检索结果-南通市图书馆

Face anti-spoofing based on multi-modal and multi-scale features fusion

The Journal of China Universities of Posts and Telecommunications 2022年第6期29卷 73-82页

作者： Kong Chao Ou Weihua Gong Xiaofeng Li Weian Han Jie Yao Yi Xiong Jiahao School of Big Data and Computer science Guizhou Normal UniversityGuiyang 550025China Special Key Laboratory of Artificial Intelligence and Intelligent Control of Guizhou Province Guizhou Institute of TechnologyGuiyang 550003China Guizhou science and technology information Center Department of Science and Technology of Guizhou ProvinceGuiyang 550002China

Face anti-spoofing is used to assist face recognition system to judge whether the detected face is real face or fake face. In the traditional face anti-spoofing methods, features extracted by hand are used to describe the difference between living face and fraudulent face. But these handmade features do not apply to different variations in an unconstrained environment. The convolutional neural network(CNN) for face deceptions achieves considerable results. However, most existing neural network-based methods simply use neural networks to extract single-scale features from single-modal data, while ignoring multi-scale and multi-modal information. To address this problem, a novel face anti-spoofing method based on multi-modal and multi-scale features fusion(MMFF) is proposed. Specifically, first residual network(Resnet)-34 is adopted to extract features of different scales from each modality, then these features of different scales are fused by feature pyramid network(FPN), finally squeeze-and-excitation fusion(SEF) module and self-attention network(SAN) are combined to fuse features from different modalities for classification. Experiments on the CASIA-SURF dataset show that the new method based on MMFF achieves better performance compared with most existing methods.

关键词： face anti-spoofing multi-modal fusion multi-scale fusion self-attention network(SAN) feature pyramid network(FPN)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Chinese New Year Folk Culture Adds Impetus to Guizhou's Colorful Tourism Economy

引用

China & The World Cultural Exchange 2024年第4期 14-17页

作者： Zhang Hongxi Liao Mengying Liu Qiong Guizhou Minzu University Guiyang Institute of Information Science and Technology

During the Chinese New Year in 2024,a series of traditional folk activities were held all over Guizhou,attracting a large number of travelers,with the number of received travelers and comprehensive income of Guizhou r... 详细信息

关键词： income Guizhou attracting

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Application of improved virtual sample and sparse representation in face recognition

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1391-1402页

作者： Yongjun Zhang Zewei Wang Xuexue Zhang Zhongwei Cui Bob Zhang Jinrong Cui Lamin LJanneh College of Computer science and technology Guizhou UniversityGuiyangChina Big Data science and Intelligent Engineering Research institute Guizhou Education UniversityGuiyangChina School of Mathematics and Big Data Guizhou Education UniversityGuiyangChina Department of Computer and information science University of MacaoAvenida da UniversidadeTaipaMacaoChina School of Mathematics and information South China Agricultural UniversityGuangzhouChina

Sparse representation plays an important role in the research of face recognition.As a deformable sample classification task,face recognition is often used to test the performance of classification algorithms.In face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition accuracy.Essentially,there may be significant differences between different image samples of the same face,which makes image classification very difficult.Therefore,how to build a robust virtual image representation becomes a vital issue.To solve the above problems,this paper proposes a novel image classification algorithm.First,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual sample.Second,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,respectively.After obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test sample.These two distances are converted into distance scores.Finally,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual image.The fused score will determine the final classification result.The experimental results show that the proposed method outperforms other typical sparse representation classification methods.

