检索结果-内蒙古大学图书馆

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Weifang Ma Peiyan Wang Dongfeng Cai Dahan Wang Human-computer Intelligence Research Center Shenyang Aerospace University Shenyang People’s Republic of China

ISBN: (纸本)9781728152103

Content-based 3D CAD model retrieval takes a 3D CAD model as input and finds other models with the same or similar structure. This paper proposes a two-stage retrieval method that can take into account the global and local similarity of CAD models. In the first stage, the CAD model formation candidate modles with high global matching degree with the query model is selected, and the TF-IMF (Term Frequency-Inverse Model Frequency) vector method is proposed to describe the global surface line distribution of the 3D CAD model. In the second stage, on the basis of the global similarity, the models which are locally similar with the query models are further filtered, and the attribute adjacency graphs between models are calculated by ACO (ant colony optimization) algorithm. Experimental results show that the proposed method achieves better retrieval performance than the maximum clique method based on the attribute adjacency graph (NDCG), which is 90.68%, and has higher retrieval efficiency.

关键词： ant colony optimisation CAD content-based retrieval design feature extraction graph theory image matching image retrieval solid modelling entity modeling Computer-Aided Design DFFB gene Content retrieval image matching image retrieval Graph theory Feature extraction Ant colony optimization retrieval three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Multiple License Plate Location Algorithm in Complex Scene

Multiple License Plate Location Algorithm in Complex Scene

引用

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： YuMei Zhou MeiNi Lv ZiQing Ling DongLing Li School of Electrical and Eletronic Engineering TianHe College of GuangDong Polytechnic Normal University GuangZhou China School of Eletronic and Information Engineering WuZhou University WuZhou China

ISBN: (纸本)9781728152103

Aiming at the problem that the existing license plate location methods can't work well in locating the license plate in certain natural scenes such as low luminance, low resolution and inclination scene of vehicle, a license plate location method based on cascade classifier and convolution neural network is proposed. Firstly, the cascade classifier is used for license plate coarse location, and the convolution neural network is used for license plate precise location. Experiments show that, compared with cascade classifier, the method in this paper has higher accuracy and recall rate for target license plate location, and the method in this paper has strong adaptability to different environments.

关键词： character recognition convolutional neural nets edge detection feature extraction image colour analysis object detection traffic engineering computing License plates image colour analysis Character recognition Object detection Edge detection Feature extraction engineering computing cascades Retrieval recall

来源：评论

学校读者我要写书评

暂无评论

M^2 S^2 F^2 : Multiscale Multistage Spectral-Spatial Features Fusion Framework for Hyperspectral image Classification

M^2 S^2 F^2 : Multiscale Multistage Spectral-Spatial Feature...

引用

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Xiangbin Shi Kuo Song Zhaokui Li Jing Bi Deyuan Zhang School of Computer Science Shenyang Aerospace University Shenyang China

ISBN: (纸本)9781728152103

Hyperspectral image classification has been widely applied in many fields, but it also faces challenges because of small number of labeled samples. In this paper, we propose the Multiscale Multistage Spectral-Spatial Feature Fusion Framework (M^2 S^2 F^2 ) for hyperspectral image classification using small training samples. The Framework is the combination of two deep convolutional neural networks, which can extract more representative and discriminative features by combining the following operations. Firstly, two different scale 3-D cubes are the inputs for the spectral and spatial feature extraction respectively. Secondly, by fusing strong complementary information between different layers, we form multistage spectral and spatial features by fusion primary, intermediate and advanced features of the spectral and spatial features respectively. Spectral and spatial features are extracted by spectral and spatial skipped residual blocks, which can effectively alleviate the problems of gradient degradation. Thirdly, the fusion of complementary multistage spectral and spatial features can improve the classification accuracy. Experimental results on the IN, UP and KSC datasets show the effectiveness of the proposed method using small training samples.

关键词： convolutional neural nets feature extraction hyperspectral imaging image classification image fusion image classification hyperspectral imagery Feature extraction image fusion MULTISTAGE Fusion reactions Fusion, biological FUSION fusion (melting) Taxonomy

来源：评论

学校读者我要写书评

暂无评论

MSK Carrier Synchronization Scheme Based on Demodulation Soft Information Aided

MSK Carrier Synchronization Scheme Based on Demodulation Sof...

引用

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yuan Qiu Xiaoxin He Institute of Software Beijing China

ISBN: (纸本)9781728152103

The existing carrier synchronization algorithms for MSK signals suffer from the disadvantages of low estimation accuracy and difficult implementation under the condition of low signal-to-noise ratio (SNR). To address the problems, the paper proposes a novel carrier synchronization scheme based on demodulation soft information aided. The joint iteration of the synchronizer and demodulator aims to maximize the objective function, the mean square value of demodulation soft information. In the two-dimensional search of carrier frequency and phase offset, the scheme realizes carrier synchronization of near maximum likelihood estimation. It is shown, via analyses and simulations, that its bit error rate (BER) performance approaches the theoretical bound. This scheme is an effective solution for MSK short-time burst transmission systems at the expense of low complexity.

