检索结果-内蒙古大学图书馆

A robust deep learning approach for glasses detection in non-standard facial images

IET BIOMETRICS 2021年第1期10卷 74-86页

作者： Bekhet, Saddam Alahmer, Hussein South Valley Univ Fac Commerce Qena 83523 Egypt Al Balqa Appl Univ Al Salt Jordan

Automated glasses detection is a cardinal component in facial/ocular analysis that powers forensic, surveillance and biometric authentication systems. Throughout literature, glasses detection was always experimented by either utilizing hand-crafted or deep learning features. Nevertheless, in both cases, highly standard face/ocular images were needed to derive the suggested technique. Both working methods performed reasonably well, but the results were bonded to the quality of the facial image and extracted features, where a slight shift and/or rotation in the input face image negatively affects the results. In addition, the obtained performance is even worse on real-world (non-standard) images, especially when compared to recent achievements in other computer vision research areas. In this paper, we present a robust deep learning approach for glasses detection from selfie photos full/partial frontal body non-standard images captured in real-life uncontrolled environments that do not utilize any facial landmarks. To the best of our knowledge this paper is the first to experiment detecting glasses from selfie photos, using a robust deep learning approach. Experimental results on various benchmark facial analysis datasets demonstrated the superior performance of the proposed technique with 96% accuracy.

关键词： facial image input face image facial-ocular analysis experiment detecting glasses automated glasses detection image recognition extracted features biometric authentication systems deep learning (artificial intelligence) biometrics (access control) robust deep learning approach utilizing hand-crafted facial landmarks nonstandard facial images benchmark facial analysis datasets real-life uncontrolled environments selfie photos face recognition Data security computer vision computer vision and image processing techniques feature extraction

来源：评论

学校读者我要写书评

暂无评论

Framework for FPGA-based discrete biorthogonal wavelet transforms implementation

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 2006年第6期153卷 721-734页

作者： Uzun, I. S. Amira, A. Queens Univ Belfast Sch Elect Elect & Comp Sci Belfast Antrim North Ireland Brunel Univ Sch Engn & Design Uxbridge UB8 3PH Middx England

The discrete wavelet transform has taken its place at the forefront of research for the development of signal and image processing applications. These wavelet-based approaches have outperformed existing strategies in many areas including telecommunication, numerical analysis and, most notably, image/video compression. The authors present an investigation into the design and implementation of 1-D and 2-D discrete biorthogonal wavelet transforms (DBWTs) using a field programmable gate array (FPGA)-based rapid prototyping environment. The proposed architectures for DBWTs are scalable, modular and have less area and time complexity when compared with existing structures. FPGA implementation results based on a Xilinx Virtex-2000E device have shown that the proposed system provides an efficient solution for the processing of DBWTs in real-time.

关键词： FPGA discrete biorthogonal wavelet transforms discrete wavelet transforms field programmable gate arrays Optical, image and video signal processing image processing Integral transforms image processing applications Logic and switching circuits computer vision and image processing techniques field programmable gate array Logic circuits signal processing applications

来源：评论

学校读者我要写书评

暂无评论

Handwritten Hindi character recognition: a review

引用

IET image processing 2018年第11期12卷 1919-1933页

作者： Yadav, Madhuri Purwar, Ravindra Kumar Mittal, Mamta Guru Govind Singh Indrapratha Univ USIC&T Delhi India GB Panth Govt Engn Coll Dept Comp Sci & Engn Delhi India

As the years passed by, computers became more powerful and automation became the need of generation. Humans tried to automate their work and replace themselves with machines. This effort of transition from manual to automatic gave rise to various research fields, and document character recognition is one such field. From the last few years, there is a sincere contribution from researchers for the development of optical character recognition systems for various scripts and languages. As a result of intensive research and development, there has been a significant improvement in handwritten devnagari text recognition. The main focus of this study is detailed survey of existing techniques for recognition of offline handwritten Hindi characters. It addresses all the aspects of Hindi character recognition starting from database to various phases of character recognition. The most relevant techniques of preprocessing, feature extraction and classification are discussed in various sections of this study. Moreover, this study is a zest of work accepted and published by research community in recent years. This study benefits its readers by discussing limitations of existing techniques and by providing beneficial directions of research in this field.

