检索结果-内蒙古大学图书馆

Wavelet-based image denoising with the normal inverse Gaussian prior and linear MMSE estimator

IET image processing 2008年第4期2卷 203-217页

作者： Bhuiyan, M. I. H. Ahmad, M. O. Swamy, M. N. S. Concordia Univ Dept Elect & Comp Engn Ctr Commun & Signal Proc Montreal PQ H3G 1M8 Canada

A new spatially adaptive wavelet-based method is introduced for reducing noise in images corrupted by additive white Gaussian noise. It is shown that a symmetric normal inverse Gaussian distribution is highly suitable for modelling the wavelet coefficients. In order to estimate the parameters of the distribution, a maximum-likelihood-based technique is proposed, wherein the Gauss-Hermite quadrature approximation is exploited to perform the maximisation in a computationally efficient way. A Bayesian minimum mean-squared error (MMSE) estimator is developed utilising the proposed distribution. The variances corresponding to the noise-free coefficients are obtained from the Bayesian estimates using a local neighbourhood. A modified linear MMSE estimator that incorporates both intra-scale and inter-scale dependencies is proposed. The performance of the proposed method is studied using typical noise-free images corrupted with simulated noise and compared with that of the other state-of-the-art methods. It is shown that the proposed method gives higher values of the peak signal-to-noise ratio compared with most of the other denoising techniques and provides images of good visual quality. Also, the performance of the proposed method is quite close to that of the state-of-the-art Gaussian scale mixture (GSM) method, but with much less complexity.

关键词： Bayesian minimum mean-squared error estimator Bayesian estimates adaptive estimation maximisation symmetric normal inverse Gaussian distribution adaptive wavelet-based method noise-free coefficients normal inverse Gaussian prior Gaussian scale mixture computer vision and image processing techniques Other topics in statistics linear MMSE estimator noise-free images Optical, image and video signal processing Mathematical analysis Integral transforms visual quality Gauss-Hermite quadrature approximation maximum likelihood estimation signal-to-noise ratio Bayes methods Gaussian distribution wavelet coefficients wavelet transforms Interpolation and function approximation (numerical analysis) parameter estimation inverse problems maximum-likelihood-based technique image denoising computational complexity additive white Gaussian noise least mean squares methods wavelet-based image denoising

来源：评论

学校读者我要写书评

暂无评论

On learning based compressed sensing for high resolution image reconstruction

引用

IET image processing 2021年第2期15卷 393-404页

作者： Islam, Sheikh Rafiul Maity, Santi P. Ray, Ajoy Kumar Indian Inst Engn Sci & Technol Dept Informat Technol Howrah 711103 W Bengal India Indian Inst Technol Dept Elect & Elect Commun Engn Kharagpur W Bengal India

Compressed sensing (CS) or compressive sampling has shown an enormous potential to reconstruct a signal from its highly under-sampled observations. A high dimensional image processing system can adopt the CS paradigm to reduce the storage and the transmission burden. However, a large sensing system (matrix) is required to capture high dimensional images. The CS reconstruction algorithms demand heavy computational requirement due to the use of large sensing matrix. It sometimes becomes impractical to implement a sensing system of the desired size due to the limited access to the CPU memory. To address this issue, the present work proposes a deep learning based CS framework that uses a convolutional neural network to enable capturing of a high dimensional image by utilizing a multi-layer subsampling and filtering operations. The proposed approach uses another convolutional neural network that reconstructs the original image without depending on the sensing network at a significantly reduced computational cost. Extensive simulation results show that the proposed method reconstructs a high dimensional image with an improved PSNR value by 1.5 +/- 0.63 dB, SSIM value by 0.04 +/- 0.02 and FSIM value by 0.02 +/- 0.02 compared to the other state-of-the-art methods in less than 1.4 seconds.

