检索结果-内蒙古大学图书馆

Wavelet domain-based video noise reduction using temporal discrete cosine transform and hierarchically adapted thresholding

引用

IET image processing 2007年第1期1卷 2-12页

作者： Gupta, N. Swamy, M. N. S. Plotkin, E. I. Concordia Univ Ctr Signal Proc & Commun Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada

A novel spatio-temporal filter for video denoising, which operates entirely in the wavelet domain, is proposed. For effective noise reduction, the spatial and temporal redundancies that exist in the wavelet domain representation of a video signal are exploited. First, a 2D discrete wavelet transform is applied to the input noisy frames. This is followed by a discrete cosine transform (DCT), which is applied to the temporal subband coefficients to minimise the redundancy among the consecutive frames. The DCT transformed, noise-free coefficients in the different wavelet domain subbands for the original image sequence are modelled using a prior having a generalised Gaussian distribution. On the basis of this prior, filtering of the noisy wavelet coefficients in each subband is carried out using a new, low-complexity wavelet shrinkage method, which utilises the correlation that exists between subsequent resolution levels. Experimental results show that the proposed scheme outperforms several state-of-the-art spatio-temporal filters in terms of both the peak signal-to-noise ratio and the visual quality.

关键词： image resolution noisy wavelet coefficients discrete cosine transforms Filtering methods in signal processing temporal discrete cosine transform generalised Gaussian distribution noise-free coefficients spatio-temporal filter hierarchically adapted thresholding video signal processing temporal subband coefficients computer vision and image processing techniques 2D discrete wavelet transform wavelet domain-based video noise reduction Optical, image and video signal processing low-complexity wavelet shrinkage method Integral transforms wavelet domain subbands visual quality discrete wavelet transforms image sequences signal-to-noise ratio Gaussian distribution filtering theory subsequent resolution levels Video signal processing video denoising image denoising Other topics in statistics image sequence

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral face recognition with a spatial information fusion for local dynamic texture patterns and collaborative representation classifier

引用

IET image processing 2021年第8期15卷 1617-1628页

作者： Hao, Min Liu, Guangyuan Xie, Desheng Southwest Univ Coll Elect & Informat Engn Chongqing Peoples R China Southwest Univ Chongqing Key Lab Nonlinear Circuit & Intelligent Chongqing Peoples R China Suson Co Ltd Chengdu Sichuan Peoples R China

Hyperspectral face recognition provides improved classification rates due to its abundant information in the face cubes of every subject in hyperspectral face databases. However, while offering excellent opportunities, it also brings new challenges, such as low signal-to-noise ratio, interband misalignment, and high data dimensionality. Based on these ad hoc problems, literature has already proposed some optimisation methods including dimensionality reduction, image denoising, and alignment to perform face recognition, yet lacking comprehensive evaluation. This paper proposes a novel hyperspectral face recognition algorithm that is based on spatial information fusion for feature extraction (histogram of local dynamic texture patterns) and collaborative representation classifier for classification. Meanwhile, the algorithm is applied to three popular hyperspectral face databases, Carnegie Mellon University (CMU)-hyperspectral face database (HSFD), University of Western Australia (UWA)-HSFD, and Hong Kong Polytechnic University (PolyU)-HSFD databases. Experimental results demonstrate that CMU-HSFD and UWA-HSFD databases achieve very competitive classification results. PolyU-HSFD database also achieves rather good classification rates. The best recognition results are 98.5% +/- 0.95, 96.6% +/- 0.98, and 94.0% +/- 2.86 for CMU-HSFD, UWA-HSFD and PolyU-HSFD, respectively. It demonstrates experimentally that this algorithm can be used to recognise faces. Moreover, we compared eight existing state-of-the-art face recognition techniques with our proposed method in performing hyperspectral face recognition. In this research, we formulate hyperspectral face recognition as an image-set classification problem and evaluate the performances compared with other kinds of algorithms. Comparisons with the eight existing hyperspectral face recognition techniques on three standard datasets show that the proposed algorithm outperforms most other state-of-the-art algorithms, indicating t

关键词： image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Document binarisation using kohonen SOM