关键词： optical character recognition text analysis natural language processing languages document image processing Natural language processing preprocessing technique image recognition computer vision and image processing techniques feature extraction technique scripts document character recognition optical character recognition systems image classification feature extraction Document processing techniques offline handwritten Hindi character recognition handwritten Devnagari text recognition classification technique

来源：评论

学校读者我要写书评

暂无评论

Deep learning for waveform estimation and imaging in passive radar

引用

IET RADAR SONAR AND NAVIGATION 2019年第6期13卷 915-926页

作者： Yonel, Bariscan Mason, Eric Yazici, Birsen Rensselaer Polytech Inst Dept Elect Comp & Syst Engn Troy NY 12180 USA Naval Res Lab Tact Elect Warfare Div Washington DC 20375 USA

The authors consider a bistatic configuration with a stationary transmitter transmitting unknown waveforms of opportunity and a single moving receiver and present a deep learning (DL) framework for passive synthetic aperture radar (SAR) imaging. They approach DL from an optimisation based perspective and formulate image reconstruction as a machine learning task. By unfolding the iterations of a proximal gradient descent algorithm, they construct a deep recurrent neural network (RNN) that is parameterised by the transmitted waveforms. They cascade the RNN structure with a decoder stage to form a recurrent auto-encoder architecture. They then use backpropagation to learn transmitted waveforms by training the network in an unsupervised manner using SAR measurements. The highly non-convex problem of backpropagation is guided to a feasible solution over the parameter space by initialising the network with the known components of the SAR forward model. Moreover, prior information regarding the waveform structure is incorporated during initialisation and backpropagation. They demonstrate the effectiveness of the DL-based approach through numerical simulations that show focused, high contrast imagery using a single receiver antenna at realistic signal-to-noise-ratio levels.

关键词： deep recurrent neural network computer vision and image processing techniques passive radar learning (artificial intelligence) Optimisation techniques radar imaging recurrent neural nets Neural computing techniques stationary transmitter encoding Antennas deep learning framework Optical, image and video signal processing radar computing image reconstruction moving receiver proximal gradient descent algorithm Knowledge engineering techniques sufficient directivity Radar equipment, systems and applications recurrent-auto encoder architecture passive synthetic aperture radar imaging SAR measurements transmitted waveforms Electrical engineering computing gradient methods iterative methods waveform estimation concave programming single receiver bistatic configuration synthetic aperture radar machine learning task receiving antennas SAR forward model backpropagation Interpolation and function approximation (numerical analysis) RNN structure waveform structure passive radar methods Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Sparse patch-based representation with combined information of atlas for multi-atlas label fusion

引用

IET image processing 2018年第8期12卷 1345-1353页

作者： Yan, Meng Liu, Hong Song, Enmin Qian, Yuejing Jin, Lianghai Hung, Chih-Cheng Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan Hubei Peoples R China Hubei Univ Technol Sch Comp Wuhan Hubei Peoples R China Kennesaw State Univ Ctr Machine Vis & Secur Res Kennesaw GA USA

To obtain a higher accuracy in the multi-atlas patch-based label fusion method, it is essential to have the accurate similarity measure of selected patches. In this study, the authors propose a new sparse patch-based representation method using a local binary texture (LBT) in the atlas image and atlas label information for the multi-atlas label fusion. In the proposed method, the intensity information in a patch is converted into a LBT which is then combined with the labels of corresponding patches from the atlas to form an atom of a dictionary. The initial labels of target images are estimated through a rough segmentation. The voxel in a patch to be labelled is also constructed as a vector similar to the atom. The voxel vector is then modelled as a sparse linear combination of the atoms in the dictionary. Experimental results on two MR brain data sets demonstrated that the proposed method is efficient in the segmentation which can achieve competitive performance compared with the state-of-the-art methods.

关键词： sparse patch-based representation label fusion method image representation local binary texture Patient diagnostic methods and instrumentation atlas information voxel vector brain multiatlas label fusion Biology and medical computing computer vision and image processing techniques biomedical MRI image fusion representation method Optical, image and video signal processing image segmentation Biomedical magnetic resonance imaging and spectroscopy image classification atlas image sparse linear combination atlas label information medical image processing Medical magnetic resonance imaging and spectroscopy multiatlas patch

来源：评论

学校读者我要写书评

暂无评论

Human gait recognition from motion capture data in signature poses

引用

IET BIOMETRICS 2017年第2期6卷 129-137页

作者： Balazia, Michal Plataniotis, Konstantinos N. Univ Toronto Edward S Rogers Sr Dept Elect & Comp Engn Toronto ON M5S 1A1 Canada Masaryk Univ Fac Informat Brno Czech Republic

