检索结果-内蒙古大学图书馆

Low-light image enhancement algorithm using a residual network with semantic information

The Journal of China Universities of Posts and Telecommunications 2022年第2期29卷 52-62,84页

作者： Duan Lian Tang Guijin Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China

Aiming to solve the poor performance of low illumination enhancement algorithms on uneven illumination images,a low-light image enhancement(LIME)algorithm based on a residual network was *** algorithm constructs a deep network that uses residual modules to extract image feature information and semantic modules to extract image semantic information from different ***,a composite loss function was also designed for the process of low illumination image enhancement,which dynamically evaluated the loss of an enhanced image from three factors of color,structure,and *** ensures that the model can correctly enhance the image features according to the image semantics,so that the enhancement results are more in line with the human visual *** results show that compared with the state-of-the-art algorithms,the semantic-driven residual low-light network(SRLLN)can effectively improve the quality of low illumination images,and achieve better subjective and objective evaluation indexes on different types of images.

关键词： image enhancement convolutional neural network(CNN) residual learning image semantics

来源：评论

学校读者我要写书评

暂无评论

Free Viewpoint Action Recognition based on Self-similarities

Free Viewpoint Action Recognition based on Self-similarities

引用

2012 IEEE 11th International Conference on Signal processing(ICSP 2012)

作者： Jiao Wang Changhong Chen Xiuchang Zhu Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781467321969

Action recognition is an important topic in computer vision and most current work focuses on view-dependent representations. In this paper, we develop a novel free viewpoint action recognition based on Self-similarity matrix (SSM), which tends to be stable across views. We choose Local Self-similarity (LSS) descriptor as our low-level feature, then SSM is calculated by computing the similarity between any pair of frame features. Each video sequence is represented using a diagonal descriptor vector extracted from the SSM. Support Vector Machines (SVM) is employed for classification. The encouraging experimental results on the public IXMAS multi-view data set demonstrate effectiveness of the proposed method.

关键词： local self-similarity descriptor self-similarity matrix diagonal feature action recognition view independent

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Stream Fusion Network for Underwater image Enhancement

引用

China communications 2024年第2期21卷 166-182页

作者： Guijin Tang Lian Duan Haitao Zhao Feng Liu Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and TelecommunicationsNanjing 210003China

Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual ***, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.

关键词： image enhancement multi-stream fusion underwater image

来源：评论

学校读者我要写书评

暂无评论

Speaker conversion using kernel non-negative matrix factorization

引用

The Journal of China Universities of Posts and Telecommunications 2017年第5期24卷 60-67页

作者： Xu Qinyu Lu Guanming Yan Jingjie Li Haibo Cheng Xiao College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu Province Key Laboratory on Image Processing and Image Communication Nanjing 210003 China

Voice conversion （VC） based on Gaussian mixture model （GMM） is the most classic and common method which converts the source spectrum to target spectrum. However this method is prone to over-fitting because of its frame-by-frame conversion. The VC with non-negative matrix factorization （NMF） is presented in this paper, which can keep spectrum from over-fitting by adjusting the size of basis vector （dictionary）. In order to realize the non-linear mapping better, kernel NMF （KNMF） is adopted to achieve spectrum mapping. In addition, to increase the accuracy of conversion, KNMF combined with GMM （GKNMF） is also introduced into VC. In the end, KNMF, GKNMF, GMM, principal component regression （PCR）, PCR combined with GMM （GPCR）, partial least square regression （PLSR）, NMF correlation-based frequency warping （NMF-CFW） and deep neural network （DNN） methods are compared with each other. The proposed GKNMF gets better performance in both objective evaluation and subjective evaluation.

关键词： VC kemel NMF spectrum mapping

来源：评论

学校读者我要写书评

暂无评论

Stereo Matching based on Robust Likelihoods and MST Leveraged Smoothness Priors

Stereo Matching based on Robust Likelihoods and MST Leverage...

引用

2012 IEEE 11th International Conference on Signal processing(ICSP 2012)

作者： Tianliang Liu Liang Wang Xiuchang Zhu Jiangsu Provincial Key Lab of Image Processing and Image Communication College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781467321969

This paper proposes a global stereo correspondence using robust matching likelihoods and minimum spanning tree （MST） leveraged smooth priors in a probabilistic graphical model framework. The matching likelihoods of the stereo correspondence can be robustly constructed as data term by aggregating initial matching costs from Weber local descriptors using an unsymmetrical guided filtering in a linear model. The disparity priors are devised as smooth term to characterize the smoothness constraints leveraged by the MST structure. The presented stereo approach provides an effective and efficient way to reflect robust visual dissimilarity and resolve local and regional discontinuities. Experiments demonstrate that the proposed global stereo matching method can produce piecewise smooth, accurate and dense disparity map, while removing effectively the visual ambiguity of the stereo matching problem.

