检索结果-内蒙古大学图书馆

Matching hyperspectral absorptions by weighted hamming distance

ELECTRONICS LETTERS 2021年第19期57卷 727-729页

作者： Guo, Baofeng Hangzhou Dianzi Univ Sch Automat Hangzhou Peoples R China

To analyse and compare hyperspectral signatures, features extraction and matching are two key issues. In this letter, hyperspectral absorption features and the corresponding matching algorithm are discussed. First, an absorption detection method is applied to catch all necessary spectral absorptions with improved reliability. Then, a weighted Hamming distance is proposed to match the binary absorption-features. Next, an elastic matching scheme is designed to classify the hyperspectral data. Experiments of classification are carried out on six classes of vegetation from the Salinas data-set. Results show that the proposed method not only increased the overall classification accuracy to 73.13% from back propagation neural network's 71.86% and support vector machine's 73.06%, but also improved the error distributions among different classes.

关键词： image recognition computer vision and image processing techniques Neural nets Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Technique for accurate correspondence estimation in object borders and occluded image regions

引用

ELECTRONICS LETTERS 1999年第1期35卷 34-35页

作者： Izquierdo, E Univ Essex Dept Elect Syst Engn Colchester CO4 3SQ Essex England

An advanced block-matching technique, in which the shape of the matching window is: calculated adaptively by applying an energy-based model, is introduced. In this model the window shape is controlled by external forces defined according to the entropy of previously estimated disparities. their reliability and the variation of the image intensity.

关键词： image processing estimation theory image intensity variation accurate correspondence estimation Optical, image and video signal processing block-matching technique computer vision energy-based model initial displacement estimation matching window shape occluded image regions adaptive calculation object borders entropy computer vision and image processing techniques image matching

来源：评论

学校读者我要写书评

暂无评论

Lossless image compression using ordered binary-decision diagrams

引用

ELECTRONICS LETTERS 2001年第3期37卷 162-163页

作者： Mateu-Villarroya, P Prades-Nebot, J Univ Politecn Valencia Dept Comun ETSITV Valencia 46022 Spain

A lossless compression algorithm for images based on ordered binary-decision diagrams (OBDDs) is presented. The algorithm finds an OBDD which represents the image exactly and then codes the OBDD efficiently. The resul... 详细信息

关键词： OBDD binary decision diagrams image and video coding data compression image coding Signal processing theory lossless compression algorithm Combinatorial mathematics lossless image compression computer vision and image processing techniques ordered BDD ordered binary-decision diagrams

来源：评论

学校读者我要写书评

暂无评论

Reweighting neural network examples for robust object detection at sea

引用

ELECTRONICS LETTERS 2021年第16期57卷 608-610页

作者： Becktor, J. Boukas, E. Blanke, M. Nalpantidis, L. Tech Univ Denmark Dept Elect Engn Lyngby Denmark

Deep neural networks have had profound significance in addressing visual object detection and classification tasks. However, though with the caveat of needing large amounts of annotated training data. Furthermore, the possibility of neural networks overfitting to the biases and faults included in their respective datasets. In this work, methods for achieving robust neural networks, able to tolerate untrusted and possibly erroneous training data, are explored. The proposed method is shown to improve performance and help neural networks learn from untrusted data, provided a thoroughly annotated subset.

关键词： Optical, image and video signal processing computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

Optimal vertex adjustment method using a Viterbi algorithm for vertex-based shape coding

引用

ELECTRONICS LETTERS 1999年第9期35卷 706-707页

作者： Lee, JH Chung, JW Kim, JK Korea Adv Inst Sci & Technol Dept Elect Engn Taejon 305701 South Korea Hyundai Elect Ind Co Ltd Informat & Telecommun R&D Ctr Seoul 137070 South Korea

An optimal vertex adjustment method is presented for vertex-based shape coding. The method optimally shifts the vertices, selected by a conventional vertex selection method, within the window that satisfies the allowable maximum distortion using a Viterbi algorithm. Experimental results show that the proposed method reduces the approximation distortion of the contour by similar to 30% for the same rate over a wide range of distortion, compared with the conventional method.