关键词： representation sample image

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Gas equilibrium heat capacity synthesis under the influence of acoustic relaxation process and its application in gas detection

引用

Chinese Journal of Acoustics 2019年第4期38卷 386-402页

作者： ZHANG Kesheng ZHANG Xiangqun SHAO Fang School of Electrical and information Engineering Guizhou Institute of TechnologyGuiyang 550003 School of Electronic information and Communications Huazhong University of Science and TechnologyWuhan 430074 School of Mechanical Engineering Guizhou Institute of TechnologyGuiyang 550003

In an excitable gas,the molecular vibration relaxation process caused by an acoustic disturbance leads the equilibrium heat capacity to the effective one that depends on the acoustic frequency,resulting in acoustic dispersion and acoustic relaxational absorption.Based on the algorithm of synthesizing a single-relaxation process,we develop a synthesizing method to get the equilibrium heat capacities of excitable gases from the two-frequency acoustic speed and absorption measurements.The two measurement frequencies are selected in the range where the acoustic relaxational absorption is obvious.The method can obtain the heat capacities of internal and external degrees of freedom of gas molecules respectively,and effectively eliminate the influence of the acoustic relaxation process on the measurement results of excitable gas heat capacity.For various gases,consisting of CO2,CH4,Cl2,N2 and O2 at room temperature,the gas heat capacities obtained in this paper agree with the thermodynamic theoretical calculations based on the Planck-Einstein formula,and the maximum relative error is 3.51% in comparison to the experimental result.The synthesized heat capacities of rotation and vibration can be applied to the detection of gas molecular geometry,vibration frequency and mole fractions of gas mixtures.

关键词： relaxation equilibrium gases

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Effect of cold stratification on the temperature range for germination of Pinus koraiensis

引用

Journal of Forestry Research 2023年第1期34卷 221-231页

作者： Yuan Song Xinghuan Li Mingyi Zhang Guowei Xia Chao Xiong College of Eco-Environmental Engineering Guizhou Minzu UniversityGuiyangPeople’s Republic of China Qingyuan Forest CERN Chinese Academy of SciencesShenyang 110016People’s Republic of China Karst Environmental Geological Hazard Prevention Laboratory of Guizhou Minzu University GuiyangPeople’s Republic of China Guiyang Institute of Information Science and Technology GuiyangPeople’s Republic of China

Germination at low spring temperatures may offer a competitive advantage for the growth and survival of plant species inhabiting temperate forest ecosystems.Pinus koraiensis is a dominant species in temperate forests of northeastern China.Its seeds exhibit primary morphophysiological dormancy following dispersal in autumn,limiting natural or artificial regeneration:direct seeding and planting seedlings in spring.The aim of this study was to determine the optimum cold stratification temperature that induces germination to increase towards lower temperatures.Seeds from two populations(Changbaishan and Liangshui)were cold stratified at 0,5 and 10℃.Germination to incubation temperatures(10/5,20/10,25/15 and 30/20℃;14/10 h day/night)were determined after 2 and 4 weeks,and 5.5 and6.5 months of cold stratification.After 5.5 months,approximately 68-91%of seeds from both populations germinated at incubation temperatures of 25/15℃and 30/20℃,regardless of cold stratification temperatures.When the cold stratification temperature was reduced to 0℃and the period increased to 6.5 months,germination at 10/5℃significantly improved,reaching 37%and 64%for the Changbaishan and Liangshui populations,respectively.After 6.5 months of cold stratification,there was a significant linear regression between cold stratification temperatures and germination at10/5℃.The range in temperatures allowing for germination gradually expanded to include lower temperatures with decreasing cold stratification temperatures from 10 to 5℃and further to 0℃.

关键词： Cold Stratification temperatures Pinus koraiensis Seed germination Germination temperature range

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Calculation of vibrational energy transition rates in acoustic relaxation processes for excitable gas molecules

引用

Chinese Journal of Acoustics 2018年第2期37卷 202-218页

作者： ZHANG Kesheng ZHANG Xiangqun TANG Wenyong XIAO Yingqun JIANG Xueqin School of Electrical and information Engineering~ Guizhou institute of technology guiyang 550003 School of Electronic information and Communications Huazhong University of Science and Technology Wuhan 430074 School of Big Data Guizhou Institute of Technology Guiyang 550003

