检索结果-南通市图书馆

Using Entropy Based Mean Shift Filter and Modified Watershed Transform for Grain Segmentation

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2015年第2期12卷 199-207页

作者： Kun Zhang Min-Rui Fei Hui-Yu Zhou Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronic Engineering and AutomationShanghai University The Institute of electronics Communications and Information TechnologyQueen's University Belfast

Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper, we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice. However, due to the over-segmentation issue, this technique has experienced poor performance in various applications, such as inhomogeneous background and connected targets. To solve this problem, we present a combination of two classical techniques to handle this issue. In the first step, a mean shift filter is used to eliminate the inhomogeneous background,where entropy is used to be a converging criterion. Secondly, a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.

关键词： Robust segmentation cluttered grains mean shift filter entropy modified marked watershed transform.

Scene text detection and recognition： recent advances and future trends

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2016年第1期10卷 19-36页

作者： Yingying ZHU Cong YAO Xiang BAI school of Electronic Information and communications Huazhong University of Science and Technology Wuhan 430074 China

Text, as one of the most influential inventions of humanity, has played an important role in human life, so far from ancient times. The rich and precise information embod- ied in text is very useful in a wide range of vision-based ap- plications, therefore text detection and recognition in natu- ral scenes have become important and active research topics in computer vision and document analysis. Especially in re- cent years, the community has seen a surge of research efforts and substantial progresses in these fields, though a variety of challenges （e.g. noise, blur, distortion, occlusion and varia- tion） still remain. The purposes of this survey are three-fold： 1） introduce up-to-date works, 2） identify state-of-the-art al- gorithms, and 3） predict potential research directions in the future. Moreover, this paper provides comprehensive links to publicly available resources, including benchmark datasets, source codes, and online demos. In summary, this literature review can serve as a good reference for researchers in the areas of scene text detection and recognition.

关键词： text detection text recogntion natural image,algorithms applications

Hierarchical simultaneous entanglement swapping for multi-hop quantum communication based on multi-particle entangled states

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2021年第3期30卷 151-159页

作者： Guang Yang Lei Xing Min Nie Yuan-Hua Liu Mei-Ling Zhang school of communications and Information Engineering&school of Artificial Intelligence Xi’an University of Posts and TelecommunicationsXi’an 710121China

Entanglement swapping is a key technology for multi-hop communication based on entanglement in quantum networks. However, the end-to-end delay of the traditional sequential entanglement swapping (SEQES) grows rapidly withthe increase of network scale. To solve this problem, we first propose a low-delay multi-particle simultaneous entanglementswapping (SES) scheme to establish the remote four-particle Greenberger–Horne–Zeilinger (GHZ) channel states for thebidirectional teleportation of three-particle GHZ states, in which the intermediate nodes perform Bell state measurements,send the measurement results and the Bell state type to the user node Bob (or Alice) through classical channel simultaneously. Bob (or Alice) only needs to carry out a proper unitary operation according to the information he (or she) hasreceived. Further, we put forward a hierarchical simultaneous entanglement swapping (HSES) scheme to reduce the classical information transmission cost, which is composed of level-1 SES and level-2 SES (schemes). The former is an innersegment SES, and the latter is an inter segments SES. Theoretical analysis and simulation results show the HSES can obtainthe optimal performance tradeoff between end-to-end delay and classical cost.

关键词： multi-hop quantum communication entanglement swapping teleportation multi-particle

Kinetic theory of (2+4)-level atom in σ^+ σ^-laser fields

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2009年第8期18卷 3395-3403页

作者：于闯于得水陈景标 Institute of Quantum electronics School of Electronics Engineering & Computer SciencePeking University

The kinetic theory of （2＋4）-level atoms in σ^＋ -σ^- laser fields is presented. We systemically discuss friction coefficient, momentum diffusion tensor and atomic temperature based on the Fokker-Planck equation. This cooling system is much like that of a （1＋3）-level atom, and the temperature is still limited to the Doppler temperature. Since this cooling system has not been investigated before, this work may be regarded as a necessary complement to the laser cooling theory.

关键词： laser cooling Fokker-Planck equation quantum optics

A Conformal Conical Archimedean Spiral Antenna for UWB communications

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of electronics 2015年第2期24卷 402-407页

作者： SONG Lizhong FANG Qingyuan school of electronics and Information Engineering Harbin Institute of Technology at Weihai school of electronics and Information Engineering Harbin Institute of Technology

In this paper, a wide-band miniaturized Conformal conical Archimedean spiral(CCARS) antenna is proposed for Ultra wideband(UWB) *** CCARS antenna utilizes the vertical space instead of horizontal space significantly saving the antenna installation space. We investigate the transformation from Planar Archimedean spiral(PARS) antenna to the CCARS antenna and the antenna miniaturization technique. Due to the using of flexible dielectric substrate, the PARS antenna can be bent freely, which assures the transformation from the PARS antenna to the CCARS antenna. To realize antenna miniaturization, zigzag shape arms are applied to the PARS antenna. Moreover, the CCARS antenna has good unidirectional radiation property that avoids the using of traditional absorber-loaded back cavity. The measured results of antenna prototype indicate that the Voltage standing wave ratio(VSWR) is below 2 over the frequency range from 1.3GHz to 9GHz. The antenna gain is higher than3.4d Bi and the Front to back(F/B) ratio is better than20 d B from 2GHz to 7GHz. In addition, good radiation patterns and broad 3d B beam width are also available for the CCARS antenna.

