检索结果-内蒙古大学图书馆

Chord bisection strategy for fast ellipse location

ELECTRONICS LETTERS 1999年第9期35卷 703-705页

作者： Davies, ER Univ London Royal Holloway & Bedford New Coll Dept Phys Machine Vis Grp Egham TW20 0EX Surrey England

It is shown that a previously proposed rapid sampling technique can be extended using a strategy based on chord bisection. The strategy is characterised by very high speed of operation coupled with accurate location, and can be matched to the level of robustness required by the application. The new technique has been tested on images in which the ellipses are cereal grains with close to 2:1 aspect ratio, but it appears to be suitable for locating ellipses of any eccentricity with near ultimate speed of processing.

关键词： image recognition fast ellipse location computer vision images image sampling cereal grains chord bisection strategy image recognition computer vision and image processing techniques rapid sampling technique

来源：评论

学校读者我要写书评

暂无评论

NEW ARRAY PROCESSOR ARCHITECTURES FOR TWO-DIMENSIONAL FIR DIGITAL-FILTERS

引用

IEE PROCEEDINGS-E computerS AND DIGITAL techniques 1989年第4期136卷 234-238页

作者： FAHMY, MM WAN, Y Department of Electrical Engineering Queen's University Kingston Canada

A new array processor architecture for two-dimensional (2D) FIR digital filters is developed. The processor has two processing rates for processing 2D signals in two directions. It processes the input signal using a row-by-row scheme. Owing to its high speed (about 30 images per second), it can be used for real-time image processing.

关键词： two-dimensional FIR digital filters real-time image processing row-by-row scheme processing rates array processor architectures Digital filters digital filters Optical information, image and video signal processing computer vision and image processing techniques picture processing

来源：评论

学校读者我要写书评

暂无评论

Nonlinear fuzzy rule-based approach for estimating video traffic rate

引用

ELECTRONICS LETTERS 1998年第15期34卷 1461-1462页

作者： Grant, PM Saw, YS Hannah, JM Univ Edinburgh Dept Elect & Elect Engn Edinburgh EH9 3JL Midlothian Scotland

The authors investigate a fuzzy logic-based video rate control technique which aims to regulate compressed video to a constant transmission rate, without incurring objectionable quality degradation. Conventional fuzzy rule-based control (FRC) does not adequately control the output video quality. Video information is therefore added into the FRC design by incorporating feed-forward scaling factors, derived from scene change features. The performance of this coder has been compared with other approaches measuring buffer occupancy, the number of coded bits per frame and peak signal-to-noise ratio.

关键词： buffer occupancy feedforward data compression constant transmission rate Codes knowledge based systems compressed video quality degradation nonlinear fuzzy rule-based approach Knowledge engineering techniques Optical information, image and video signal processing scene change features peak signal-to-noise ratio computer vision and image processing techniques FRC design feed-forward scaling factors fuzzy logic video coding video traffic rate

来源：评论

学校读者我要写书评

暂无评论

Conditional differential chain coding for lossless representation of object contour

引用

ELECTRONICS LETTERS 1998年第1期34卷 55-56页

作者： Chung, JW Moon, JH Kim, JK Korea Adv Inst Sci & Technol Dept Elect Engn Yusong Ku Taejon 305701 South Korea Hyundai Elect Ind Co Ltd Multimedia R&D Ctr Ichon 467860 Kyoungki Do South Korea

A new conditional differential chain coding (CDCC) scheme is presented for lossless representation of an object contour. It uses the conditional probability of directional symbols depending on the context of preceding contour directions. Experimental results show that the CDCC reduces coding bits by 5-10% when compared with the conventional differential chain coding (DCC) which does not use conditional probability.

关键词： directional symbols lossless representation data compression Codes Optical information, image and video signal processing object contour Information theory conditional probability video coding conditional differential chain coding computer vision and image processing techniques probability Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

A distributed document management system

引用

COMPUTING & CONTROL ENGINEERING JOURNAL 2002年第6期13卷 315-318页

作者： Homer, GR Thompson, DM Deacon, M Wolverhampton Univ Sch Comp & Informat Technol Wolverhampton WV1 1EL W Midlands England Adv Grp Ltd AMI Wolverhampton WV10 0AY W Midlands England

A commercial system for distributed document management, which was designed during a recent TCS Programme, is described. A brief introduction to the commercial partner, AMI-The Advance Group Ltd., is given, and the design features required from the system are discussed. The article concludes by discussing the degree of commercial success accruing from the system and the associated business demands resulting from this work.