关键词： vertex selection method approximation distortion reduction image and video coding Viterbi decoding vertex-based shape coding Viterbi algorithm image coding vectors computer vision and image processing techniques optimal vertex adjustment method

来源：评论

学校读者我要写书评

暂无评论

Rate-optimised motion estimation

引用

ELECTRONICS LETTERS 2000年第14期36卷 1196-1197页

作者： Choi, SY Chae, SI Shim, YS Commun Technol Ctr Inst Adv Engn Yongin 449860 Kyonggi Do South Korea Seoul Natl Univ Dept Elect Engn Seoul 151742 South Korea

The authors propose a motion estimation (ME) algorithm fcr determining a motion vector which minimises the estimated total number of bits allocated to the motion vector and to the residual discrete cosine transform coefficients. This rate-optimised ME algorithm contributes to an improved reconstructed image quality and a reduced number of coding bits per frame.

关键词： motion vector Signal processing theory residual discrete cosine transform coefficients image quality motion estimation algorithm Codes estimated total number optimisation image coding reduced number rate-optimised motion estimation computer vision and image processing techniques image processing and restoration motion estimation image and video coding Optimisation techniques vector quantisation rate-optimised ME algorithm discrete cosine transforms image sequences coding bits

来源：评论

学校读者我要写书评

暂无评论

image retrieval using VQ-based local Gabor feature

引用

ELECTRONICS LETTERS 2002年第11期38卷 505-507页

作者： Shin, DK Kim, HS Chung, TY Kim, TS Park, SH Yonsei Univ Dept Elect & Elect Engn Sodaemoon Gu Seoul 120749 South Korea

A new method of retrieving images from large image databases is proposed. The method is based on vector quantisation (VQ) of local texture information extracted by a Gabor wavelet filter bank at interest points automatically detected in an image. The performance of the proposed method is tested on a trademark image database and compared with the performance of some existing methods.

关键词： wavelet transforms local texture information trademark image database visual databases filtering theory Optical, image and video signal processing Gabor wavelet filter bank image retrieval Filtering methods in signal processing vector quantisation VQ-based local Gabor feature feature extraction Spatial and pictorial databases image texture computer vision and image processing techniques large image databases

来源：评论

学校读者我要写书评

暂无评论

VQ-based digital image watermarking method

引用

ELECTRONICS LETTERS 2000年第14期36卷 1201-1202页

作者： Lu, ZM Pan, JS Sun, SH Harbin Inst Technol Dept Automat Test & Control Harbin 150006 Peoples R China Natl Kaohsiung Inst Technol Dept Elect Engn Kaohsiung 80782 Taiwan

A vector-quantisation (VQ)-based watermarking method is presented which utilises the codebook expansion technique. This method is efficient, provides enhanced security and the watermarked image is robust against the effects of VQ compression. Moreover, the watermark extraction can be performed without the original image. Experimental results are presented which demonstrate the effectiveness of this algorithm.

关键词： watermark extraction image and video coding data compression VQ compression image coding VQ-based digital image watermarking method Codes codebook expansion technique robust vectors vector-quantisation based watermarking method image processing and restoration security enhanced security computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

PIPELINED LOGICAL CONVOLVERS FOR BINARY PICTURE-processing

引用

ELECTRONICS LETTERS 1989年第15期25卷 961-963页

作者： HALL, AD Computer Laboratory University of Cambridge Cambridge UK

Pipelined logical convolvers (PLCs) are well suited to document facsimile processing as they can simply be inserted into the video data stream of scanners, etc. Their introduction has no effect on throughput and they require only a partial picture memory. A method is described for designing and implementing PLCs, using a structured approach that encourages experimentation and produces a cost efficient circuit. An example PLC is presented which performs image smoothing.

关键词： pipelines logic convolvers binary picture processing throughput partial picture memory pipeline processing document facsimile processing Optical information, image and video signal processing facsimile equipment video data stream image smoothing computerised picture processing computer vision and image processing techniques Facsimile transmission cost efficient circuit

来源：评论

学校读者我要写书评

暂无评论

Segmentation method for face detection in complex background

引用

ELECTRONICS LETTERS 2000年第3期36卷 213-214页

作者： Wang, YJ Yuan, BZ No Jiaotong Univ Inst Sci Informat Beijing 100044 Peoples R China

A nevi method for segmenting candidate regions of human faces with a complex background is proposed. A number of evolutionary agents are distributed in the 2-D colour image environment in order to find the face-like p... 详细信息

关键词： complex background image segmentation method face-like pixels image colour analysis image segmentation face detection image recognition Pattern recognition robust face recognition human faces evolutionary agents 2D colour image environment computer vision and image processing techniques image processing and restoration face-like region

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：