关键词： Ultra wideband(UWB) communications Conformal antenna Miniaturized antenna Archimedean spiral antenna Microstrip tapered Balun

DISTRIBUTION OF ACTIVE EARTH PRESSURE OF RETAINING WALL WITH WALL MOVEMENT OF ROTATION ABOUT TOP

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2004年第7期25卷 761-767页

作者：王元战唐照评郑斌 school of Civil Engineering China communications Fourth Design Institute of Navigation

Based on the Coulomb's theory that the earth pressure against the back of a retaining wall is due to the thrust exerted by the sliding wedge of soil from the back of the wall to a plane which passes through the bottom edge of the wall and has an inclination equal to the angle of θ, the theoretical answers to the unit earth pressure, the resultant earth pressure and the point of application of the resultant earth pressure on a retaining wall were obtained for the wall movement mode of rotation about top. The comparisons were made among the formula presented here, the formula for the wall movement mode of translation, the Coulomb's formula and some experimental observations. It is demonstrated that the magnitudes of the resultant earth pressures for the wall movement mode of rotation about top is equal to that determined by the formula for the wall movement mode of translation and the Coulomb's theory. But the distribution of the earth pressure and the points of application of the resultant earth pressures have significant difference.

关键词： retaining wall rotation about top active earth pressure distribution point of application

Analysis of influence of RF power and buffer gas pressure on sensitivity of optically pumped cesium magnetometer

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2013年第10期22卷 206-212页

作者：石荣晔王延辉 Institute of Quantum electronics School of Electronics Engineering and Computer SciencePeking University school of Software and Microelectronics Peking University

A further study is conducted on two factors which respectively influence the sensitivity of optically pumped cesium magnetometer （CsOPM）. The influence of radio frequency （RF） power and the buffer gas pressure on the sensitivity is theoretically analyzed, and some properties are predicted. Based on the established measurement system and the visible Zeeman spectrum, not only is the real influence of these factors studied, but also, under our experimental condition, optimum parameters based on the measured curves are ascertained. The properties of these measured curves match the theoretical result very well. Our research attempts to provide theory reference to help magnetometer designers determine optimum parameters under certain conditions.

关键词： optically pumped cesium magnetometer buffer gas pressure sensitivity

Learning generalizable deep feature using triplet-batch-center loss for person re-identification

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第2期64卷 58-59页

作者： Bin HU Jiwei XU Xinggang WANG school of Electronic Information and communications Huazhong University of Science and Technology

Dear editor,Metric learning loss functions are important for deep learning-based person re-identification(re-ID). Several loss functions, such as triplet loss, center loss, and sphere loss,have been proposed. However, there are a few discussions on the generalization ability of these loss *** this study, we proposed a novel metric-learning loss function, triplet-batch-center loss(TBCL), to learn more generalizable deep features than the previous loss functions.

关键词： Information Systems and Communication Service

Weakly- and Semi-Supervised Fast Region-Based CNN for Object Detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2019年第6期34卷 1269-1278页

作者： Xing-Gang Wang Jia-Si Wang Peng Tang Wen-Yu Liu school of Electronic Information and communications Huazhong University of Science and Technology Wuhan 430074China

Learning an effective object detector with little supervision is an essential but challenging problem in computer vision applications. In this paper, we consider the problem of learning a deep convolutional neural network (CNN) based object detector using weakly-supervised and semi-supervised information in the framework of fast region-based CNN (Fast R-CNN). The target is to obtain an object detector as accurate as the fully-supervised Fast R-CNN, but it requires less image annotation effort. To solve this problem, we use weakly-supervised training images (i.e., only the image-level annotation is given) and a few proportions of fully-supervised training images (i.e., the bounding box level annotation is given), that is a weakly-and semi-supervised (WASS) object detection setting. The proposed solution is termed as WASS R-CNN, in which there are two main components. At first, a weakly-supervised R-CNN is firstly trained;after that semi-supervised data are used for finetuning the weakly-supervised detector. We perform object detection experiments on the PASCAL VOC 2007 dataset. The proposed WASS R-CNN achieves more than 85% of a fully-supervised Fast R-CNN's performance (measured using mean average precision) with only 10%of fully-supervised annotations together with weak supervision for all training images. The results show that the proposed learning framework can significantly reduce the labeling efforts for obtaining reliable object detectors.

关键词： object detection weakly-supervised learning semi-supervised learning fast region-based convolutional neural network (Fast R-CNN)