关键词： image and video coding computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

New multi-resolution image stitching with local and global alignment

引用

IET computer vision 2010年第4期4卷 231-246页

作者： Fang, X. Luo, B. Zhao, H. Tang, J. Zhai, S. Anhui Univ Key Lab Intelligent Comp & Signal Proc MOE Hefei 230039 Peoples R China

Three main problems affect the alignment quality of existing studies on multi-resolution image stitching: (i) the initial motion obtained is sometimes incorrect;(ii) the local motion is hard to be estimated and (iii) the widely used global bundle adjustment is difficult to converge. The authors propose a new multi-resolution image mosaic method that combines three corresponding tactics to solve these problems. The first problem is solved by introducing an additional motion refinement strategy, which consists of the low-contrast filter and RANSAC. The former removes flatly textured surface pixels and thus eliminates the falsely matched features. The latter removes outliers and finds a robust initial motion for the next layer. The second problem is resolved by a new iteratively local registration method, which calibrates the current camera parameters based on those from previous image with robust non-linear optimisation methods. It improves the convergence efficiency and eliminates error minimisation. For the last problem, the authors introduce a five-parameter bundle adjustment method based on the axis-angle decomposition of the rotation matrix. Comparing with existing bundle adjustment methods, this method is more stable because of an accurate and simple rotation decomposition. The authors show the efficiency of the method with qualitative and quantitative experiments.

关键词： local alignment image mosaic method multiresolution image stitching Resolution of optical images global alignment image processing and restoration Optical, image and video signal processing computer vision and image processing techniques five-parameter bundle adjustment method iteratively local registration method image resolution image segmentation

来源：评论

学校读者我要写书评

暂无评论

Learn from Object Counting: Crowd Counting with Meta-learning

引用

IET image processing 2021年第14期15卷 3543-3550页

作者： Zan, Changtong Liu, Baodi Guan, Weili Zhang, Kai Liu, Weifeng China Univ Petr East China Qingdao Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian Peoples R China Monash Univ Fac Informat Technol Clayton Campus Clayton Vic Australia

The objective of crowd counting is to learn a counter that can estimate the number of people in a single image. So far, most of the proposed work evaluates the crowd density by fitting the constructed density map corresponding to the sample. The performance of those algorithms depends on a large amount of carefully prepared data. However, a significant problem with crowd data sets is the difficulty of labeling. To address such a situation, utilizing object counting data in few-shot scenes is considered and an efficient algorithm to extract the meta-information is proposed, thus improving the accuracy and convergence rate of the crowd counting tasks. Specifically, the counting network is trained with only object counting tasks constructed on different domains during the meta-training phase. Then, the meta-counter is testing on crowd counting tasks in the meta-testing stage. Experimentally, it is demonstrated that the above way improves the converge rate and accuracy of crowd counting tasks on three crowd counting datasets when meta-training on ten-type object counting tasks.

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

来源：评论

学校读者我要写书评

暂无评论

Global weighted average pooling network with multilevel feature fusion for weakly supervised brain tumor segmentation

引用

IET image processing 2023年第2期17卷 418-427页

作者： Li, Zi-Wei Xuan, Shi-Bin He, Xue-Dong Wang, Li Guangxi Minzu Univ Sch Artificial Intelligence Daxue East Rd 188 Nanning Peoples R China Guangxi Key Lab Hybtid Computat & IC Design Anal Nanning Peoples R China

Medical image segmentation plays a vital role in computer-aided diagnosis and intelligent medical treatment. It can preprocess medical images to help doctors better diagnose diseases. Class activation map (CAM) is an important technology in weakly supervised segmentation, which can achieve image segmentation without pixel-level label training. This technology can well meet the needs of medical image segmentation. However, CAM obtaining is still unperfect due to global average pooling (GAP). GAP will cause important and non-important regions to be given equal attention during the training process. So, CAM cannot demarcate the boundary of the target regions well. In order to solve this problem, a global weighted average pooling network fusing the grayscale information of medical images is proposed. The proposed network can solve the problem that GAP has the same concern for important regions and non-important regions of the feature map, because the different weights can be learned for different positions of the feature map before the GAP in the proposed model. At the same time, because of the grayscale difference between the tumor area and the non-tumor area in the brain tumor image, the low-level grayscale information of the medical image is fused with the high-level semantic information extracted by the network to learn the weights. This operation gives full play to the advantages of feature maps of different levels. The experiment results on the popular medical image dataset BraTS2019 show that the proposed method can well improve the performance of CAM and help CAM fit the boundaries of objects. Meanwhile, in the DSC evaluation, the proposed method achieves a score of 64.1%, which is a 4.6% improvement over a recent research method.