关键词： demodulation error statistics iterative methods maximum likelihood estimation mean square error methods minimum shift keying synchronisation minimum shift keying Demodulation Mean square error maximum likelihood estimation carrier synchronization iterative methods mean square values signal to noise ratios Error analysis

来源：评论

学校读者我要写书评

暂无评论

NSST Based MRI-PET/SPECT Color image Fusion Using Local Features Fuzzy Rules and NSML in YIQ Space

NSST Based MRI-PET/SPECT Color Image Fusion Using Local Feat...

引用

ieee International symposium on signal processing and Information Technology (ISSPIT)

作者： Hikmat Ullah Yaqin Zhao Longwen Wu Fakheraldin Y. O. Abdalla Hassan Mkindu School of Electronics and Information Engineering Harbin Institute of Technology Harbin P.R. China

ISBN: (数字)9781728153414

ISBN: (纸本)9781728153421

An improved algorithm for the fusion of anatomical structural MRI (magnetic resonance imaging) and metabolic functional PET (positron emission tomography) or SPECT (single photon emission computed tomography) images is proposed here. First, if any of the source image is in RGB format, it is converted to YIQ color space. Then by taking full advantage of non-subsampled shearlet transform (NSST), both the input images (channel-Y and/or gray-scale) are decomposed into one low frequency subbands (LFS) and several high frequency subbands (HFS). Second, local spatial frequency (SF) and region energy (RE) based fuzzy pixel-rules are applied for the fusion of LFS. Where, the fused HFS coefficient is directly selected by computing and comparing novel sum-modified-Laplacian (NSML) of every HFS, to extract maximum and more useful information. Finally, the required fused image is achieved by inversed NSST and inversed YIQ transform. Experimental results obtained shows that the algorithm significantly achieved maximum feature information from the source images, enhance visual quality and contrast of the fused image, and decrease computational task compared to other state-of-art proposed methods.

关键词： image color analysis Gray-scale image fusion Transforms Feature extraction Visualization Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Finger Multimodal Features Fusion and Recognition Based on CNN

Finger Multimodal Features Fusion and Recognition Based on C...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Li Wang Haigang Zhang Jingfeng Yang Tanjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China Shenzhen Polytechnic Shenzhen China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Finger-based multimodal fusion recognition has attracted increasing attention due to its high stability and security in practical application. Traditional fusion methods exist some challenges in scale inconsistency and universality. In additon, multimodal dimension standardization has not been well realized. In this paper, we propose a novel convolutional neural network(CNN) framework for finger multimodal fusion and recognition, which obtains the fusion features by network learning automatically. The fusion network makes full use of the complementary information among three modals of finger to make the fusion features more stable and effective. Firstly, the three parallel CNNs have been designed to extract unimodal features. Then, a size standardization method based on principal component analysis(PCA) is utilized for different unimodal features. Finally, the high-level unimodal features are integrated to learn fusion features with better representation capability. Extensive experiments on the finger multimodal dataset show that the proposed multimodal fusion network performs better than other state-of-the-arts.

关键词： Feature extraction Biometrics (access control) Standardization Convolution Authentication Principal component analysis Imaging

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Rehabilitation Assessment for Thermal and Heart Rate Data processing

引用

ieee TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2018年第6期26卷 1209-1214页

作者： Prochazka, Ales Charvatova, Hana Vysata, Oldrich Univ Chem & Technol Dept Comp & Control Engn Prague 16628 Czech Republic Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 166 36 Czech Republic Tomas Bata Univ Zlin Fac Appl Informat Zlin 760 01 Czech Republic Charles Univ Prague Dept Neurol Fac Med Hradec Kralove CR-11636 Prague Czech Republic

Multimodal signal analysis based on sophisticated noninvasive sensors, efficient communication systems, and machine learning, have a rapidly increasing range of different applications. The present paper is devoted to pattern recognition and the analysis of physiological data acquired by heart rate and thermal camera sensors during rehabilitation. A total number of 56 experimental data sets, each 40 min long, of the heart rate and breathing temperature recorded on an exercise bike have been processed to determine the fitness level and possible medical disorders. The proposed general methodology combines machine learning methods for the detection of the changing temperature ranges of the thermal camera and adaptive image processing methods to evaluate the frequency of breathing. To determine the individual temperature values, a neural network model with the sigmoidal and the probabilistic transfer function in the first and the second layers are applied. Appropriate statistical methods are then used to find the correspondence between the exercise activity and selected physiological functions. The evaluated mean delay of 21 s of the heart rate drop related to the change of the activity level corresponds to results obtained in real cycling conditions. Further results include the average value of the change of the breathing temperature (167 s) and breathing frequency (49 s).