引用

IET image processing 2007年第1期1卷 67-84页

作者： Badekas, E. Papamarkos, N. Democritus Univ Thrace Dept Elect & Comp Engn Image Proc & Multimedia Lab Xanthi 67100 Greece

An integrated system for the binarisation of normal and degraded printed documents for the purpose of visualisation and recognition of text characters is proposed. In degraded documents, where considerable background noise or variation in contrast and, illumination exists, there are many pixels that cannot be easily classified as foreground or background pixels. For this reason, it is necessary to perform document binarisation by combining and taking into account the results of a set of binarisation techniques, especially for document pixels that have high vagueness. The proposed binarisation technique takes advantages of the benefits of a set of selected binarisation algorithms by combining their results using a Kohonen selforganising map neural network. In order to improve further the binarisation results, significant improvements are proposed for two of the most powerful document binarisation techniques used, that is for the adaptive logical level technique and for the improvement of integrated function algorithm. The proposed binarisation technique is extensively tested with a variety of degraded documents. Several experimental and comparative results, demonstrating the performance of the proposed technique, are presented.

关键词： Neural computing techniques document binarisation text character visualisation document image processing character recognition self-organising feature maps image recognition computer vision and image processing techniques binarisation techniques Kohonen self-organising map neural network Kohonen SOM integrated function algorithm Document processing techniques text character recognition background noise image denoising document pixels degraded printed documents adaptive logical level technique

来源：评论

学校读者我要写书评

暂无评论

Underwater image enhancement based on colour correction and fusion

引用

IET image processing 2021年第11期15卷 2591-2603页

作者： Zhu, Daqi Liu, Zhiqiang Zhang, Youmin Shanghai Maritime Univ Shanghai Engn Res Ctr Intelligent Maritime Search Haigang Ave 1550 Shanghai 201306 Peoples R China Concordia Univ Dept Mech Ind & Aerosp Engn Montreal PQ Canada

Underwater image processing has always been a very challenging problem. Under the influence of environmental factors, underwater images are prone to some problems, such as colour cast, low visibility, and few edge details. Here, an image enhancement algorithm is proposed to improve image degradation mainly caused by the absorption of light. First, colour compensation and white balance algorithm are used to restore the natural appearance of the image. Then the improved dark channel prior (DCP) is used to improve the visibility and avoid blocking artifacts which appear in traditional DCP. Unsharp masking (USM) is applied to enhance the texture features of the DCP image. Finally, wavelet fusion is used to fuse the DCP image and DCP+USM image. The fusion algorithm not only further improves the visibility and texture features, but also reduces the noise of DCP+USM. Compared with other methods, quantitative analysis results show that the enhanced images have higher visibility, more details and edge information.

关键词： Optical, image and video signal processing Sensor fusion computer vision and image processing techniques Integral transforms Integral transforms

来源：评论

学校读者我要写书评

暂无评论

image enhancement by wavelet-based thresholding neural network with adaptive learning rate

引用

IET image processing 2011年第7期5卷 573-582页

作者： Bhutada, G. G. Anand, R. S. Saxena, S. C. Indian Inst Technol Roorkee Dept Elect Engn Roorkee Uttar Pradesh India

A new approach has been proposed to improve the computational performance of denoising in which adaptively defined learning step size has been used for tuning the parameter of the thresholding function of wavelet transform-based thresholding neural network (WT-TNN) methodology. In this approach, steepest gradient-based learning step size of WT-TNN methodology are changed to the proposed adaptively defined learning step size for tuning the parameters of thresholding function. The results of the image enhanced by such adaptive learning step size exhibit the increase in the speed of learning and improved edge preservation feature. Further, the learning time has also become independent of noise level and initial values of learning parameters.