关键词： global average pooling Biology and medical computing supervised learning image segmentation feature extraction medical image processing diseases multilevel feature fusion pixel-level label training target regions global weighted average pooling network CAM obtaining brain tumor image high-level semantic information weakly supervised brain tumor segmentation Neural nets medical image segmentation Optical, image and video signal processing image fusion computer vision and image processing techniques intelligent medical treatment feature map popular medical image dataset BraTS weakly supervised segmentation nontumor area image recognition computer-aided diagnosis brain low-level grayscale information class activation map nonimportant regions Patient diagnostic methods and instrumentation important regions tumours Biomedical measurement and imaging

来源：评论

学校读者我要写书评

暂无评论

Foreground segmentation for dynamic scenes with sudden illumination changes

引用

IET image processing 2012年第5期6卷 606-615页

作者： Li, J. Miao, Z. Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China

Foreground segmentation is a very difficult task in dynamic background, which is common in real-world environments, caused by for example waving foliage, rippling water or illumination changes owing to light switching etc. A large number of methods for foreground segmentation in dynamic background have been proposed in the past decades, but most of them can only handle repetitive movements or gradual changes in background, and fail when sudden illumination changes occur. This study proposes a new method, which can deal with both repetitive movements and gradual/sudden illumination changes. The authors use a two-layer Gaussian mixture model to represent the background under different lighting conditions and formulate a joint posterior function of background state and segmentation based on the learned model. Given a new image, the background state and foreground segmentation are simultaneously optimised in a Bayesian perspective using a nested two-layer optimisation. The authors test their method on several image sequences and compare the results qualitatively and quantitatively with some state-of-the-art methods to demonstrate the effectiveness of the method.

关键词： two-layer Gaussian mixture model gradual-sudden illumination change computer vision and image processing techniques lighting waving foliage background state light switching dynamic scene foreground segmentation Bayesian perspective Gaussian processes Optical, image and video signal processing image segmentation rippling water nested two-layer optimisation joint posterior function image sequences Bayes methods Other topics in statistics image sequence

来源：评论

学校读者我要写书评

暂无评论

image measurement of body position during side-approach transfer motion

引用

IET image processing 2011年第5期5卷 402-409页

作者： Tanimoto, Y. Nanba, K. Tokuhiro, A. Ukida, H. Yamamoto, H. Kibikogen Rehabil Ctr Employment Injuries Dept Med Engn Okayama Japan Univ Tokushima Fac Engn Tokushima 770 Japan

In order to clarify the side-transfer ability of spinal cord injury (SCI) patients, it is necessary to analyse the side-transfer motion of SCI patients. This study describes a method for easy detection of the body position during the transfer motion using a simple human body model and side- and front-view images taken by using two charge-coupled device (CCD) cameras. The proposed simple human body model consists of five cuboids, nine columns and two elliptical cylinders. First, the wheelchair size was measured at the 11 points on its right side using a side- view image. Next, the wheelchair position was detected from the centre position of the right back wheel, and the gap angle between the platform and the wheelchair was detected from the edge position of both back wheels on the side- and front-view images. The positions of the 11 parts of the body model were estimated by matching each part to the side- and front-view images, and then the gravity centre of the body was calculated. Finally, the two images and the centre of gravity calculated every 1 s during the transfer motion were used to realise the movement of the body during the transfer motion.