关键词： distributed document management system document image processing Document processing techniques Internet Information management Information networks Office automation business demands records management Distributed systems software computer vision and image processing techniques TCS Programme

来源：评论

学校读者我要写书评

暂无评论

Head pose-free gaze estimation using domain adaptation

引用

ELECTRONICS LETTERS 2021年第16期57卷 618-620页

作者： Ahn, Byungtae Seo, Minseok Choi, Dong-Geol Korea Inst Machinery & Mat Dept AI Machinery Mech Syst Safety Res Div Daejeon South Korea Hanbat Natl Univ Dept Informat & Commun Engn Daejeon South Korea

Human gaze information has been widely used in various areas, such as medical diagnosis and human-computer interactions (HCI). This study proposes a head pose-free 3D gaze estimation method using a deep convolutional neural network (DCNN). To infer gaze direction, only a small grayscale image is required without any special devices such as an infrared (IR) illuminator and RGBD sensor. A domain adaptation method to reduce the feature gap between real and synthetic image data is also proposed here. Moreover, a novel synthetic dataset (SynFace) that contains head poses, gaze directions, and facial landmarks is established and released. The proposed method outperforms state-of-the-art methods and achieves a mean error of less than 4(White circle).

关键词： Optical, image and video signal processing image recognition image sensors computer vision and image processing techniques Other topics in statistics Other topics in statistics User interfaces

来源：评论

学校读者我要写书评

暂无评论

Learning object dynamics for smooth tracking of moving lip contours

引用

ELECTRONICS LETTERS 2000年第6期36卷 520-521页

作者： Wark, T Sridharan, S Chandran, V Queensland Univ Technol Sch Elect & Elect Engn RCSAVT Speech REs Lab Brisbane Qld 4001 Australia

A new technique is proposed for learning the dynamic characteristics of a deformable object applied in particular to the problem of lip-tracking. Experimental results are given which demonstrate that the use of dynamic models allows the system to track more robustly under adverse conditions and to correct spurious, poorly tracked frames.

关键词： adverse conditions learning (artificial intelligence) image motion analysis dynamics dynamic models dynamic characteristics learning moving lip contours Learning in AI object dynamics learning tracking smooth tracking robust tracking computer vision and image processing techniques deformable object

来源：评论

学校读者我要写书评

暂无评论

Symmetry estimation using a convolution property of disk harmonic coefficients

引用

ELECTRONICS LETTERS 1998年第22期34卷 2113-2115页

作者： Ming, L Kakarala, R Univ Auckland Dept Elect & Elect Engn Auckland 1 New Zealand

A convolution relationship between the disk harmonic coefficients of an image and those of a translated version is derived. It is used in a new symmetry estimation algorithm that uses disk harmonic coefficients. Compared to a previously reported algorithm, the new algorithm is more tolerant to segmentation errors and provides symmetry estimation with sub-pixel accuracy.

关键词： Optical, image and video signal processing estimation theory sub-pixel accuracy segmentation errors disk harmonic coefficients image segmentation symmetry estimation convolution harmonic analysis translated version convolution property computer vision and image processing techniques image recognition

来源：评论

学校读者我要写书评

暂无评论

RECOGNIZING PARTIALLY OCCLUDED OBJECTS BY RIGID BODY RELAXATION MATCHING

引用

ELECTRONICS LETTERS 1990年第13期26卷 856-858页

作者： LEE, T LI, R KONG, SH Department of Electronic Engineering Chinese University of Hong Kong Shatin Hong Kong

By representing 3D objects by a rigid-body model (RBM), application of probabilistic relaxation to satisfy the embedded spatial constraints in the RBMs for recognising partially occluded objects using range data was i... 详细信息

关键词： probabilistic relaxation computer simulated data set computer vision computerised pattern recognition recognising partially occluded objects feature extraction range data Pattern recognition Optical information, image and video signal processing rigid-body model rigid body relaxation matching embedded spatial constraints computerised picture processing computer vision and image processing techniques 3D objects Communications computing range images

来源：评论

学校读者我要写书评

暂无评论

image segmentation using data-modulated nonlinear diffusion

引用

ELECTRONICS LETTERS 2000年第21期36卷 1767-1769页

作者： Izquierdo, E Xu, LQ Univ London Queen Mary & Westfield Coll Elect Engn Dept London E1 4NS England BT Adv Commun Res Ipswich IP5 3RE Suffolk England

Effective object segmentation is achieved by applying a novel data-modulated nonlinear diffusion technique. The advantages of this strategy are a considerable smoothing of the detail of the scene image within the boundaries of the object while inhibiting the diffusion across the boundaries, as well as preserving and even enhancing the object borders.

关键词： Optical, image and video signal processing detail smoothing object borders enhancement data-modulated nonlinear diffusion image segmentation scene image Signal processing theory computer vision and image processing techniques image enhancement

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：