To research the correlation between vibrational energy transition rates and acoustic relaxation processes in excitable gases, the vibrational relaxation theory provided by Tanczos [J. Chem. Phy3. 25, 439 （1956）] is applied to calculate the energy transition rates of Vibrational- Vibrational （V-V） and Vibrational-Translational （V-T） energy transfer in gas mixtures. The results of calculation for the multi-relaxation processes in various gas mixtures, consisting of carbon dioxide, methane, chlorine, nitrogen, and oxygen at room temperature, demonstrate that the acoustic energy stagnated in every vibrational mode is coupled with each other through V-V energy exchanges. The vibrational excitation energy will relax through the V-T de-excitation path of the lowest mode because of its fastest V-T transition rate, resulting in that only one absorption peak can be measured for most of excitable gas mixtures. Thus, an effective model is provided to analyze how the vibrational energy transition rates affect the characteristics of acoustic relaxation processes and acoustic propagation in excitable gas mixtures.

关键词： Calculation of vibrational energy transition rates in acoustic relaxation processes for excitable gas molecules

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A federated learning scheme meets dynamic differential privacy

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 1087-1100页

作者： Shengnan Guo Xibin Wang Shigong Long Hai Liu Liu Hai Toong Hai Sam State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyangChina School of Big Data Key Laboratory of Electric Power Big Data of Guizhou ProvinceGuizhou Institute of TechnologyGuiyangChina School of information Guizhou University of Finance and EconomicsGuiyangChina Faculty of Business and Communication INTI International UniversityNilaiMalaysia

Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep learning.Concretely,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created manually.It also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model training.The experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.

关键词： data privacy machine learning security of data

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Sparse representation scheme with enhanced medium pixel intensity for face recognition

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 116-127页

作者： Xuexue Zhang Yongjun Zhang Zewei Wang Wei Long Weihao Gao Bob Zhang State Key Laboratory of Public Big Data Institute for Artificial IntelligenceCollege of Computer Science and TechnologyGuizhou UniversityGuiyangGuizhouChina Department of Computer and information science University of MacaoAvenida da UniversidadeTaipaMacaoChina

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.

关键词： computer vision face recognition image classification image representation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Robust discriminative broad learning system for hyperspectral image classification

引用

Optoelectronics Letters 2022年第7期18卷 444-448页

作者： ZHAO Liguo HAN Zhe LUO Yong School of Computer and information Engineering Luoyang Institute of Science and TechnologyLuoyang 471023China Guizhou Cloud Big Data Industry Development Co. Ltd.Guiyang 550001China

With the advantages of simple structure and fast training speed,broad learning system(BLS)has attracted attention in hyperspectral images(HSIs).However,BLS cannot make good use of the discriminative information contained in HSI,which limits the classification performance of BLS.In this paper,we propose a robust discriminative broad learning system(RDBLS).For the HSI classification,RDBLS introduces the total scatter matrix to construct a new loss function to participate in the training of BLS,and at the same time minimizes the feature distance within a class and maximizes the feature distance between classes,so as to improve the discriminative ability of BLS features.RDBLS inherits the advantages of the BLS,and to a certain extent,it solves the problem of insufficient learning in the limited HSI samples.The classification results of RDBLS are verified on three HSI datasets and are superior to other comparison methods.

关键词： learning has native

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Geometric prior guided hybrid deep neural network for facial beauty analysis

引用

CAAI Transactions on Intelligence technology 2024年第2期9卷 467-480页

作者： Tianhao Peng Mu Li Fangmei Chen Yong Xu David Zhang The School of Computer science and technology Guizhou UniversityGuiyangChina Department of Automation Moutai InstituteRenhuaiGuizhouChina The School of Computer science and technology Harbin Institute of TechnologyShenzhenShenzhenChina The information and Communication Engineering Department Dalian Minzu UniversityDalianChina The School of Data science The Chinese University of Hong KongShenzhenShenzhenChina

Facial beauty analysis is an important topic in human society.It may be used as a guidance for face beautification applications such as cosmetic surgery.Deep neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable performance.However,most existing DNN-based models regard facial beauty analysis as a normal classification task.They ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty analysis.To be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the decision.Inspired by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial parts.Additionally,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two branches.In model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric features.Experiments performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid network.To the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

关键词： deep neural networks face analysis face biometrics image analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：