关键词： image measurement Patient diagnostic methods and instrumentation CCD image sensors elliptical cylinders image recognition Biology and medical computing computer vision and image processing techniques spinal cord injury patients charge coupled device cameras time 1 s body position detection CCD cameras SCI patients gap angle human body model edge detection medical image processing Biomedical measurement and imaging centre of gravity calculation image sensors side-transfer motion wheelchair position edge position detection

来源：评论

学校读者我要写书评

暂无评论

A keypoint-based object detection method with wide dual-path backbone network and attention modules

引用

IET image processing 2021年第8期15卷 1800-1813页

作者： Qu, Zhong Zhang, Run Bao, Kang-hua Chongqing Univ Posts & Telecommun Coll Comp Sci & Technol 2 Chongwen Rd Chongqing 400065 Peoples R China Southwest Comp Co Ltd Inst Informat Technol 1 Guangdian Rd Chongqing Peoples R China

Keypoint-based object detection is one of the most efficient and speedy methods at present, yet its performance is often worse than the anchor-based method. Without prior settings in the keypoint-based method, the huge search space of the keypoints results in the high recall but low precision. In this paper, the wide dual-path backbone network is introduced as a feature extractor to extract richer original information, which has fewer parameters and better classification performance. Then, the attention fusion module is designed to effectively fuse the dual-path with the consideration of the respective advantages of the residual-path and the densely connected path. In order to provide more accurate pixel-level information for keypoint prediction, the upsample dual-attention module is proposed to recover the spatial size of the feature map, which integrates multi-scale of channel-wise and spatial attention. Compared with other state-of-the-art detectors, this method has achieved accuracy-efficiency results with fewer parameters, lower FLOPs, and smaller model size. Experimental results show that the proposed wide dual-path backbone network has achieved 4.98% top1-error on the CIFAR-10 classification dataset. On the PASCAL VOC object detection dataset, this model has achieved an accuracy-efficiency tradeoff result of 78.3% mAP at the speed of 41 FPS.

关键词： image recognition Optimisation techniques Sensor fusion computer vision and image processing techniques Combinatorial mathematics Optimisation techniques Combinatorial mathematics Neural nets

来源：评论

学校读者我要写书评

暂无评论

DuGAN: An effective framework for underwater image enhancement

引用

IET image processing 2021年第9期15卷 2010-2019页

作者： Zhang, Huiqing Sun, Luyu Wu, Lifang Gu, Ke Minist Educ Engn Res Ctr Digital Commun Beijing 100124 Peoples R China

Underwater image enhancement is an important low-level vision task with much attention of community. Clear underwater images are helpful for underwater operations. However, raw underwater images often suffer from different types of distortions caused by the underwater environment. To solve these problems, this paper proposes an end-to-end dual generative adversarial network (DuGAN) for underwater image enhancement. The images processed by existing methods are taken as training samples for reference, and they are segmented into clear parts and unclear parts. Two discriminators are used to complete adversarial training toward different areas of images with different training strategies, respectively. The proposed method is able to output more pleasing images than reference images benefit by this framework. Meanwhile, to ensure the authenticity of the enhanced images, content loss, adversarial loss, and style loss are combined as loss function of our framework. This framework is easy to use, and the subjective and objective experiments show that excellent results are achieved compared to those methods mentioned in the literature.

关键词： Optical, image and video signal processing computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

Pain expression assessment based on a locality and identity aware network

引用

IET image processing 2021年第12期15卷 2948-2958页

作者： Xin, Xuwu Li, Xiaowu Yang, Shengfu Lin, Xiaoyan Zheng, Xin Hosp Shantou Univ Affiliated Hosp 2 Med Coll Shantou 515000 Peoples R China Jinan Univ Affiliated Hosp 1 Guangzhou Peoples R China Joint Shantou Int Eye Ctr Shantou Univ & Chinese Shantou Peoples R China

In clinical medicine, the pain feeling is a significant indicator for the medical condition of patients. Of late, automatic pain assessment methods have received more and more interests. Many researchers proposed corresponding methods and achieved impressive results. However, they always ignore the locality and individual differences of painful expression. Therefore, a locality and identity aware network (LIAN) for pain assessment is presented here. Concretely, for the locality characteristic, a locality aware module consisting of a two-branch structure, feature and attention branches, is presented. The former learns pain features by a deep network, while the latter guides the pain features to focus on the discriminational regions of pain. As for the individual differences, an identity aware module with a multi-task method is proposed to represent identity-related information to achieve identity-invariant pain assessment. Extensive experiments on public databases show the superiority of LIAN in pain assessment.

关键词： image recognition computer vision and image processing techniques Biology and medical computing

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：