Most contribution to the field of structure-based human gait recognition has been done through design of extraordinary gait features. Many research groups that address this topic introduce a unique combination of gait features, select a couple of well-known object classifiers, and test some variations of their methods on their custom Kinect databases. For a practical system, it is not necessary to invent an ideal gait feature - there have been many good geometric features designed but to smartly process the data there are at the authors' disposal. This work proposes a gait recognition method without design of novel gait features;instead, the authors suggest an effective and highly efficient way of processing known types of features. Their method extracts a couple of joint angles from two signature poses within a gait cycle to form a gait pattern descriptor, and classifies the query subject by the baseline 1-NN classifier. Not only are these poses distinctive enough, they also rarely accommodate motion irregularities that would result in confusion of identities. They experimentally demonstrate that their gait recognition method outperforms other relevant methods in terms of recognition rate and computational complexity. Evaluations were performed on an experimental database that precisely simulates street-level video surveillance environment.

关键词： signature poses gait pattern descriptor extraordinary gait feature design 1-NN classifier Kinect databases motion irregularity computer vision and image processing techniques computational complexity image recognition feature extraction structure-based human gait recognition gait analysis motion capture data joint angle extraction image motion analysis image classification gait cycle street-level video surveillance environment data processing object classifiers

来源：评论

学校读者我要写书评

暂无评论

Spectral recovery-guided hyperspectral super-resolution using transfer learning SRTL for HSISR

引用

IET image processing 2021年第11期15卷 2656-2665页

作者： Zhang, Shaolei Fu, Guangyuan Wang, Hongqiao Zhao, Yuqing Xian High Tech Res Inst Dept Informat Engn Xian 710025 Peoples R China

Single hyperspectral image (HSI) super-resolution (SR) has attracted researcher's attention;however, most existing methods directly model the mapping between low- and high-resolution images from an external training dataset, which requires large memory and computing resources. Moreover, there are few such available training datasets in real cases, which prevent deep-learning-based methods from further improving performance. Here, a novel single HSI SR method based on transfer learning is proposed. The proposed method is composed of two stages: spectral down-sampled image SR reconstruction based on transfer learning and HSI reconstruction via spectral recovery module. Instead of directly applying the learned knowledge from the colour image domain to HSI SR, the spectral down-sampled image is fed into a spatial SR model to obtain a high-resolution image, which acts as a bridge between the colour image and HSI. The spectral recovery network is used to restore the HSI from the bridge image. In addition, pre-training and collaborative fine-tuning are proposed to promote the performance of SR and spectral recovery. Experiments on two public HSI datasets show that the proposed method achieves promising SR performance with a small paired HSI dataset.

关键词： HSI reconstruction image resolution available training datasets image representation external training dataset hyperspectral imaging spatial SR model image colour analysis image reconstruction computing resources computer vision and image processing techniques single hyperspectral image super-resolution geophysical image processing Optical, image and video signal processing bridge image spectral down-sampled image spectral recovery-guided high-resolution image learned knowledge image SR reconstruction public HSI datasets HSISR transfer learning spectral recovery module spectral recovery network learning (artificial intelligence) researcher Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research promising SR performance novel single HSI SR method colour image domain paired HSI dataset

来源：评论

学校读者我要写书评

暂无评论

Detecting multiple H.264/AVC compressions with the same quantisation parameters

引用

IET INFORMATION SECURITY 2017年第3期11卷 152-158页

作者： Zhang, Zhenzhen Hou, Jianjun Zhang, Yu Ye, Jingyu Shi, Yunqing Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Qualcomm Inc Corp R&D Beijing 100013 Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

Multiple-compression detection is of particular importance in video forensics, as it reveals possible manipulations to the content. However, methods for detecting multiple compressions with same quantisation parameters (QPs) are rarely reported. To deal with this issue, a novel method is presented in this study to detect multiple H.264/advanced video coding compressions with the same QPs. First, a new set, named ratio difference set (RDS), is proposed, which is calculated by identifying the quantised DCT coefficients whose values will be changed after re-compression. Then, a discriminative and fixed statistical feature set extracted from RDS of each video is obtained to serve as input for classification. With the aid of support vector machines, the extracted feature set is used to classify the videos that have undergone H. 264 compressions twice or more from those compressed just once. Experimental results show that high classification accuracy and robustness against copy-move attack and frame-deletion attack can be achieved with the authors' proposed method.