关键词： edge detection Neural computing techniques WT-TNN methodology image denoising computer vision and image processing techniques gradient-based learning step size wavelet-based thresholding neural network adaptive learning rate telecommunication computing Optical, image and video signal processing image enhancement edge preservation feature neural nets

来源：评论

学校读者我要写书评

暂无评论

MPGI-Terminal defect detection based on M-FRCNN

引用

IET image processing 2023年第2期17卷 428-438页

作者： Liu, Qunpo Wang, Mengke Wang, Haixing Hanajima, Naohiko Henan Polytech Univ Sch Elect Engn & Automat 2001 Century Ave Jiaozuo 454003 Henan Peoples R China Henan Int Joint Lab Direct Drive & Control Intell 2001 Century Ave Jiaozuo Henan Peoples R China Muroran Inst Technol Coll Informat & Syst 27-1 Mizumoto Cho Muroran Hokkaido Japan

Micro-precision glass insulated terminal (MPGI-Terminal) is a high-precision and widely used micro-precision component. The MPGI-Terminal is small in size with 2-5 mm in diameter. It is difficult to distinguish missing blocks on the surface during manual inspection, which is prone to false detection and missing detection. The advantages of deep learning methods in the field of object detection have gradually highlighted. They can be used to construct the missing block detection model of MPGI-Terminal. A Max-Min Intersection over Union (MIoU) loss function based on overlap area, distance and aspect ratio is proposed, which helps the model to perform bounding box regression more reasonably, so as to obtain the object position more accurately. In addition, the Spatial Attention Module (SAM) and the Region of Interest Alignment (RoI Align) module are introduced to further improve the model performance. Based on the above modules, a MPGI-Terminal missing block detection model based on M-FRCNN is constructed. The results show that the proposed model can meet the requirements of fast and high accuracy of MPGI-Terminal missing block detection.

关键词： MPGI-Terminal missing block detection model missing detection image segmentation feature extraction Regression analysis object detection false detection deep learning (artificial intelligence) Neural nets missing blocks Optical, image and video signal processing regression analysis microprecision glass insulated terminal microprecision component MPGI-Terminal defect detection computer vision and image processing techniques inspection convolutional neural nets

来源：评论

学校读者我要写书评

暂无评论

Real-time CVSA decals recognition system using deep convolutional neural network architectures

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第11期15卷 1359-1371页

作者： Yepez, Juan Castro-Zunti, Riel Choi, Younhee Ko, Seok-Bum Univ Saskatchewan Dept Elect & Comp Engn Saskatoon SK Canada Int Rd Dynam Inc Saskatoon SK Canada

The Commercial Vehicle Safety Alliance (CVSA) aims to achieve uniformity, compatibility and reciprocity of commercial motor vehicle inspections and enforcement by certified inspectors dedicated to driver and vehicle safety. Commercial vehicles that pass a CVSA inspection are eligible for a decal representing a commitment to safety. In this work, we propose a two-step automatic CVSA decal recognition system using deep convolutional neural network architectures. The first step localizes a vehicle's windshield and the CVSA decal within, and classifies the decal colour. The CVSA decal is cropped and used as input to the second stage, which localizes and classifies a digit and the corner-cut of a CVSA decal. With the corner cut, colour, and digit, the system can determine the decal's date of issue. We use as our baseline the MobileDet architecture, customizing the backbone to our tasks. Our first custom architecture is larger than the baseline because it needs more representational power to detect small decals within an image. The second architecture is much smaller because digit and corner-cut recognition is a simpler task. Our custom architectures reduce processing time and exceed accuracies relative to pre-trained architectures. We implemented our models on different edge hardware accelerators (e.g. the Google Coral, Nvidia Jetsons, and Intel NCS) and compared the performance when processing a real-time video stream. Our system can predict frames at 173.31 FPS on an NVIDIA Jetson AGX Xavier with 98.5% mean average precision @ 0.5 IoU.

关键词： image recognition computer vision and image processing techniques Traffic engineering computing Neural nets

来源：评论

学校读者我要写书评

暂无评论

MSNet: A novel end-to-end single image dehazing network with multiple inter-scale dense skip-connections

引用

IET image processing 2021年第1期15卷 143-154页

作者： Yi, Qiaosi Jiang, Aiwen Deng, Xiaolin Liu, Changhong Jiangxi Normal Univ Sch Comp & Informat Engn Nanchang Jiangxi Peoples R China