关键词： Multimodal signal analysis computational intelligence machine learning thermal imaging physical rehabilitation assessment respiratory monitoring

来源：评论

学校读者我要写书评

暂无评论

DnM3Net: Multi-Scale & Multi-Level Shuffle-CNN Via Multi-Level Attention for image Denoising

DnM3Net: Multi-Scale & Multi-Level Shuffle-CNN Via Multi-Lev...

引用

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yue Cao Jinhe He Yu Zhang Gang Lu Shigang Liu Xiaojun Wu School of Computer Science Shaanxi Normal University Xian Shaanxi Normal University Xi'an China

ISBN: (纸本)9781728152103

Recently, based on novel convolutional neural net-work architectures proposed, tremendous advances have been achieved in image denoising task. An effective and efficient multi-level network architecture for image denoising refers to restore the latent clean image from a coarser scale to finer scales and pass features through multiple levels of the model. Unfortunately, the bottleneck of applying multi-level network architecture lies in the multi-scale information from input images is not effectively captured and the fine-to-coarse feature fusion strategy to be ignored in image denoising task. To solve these problems, we propose a multi-scale & multi-level shuffle-CNN Via multi-level attention (DnM3Net), which plugs the multi-scale feature extraction, fine-to-coarse feature fusion strategy and multi-level attention module into the new network architecture in image denoising task. The advantage of this approach are two-fold: (1) It solve the multi-scale information extraction issue of multi-level network architecture, making it more effective and efficient for the image denoising task. (2) It is impressive performance because the better trade-off between denoising and detail preservation. The proposed novel network architecture is validated by applying on synthetic gaussian noise gray and RGB images. Experimental results show that the DnM3Net effectively improve the quantitative metrics and visual quality compared to the state-of-the-art denoising methods.

关键词： convolutional neural nets feature extraction Gaussian noise image colour analysis image denoising image sampling image denoising image samples image colour analysis NETWORK STRUCTURE Gaussian noise Feature extraction multi-scale hierarchical models Noise reduction

来源：评论

学校读者我要写书评

暂无评论

A New Nonlinear Compounding Technique for Ultrasound B-mode Medical Imaging

A New Nonlinear Compounding Technique for Ultrasound B-mode ...

引用

ieee International Ultrasonics symposium

作者： Asraf Mohamed Moubark Luzhen Nie David M. J Cowell Sawal Hamid Md Ali Steven Freear Center for Integrated Systems Engineering and Advanced Technologies University Kebangsaan Malaysia Selangor Malaysia Ultrasound Group School of Electronic and Electrical Engineering University of Leeds UK

Compounding techniques have been used in ultra-fast ultrasound imaging to improve image quality by reducing clutter noise, smoothing speckle variance and enhancing its spatial resolution at the cost of reducing frame rate. However, the reduction of clutter noise and side lobes inside the anechoic regions is minimal when combining conventional spatial compounding and delay-and-sum (DAS) beamforming. Despite the availability of advanced beamforming algorithms such as filtered-delay-multiply-and-sum (FDMAS), its prevalence is hindered by relatively high computational cost. In this study, a new nonlinear compounding technique known as filtered multiply and sum (FMAS) was proposed to improve the B-mode image quality without increasing the overall computational complexity. With three compunding angles, the lateral resolution for DAS-FMAS was improved by 36% and 19% compared to DAS and FDMAS. The proposed DAS-FMAS technique also provided improvements of 14.1 dB and 7.29 dB in contrast ratio than DAS and FDMAS.

关键词： Frequency division multiaccess Ultrasonic imaging Array signal processing Imaging Clutter Acoustics Wires

来源：评论

学校读者我要写书评

暂无评论

An Object Detection Network for Embedded System

An Object Detection Network for Embedded System

引用

ieee International symposium on Parallel and Distributed processing with Applications and ieee International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yanpeng Sun Chenlu Wang Lele Qu College of Electronic Information Shenyang Aerospace University Shenyang China

ISBN: (纸本)9781728152103

Object detection in images has a wide range of applications in various fields. However, many of the convolutional neural networks recently proposed have higher requirements on computing resources while achieving higher precision, which cannot guarantee good real-time performance on embedded platforms with limited resources. This paper proposed an object detection network suitable for embedded systems. The M-YOLO (Mobile-YOLO) model proposed in this paper combines depthwise separable convolution and residual blocks in feature extraction layers, which helps to reduce the amount of computation of the network. Multi-scale feature fusion is applied to the output layers to improve the accuracy. Experiments show that the M-YOLO model has 9.68M FLOPs (Floating Point Operations), which is about 22% of Tiny-YOLO model. The accuracy of the network reaches 56.61% on the PASCAL VOC dataset, and the speed in ARM is over 3 times faster than Tiny-YOLO model. The network is more suitable for embedded systems.

关键词： convolutional neural nets embedded systems feature extraction image fusion object detection Embedded systems Object detection image fusion Feature extraction

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：