关键词： stereo vision Markov random field Weber descriptor minimun spanning tree QPBO optimization

来源：评论

学校读者我要写书评

暂无评论

Low-light color image enhancement based on NSST

引用

The Journal of China Universities of Posts and Telecommunications 2019年第5期26卷 41-48页

作者： Wu Xiaochu Tang Guijin Liu Xiaohua Cui Ziguan Luo Suhuai Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and TelecommunicationsNanjing 210003China School of Electrical Engineering and Computing the University of NewcastleNSW 2308Australia

In order to improve the visibility and contrast of low-light images and better preserve the edge and details of images,a new low-light color image enhancement algorithm is proposed in this *** steps of the proposed algorithm are described as ***,the image is converted from the red,green and blue(RGB)color space to the hue,saturation and value(HSV)color space,and the histogram equalization(HE)is performed on the value ***,non-subsampled shearlet transform(NSST)is used on the value component to decompose the image into a low frequency sub-band and several high frequency ***,the low frequency sub-band and high frequency sub-bands are enhanced respectively by Gamma correction and improved guided image filtering(IGIF),and the enhanced value component is formed by inverse NSST ***,the image is converted back to the RGB color space to obtain the enhanced *** results show that the proposed method not only significantly improves the visibility and contrast,but also better preserves the edge and details of images.

关键词： non-subsampled shearlet transform guided image filtering low-light image enhancement the HSV color space

来源：评论

学校读者我要写书评

暂无评论

Flicker-Free Adaptive Enhancement for Infrared Video 13

Flicker-Free Adaptive Enhancement for Infrared Video

引用

13th International Conference on Wireless communications and Signal processing, WCSP 2021

作者： Wei, Caixia Gan, Zongliang Nanjing University of Posts and Telecommunications Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing China

ISBN: (纸本)9781665407854

Infrared videos often suffer from low contrast and insufficient texture. In order to improve poor visual effect, a novel infrared video enhancement method is proposed, which contains intra-frame brightness enhancement and inter-frame brightness continuity adjustment. In intra-frame brightness enhancement, it has two steps including global contrast enhancement and local details enhancement. To global contrast enhancement, the processed image contrast by geometric distribution, and it is incorporated into an optimization problem with a sorted histogram of each frame to yield a modified histogram. To local details enhancement, after Retinex decomposition, the reflection component is magnified by boundary preserving filter, and this strategy can effectively suppress noise in relatively uniform regions. Furthermore, to maintain inter-frame brightness continuity, adaptive parameters are introduced through optical flow to control the combination ratio of geometric distribution histogram, in which the enhancement degree of each frame can be adjusted according to inter-frame similarity and the moving region are enhanced adaptively according to the change of each frame. Experimental results demonstrate that proposed algorithm can effectively enhance the contrast and detail of infrared video, and improve the visual effect in subjective and objective quality evaluation. © 2021 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A novel improved binarized normed gradients based objectness measure through the multi-feature learning 8th

A novel improved binarized normed gradients based objectness...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Zhao, Danfeng Hu, Yuanyuan Gan, Zongliang Chen, Changhong Liu, Feng Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219776

In this paper, we propose a novel improved binarized normed gradients (BING) objectness method based on the multi-feature boosting learning. A series of difference of gaussians (DoG) of the images with given parameters are used for the feature extraction stage, since the image DoG filter can better describe objects border. In addition, in training phase, the classifier can adaptively combine the features from different scales and different frequency components. Moreover, since the norm of the feature gradients is a simple 64D feature in the proposed framework, the computational complexity of the algorithm is in the same level compared with the BING measure. Experiments on the challenging PASCAL VOC 07 dataset show that the proposed method can not only achieve higher detection rate and average score than some current related objectness measures, but also lead to a very competitive accuracy of locating objects, even in some difficult cases. © Springer International Publishing Switzerland 2015.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Edge directed single image super resolution through the learning based gradient regression estimation 8th

Edge directed single image super resolution through the lear...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Si, Dandan Hu, Yuanyuan Gan, Zongliang Cui, Ziguan Liu, Feng Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219622

Single image super resolution (SR) aims to estimate high resolution (HR) image from the low resolution (LR) one, and estimating accuracy of HR image gradient is very important for edge directed image SR methods. In this paper, we propose a novel edge directed image SR method by learning based gradient estimation. In proposed method, the gradient of HR image is estimated by using the example based ridge regression model. Recognizing that the training samples of the given sub-set for regression should have similar local geometric structure based on clustering, we employ high frequency of LR image patches with removing the mean value to perform such clustering. Moreover, the precomputed projective matrix of the ridge regression can reduce the computational complexity further. Experimental results suggest that the proposed method can achieve better gradient estimation of HR image and competitive SR quality compared with other SR methods. © Springer International Publishing Switzerland 2015.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Robust face hallucination via similarity selection and representation 8th

Robust face hallucination via similarity selection and repre...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Liu, Feng Yin, Ruoxuan Gan, Zongliang Chen, Changhong Tang, Guijin Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783319219684

Face image super resolution, also referred to as face hallucination, is aiming to estimate the high-resolution (HR) face image from its low-resolution (LR) version. In this paper, a novel two-layer face hallucination method is proposed. Different from the previous SR methods, by applying global similarity selecting, the proposed approach can narrow the scope of samples and boost the reconstruction speed. And the local similarity representation step make the method have better ability to suppress noise for applications under severe condition. As a general framework, other useful algorithms can also be incorporated into it conveniently. Experiments on commonly used face database demonstrate our scheme has better performance, especially for noise face image. © Springer International Publishing Switzerland 2015.

关键词： Computers

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：