soewu S.v. Uday Kalyan Manik Rakhra Dalwinder Singh Department of computer engineering Olabisi Onabanjo University Ago Iwoye Nigeria Department Of Computer Science and Engineering Lovely Professional University Phagwara India Head Of Department Computer Science and Engineering Lovely Professional University Phagwara India

One of the common diseases related to cancer which have high rate is lung cancer, which is largely due to the slow capture of the malignant tumor. Again, the commonly used methods for diagnosing lung cancer have several drawbacks. Despite the effectivity of computed tomography of identifying this malignancy, the need for radiologists to process vast amounts of data not only makes their job more difficult but can also delay the detection of lung cancer in time enough for treatment to begin. In this context, computer-aided diagnostic (CAD) systems were developed. A convolutional neural network is one of the ways that can be used to describe an alternate method of applying a set of deep learning algorithms with filtering. These algorithms can be learned by performing local pooling operations on CT images in order to generate a set of hierarchical complicated functions. The convolutional neural network is the method that is considered to be the most effective. In order to properly segment lung nodules, one stage that cannot be skipped while attempting to design a reliable system for detection called for the application of data-driven methodologies. This stage is essential. Lung nodule identification has been effectively achieved using models and variants of convolutional neural networks. Since it has been utilized in the medical sector for some time, the 2D Convolution layer has demonstrated both many strengths and numerous limitations. The 3D model is currently rapidly gaining popularity as it addresses these shortcomings and improves the convolutional neural network’s detection skills. The accuracy and specificity of 3D models were already found to be high for lung nodule detection, implementing a a 3D model for the medical industry can be challenging due to time requirements, training difficulties, and hardware memory requirements. See this study for developments in the use of a 3D CNN model for lung cancer diagnosis.

关键词： Solid modeling Three-dimensional displays Convolution Computational modeling Computed tomography Memory management Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A computer vision based online quality control system for textile yarns

引用

COMPUTERS IN INDUSTRY 2021年 133卷

作者： Haleem, Noman Bustreo, Matteo Del Bue, Alessio Ist Italiano Tecnol Pattern Anal & Comp Vis Via Enrico Melen 83 I-16152 Genoa Italy Haukeland Univ Sjukehus Med Avdeling Postboks 61Jonas Lies Vei 65 N-5021 Bergen Norway

Yarn quality control is a crucial step in producing high quality textile end products. Online yarn testing can reduce latency in necessary process control by providing rapid insights into yarn quality, leading to pro-duction of superior quality yarns. However, both widely used capacitance based evenness testers and emerging imaging based evenness testing systems are largely offline in operation (i.e. a posteriori). A suitable online system that could be employed to test quality of a variety of yarns in normal industrial processing conditions does not yet exist. In this study, we propose an online evenness testing system for measurement of a certain type of yarn defect called nep by using imaging and computer vision techniques. The developed system directly captures yarn images on a spinning frame and uses viola-Jones object detection algorithm for real-time detection of nep defects. The validation of nep detection algorithms and comparison of the new method with an existing evenness tester in terms of nep count demonstrated its reasonable defect detection accuracy and promising potential for application in wider yarn spinning industry. (c) 2021 The Authors. Published by Elsevier B.v. CC_BY_NC_ND_4.0

关键词： image acquisition Computer vision Textile yarn Online quality control viola-Jones algorithm Yarn spinning

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：