关键词： discrete cosine transforms statistical analysis discriminative feature set extraction QP ratio difference set fixed statistical feature set extraction data compression image recognition multiple H.264/AVC compression detection video forensics computer vision and image processing techniques Knowledge engineering techniques image and video coding quantisation parameters video classification quantisation (signal) video coding image classification copy-move attack RDS quantised DCT coefficients feature extraction video re-compression Video signal processing support vector machines frame-deletion attack

来源：评论

学校读者我要写书评

暂无评论

A novel outlier removal method for two-dimensional radar odometry

引用

IET RADAR SONAR AND NAVIGATION 2019年第10期13卷 1705-1712页

作者： Scannapieco, Antonio F. Cranfield Univ Def Acad United Kingdom Ctr Elect Warfare Informat & Cyber Shrivenham SN6 8LA England

Autonomous navigation of platforms in complex environments has a key role in many applications. However, environmental conditions could negatively affect the performance of electro-optical sensors. Hence, the idea of using radar odometry (RO) has been recently developed. However, it suffers from the presence of outliers in the scene as its electro-optical counterparts. This work presents a method to classify radar echoes as inliers or outliers for two-dimensional RO, based on their range rate and bearing angle. The range rate and bearing angle are, in fact, combined to give a classification value, different for each target. At each acquisition time, the median of all classification values is computed. Since classification values of stationary targets, i.e. the inliers, cluster around the median, while moving targets, i.e. the outliers, exhibit larger distance from the median, stationary targets and moving targets can be separated. This is also useful for sense-and-avoid purposes. The method has been tested in the simulated scenario to show effectiveness in detecting outliers and in a real-case scenario to demonstrate significant improvement in the reconstruction of the trajectory of the platform, keeping the final error around 10% of the travelled distance. Further improvement is envisaged by integrating the method in the target tracking strategy.

关键词： bearing angle computer vision and image processing techniques inliers environmental conditions moving targets electro-optical sensors range rate outliers target tracking strategy stationary targets radar tracking Optical, image and video signal processing electro-optical counterparts classification value Radar equipment, systems and applications optical sensors median two-dimensional RO outlier removal method radar echoes mobile robots complex environments distance measurement two-dimensional radar odometry Mobile robots target tracking

来源：评论

学校读者我要写书评

暂无评论

Driver activity recognition using spatial-temporal graph convolutional LSTM networks with attention mechanism

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第2期15卷 297-307页

作者： Pan, Chaopeng Cao, Haotian Zhang, Weiwei Song, Xiaolin Li, Mingjun Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body Changsha Peoples R China Shanghai Univ Engn Sci Coll Automot Engn Shanghai Peoples R China

Driver activity engagement while driving plays a vital role that leads to negative outcomes of driving safety. To reduce traffic accidents and ensure driving safety, real-time driver activity recognition architecture is proposed in this study. Specifically, a total of eight kinds of common driving-related activities are identified, which include the normal driving, left or right checking, texting, answering the phone, using media, drinking, and picking up objects. Raw experiment videos are collected via onboard monocular cameras, which are used for the upper body skeleton information extraction of the driver. Then, the graph convolutional networks (GCN) are constructed for spatial structure feature reasoning in a single frame, which is consecutively followed by long short-term memory (LSTM) networks for temporal motion feature learning within the sequence. Moreover, the attention mechanism is further utilised to emphasise the keyframes to select discriminative sequential information. Finally, a large-scale driver activity dataset, consisting of both naturalistic driving data and simulative driving data, is collected for model training and evaluations. Experimental results show that the general recall ratio of those eight driving-related activities reaches up to 88.8% and the real-time recognition efficiency can reach up to 24 fps, which would satisfy the real-time requirements of engineering applications.

关键词： Traffic engineering computing negative outcomes real-time recognition efficiency short-term memory networks temporal motion feature image motion analysis graph convolutional networks upper body skeleton information extraction video signal processing raw experiment videos traffic accidents image recognition computer vision and image processing techniques normal driving discriminative sequential information Optical, image and video signal processing spatial-temporal graph convolutional LSTM networks driver activity engagement image sequences large-scale driver activity dataset object detection feature extraction spatial structure feature reasoning naturalistic driving data Video signal processing learning (artificial intelligence) driver information systems real-time driver activity recognition architecture onboard monocular cameras driving safety common driving-related activities simulative driving data road safety recurrent neural nets traffic engineering computing attention mechanism

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：