Dehazing is a challenging ill-posed image restoration task. Various prior-based and learning-based methods have been proposed. Among them, end-to-end deep models achieve great success on performance improvement. However, most of them are concentrated on feature learning within the same block scale in isolation, and cannot perform associated analysis well on feature characteristics of different scales. Inter-scale information reuse which is especially beneficial to image restoration is often neglected. Therefore, in this paper, a novel end-to-end network with multiple inter-scale dense skip-connections for image dehazing is proposed. Sufficient complementary information combination is considered through dense inter-scale skip-connections among encoder and decoder block layers. Besides avoiding gradient vanishing, a kind of bottleneck residual block is proposed to control the importance of local gradients at different scales over global learning process. Extensive comparisons and ablation studies on public dehazing datasets and real-world images have been conducted. The experiment results demonstrate that the proposed novel elements can ensure more stable training process and superior testing performance with great improvements on PSNR and SSIM. Authors' haze-removal results consistently comply satisfactorily with real situations, having much higher definition and contrast without colour distortion than those from the state-of-the-art methods compared in this paper.

关键词： Optical, image and video signal processing computer vision and image processing techniques Machine learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

image compression using wavelets and JPEG2000: a tutorial

引用

ELECTRONICS & COMMUNICATION ENGINEERING JOURNAL 2002年第3期14卷 112-121页

作者： Lawson, S Zhu, J Univ Warwick Sch Engn Coventry CV4 7AL W Midlands England

The demand for higher and higher quality images transmitted quickly over the Internet has led to a strong need to develop better algorithms for the filtering and coding of such images. The introduction of the JPEG2000 compression standard has meant that for the first time the discrete wavelet transform (DWT) is to be used for the decomposition and reconstruction of images together with an efficient coding scheme. The use of wavelets implies the use of subband coding in which the image is iteratively decomposed into high- and low-frequency bands. Thus there is a need for filter pairs at both the analysis and synthesis stages. This paper aims in tutorial form to introduce the DWT, to illustrate its link with filters and filterbanks and to illustrate how it may be used as part of an image coding algorithm. It concludes with a look at the qualitative differences between images coded using JPEG2000 and those coded using the existing JPEG standard.

关键词： Integral transforms in numerical analysis tutorial image decomposition filtering subband coding high-frequency bands discrete wavelet transform filtering theory data compression Internet JPEG2000 FIR filters image coding low-frequency bands computer vision and image processing techniques image compression filterbanks image reconstruction channel bank filters transform coding discrete wavelet transforms image and video coding Filtering methods in signal processing DWT

来源：评论

学校读者我要写书评

暂无评论

Exploiting texture characteristics and spatial correlations for robustness metric of data hiding with noisy transmission

引用

IET image processing 2021年第13期15卷 3160-3171页

作者： Chen, Yanli Wang, Hongxia Wu, Hanzhou Zhou, Yonghui Zhou, Limengnan Chen, Yi Guizhou Normal Univ Sch Big Data & Comp Sci Guiyang Guizhou Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu 610065 Peoples R China Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China Univ Elect Sci & Technol China Zhongshan Inst Sch Elect & Informat Engn Zhongshan Guangdong Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu Sichuan Peoples R China

Data hiding aims to embed a secret message into a digital object such as image by slightly modifying the object content without arousing noticeable artefacts. The resultant object containing hidden information will be sent to a desired receiver via some insecure channels, e.g. images transmitted through noisy channel, social networks are vulnerable to unknown pollution or compression by a third party, which may lead the transmitted objects to be attacked such that the reconstructed message has a significant error rate. It therefore requires us to use robust embedding strategies for data hiding to realise reliable message retrieval. To this end, in this paper, a metric model to estimate the robustness of data hiding for noisy transmission based on the statistical characteristics of cover and embedding operation is presented, the former is mainly reflected by spatial frequency and texture feature, and the latter embedding operation is mainly reflected by embedding modification. The goal is to ensure that both statistical characteristics and embedding operation can be used to maximise the embedding robustness. To the best knowledge, it is the first time to estimate robustness before data hiding by a special metric model. Experimental results show that, by combining the proposed metric model in three classical data hiding methods, i.e. BPS, DE and QIM, the robustness can be significantly improved, which demonstrates its superiority and applicability.

关键词： Cryptography Optical, image and video signal processing image and video coding computer vision and image processing techniques Data security Other topics in statistics Other topics in statistics

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：