检索结果-内蒙古大学图书馆

IEEE visual communications and image processing (VCIP)

作者： Davide Cozzolino Diego Gragnaniello Giovanni Poggi Luisa Verdoliva University Federico II of Naples Italy

ISBN: (纸本)9781728173221

The ever higher quality and wide diffusion of fake images have spawn a quest for reliable forensic tools. Many GAN image detectors have been proposed, recently. In real world scenarios, however, most of them show limited robustness and generalization ability. Moreover, they often rely on side information not available at test time, that is, they are not universal. We investigate these problems and propose a new GAN image detector based on a limited sub-sampling architecture and a suitable contrastive learning paradigm. Experiments carried out in challenging conditions prove the proposed method to be a first step towards universal GAN image detection, ensuring also good robustness to common image impairments, and good generalization to unseen architectures.

关键词： Training image coding visual communication Forensics Detectors Robustness

来源：评论

学校读者我要写书评

暂无评论

image Enhancement of Finger Vein Patterns Based on the Guided Filter

Image Enhancement of Finger Vein Patterns Based on the Guide...

引用

7th International Conference on communications, Signal processing, and Systems (CSPS)

作者： Zhan, Tao Ma, Hui Hu, Na Heilongjiang Univ Coll Elect Engn Harbin 150080 Peoples R China

ISBN: (纸本)9789811365041;9789811365034

To solve the problem that image enhancement of finger vein patterns based on traditional filtering methods fails to intuitively highlight the feature of edge protection, the experimental study model based on the guided filter is proposed. Through adding the comparison experiment between guided filter and bilateral filter, and doing the binary processing to the finger vein image after the process of the guided filtering and bilateral filtering, it can be found that some noises exist around the vein texture. In order to reduce or eliminate the interference, a traditional average filtering method is applied for denoising, which not only highlights the vein texture details but eliminates the interference in the post-processing, and at the same time, adjusting the filter parameters will cause a significant impact on the enhancement of finger vein image. A comparison experiment in false recognition rate between two filtering algorithms is conducted, and visual and numerical evaluations are performed on finger vein image after the process of enhancement and binarization;the result indicates that the guided filter has better edge protection feature and lower false recognition rate than the bilateral filter.

关键词： processing Guided filter Finger vein image enhancement Bilateral filter Binary processing Median filter

来源：评论

学校读者我要写书评

暂无评论

SdBAN: Salient Object Detection Using Bilateral Attention Network With Dice Coefficient Loss

引用

IEEE ACCESS 2020年 8卷 104357-104370页

作者： Kang, Donggoo Park, Sangwoo Paik, Joonki Chung Ang Univ Dept Image Seoul 06974 South Korea

visual attention plays an important role in saliency detection by highlighting meaningful context regions. In this paper, we present a novel saliency detection method using a bilateral attention network. The proposed network consists of two branches: i) a spatial path using an encoder-decoder structure to learn spatial cues and ii) a context path using an attention mechanism to learn contextual cues. The feature aggregation module is finally used to predict salient objects by concatenating the cues. To optimize the weights of the network in the sense of minimizing the class imbalance problem, we minimize the dice coefficient loss together with the classical cross-entropy loss. The proposed network can predict salient regions in an end-to-end manner without post-processing. Experimental results show that the proposed network achieved better performance than existing state-of-the-art methods in most cases. Furthermore, the proposed network takes only 0.03 seconds to process a image. The code for the proposed method can be found at the following

关键词： Salient object detection deep learning dice coefficient attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Blind image Super-Resolution using Iterative Networks

Deep Learning-Based Blind Image Super-Resolution using Itera...

引用

IEEE visual communications and image processing (VCIP)

作者： Asfand Yaar Hasan F. Ates Bahadir K. Gunturk School of Engineering and Natural Sciences Istanbul Medipol University Turkey

ISBN: (纸本)9781728173221

Deep learning-based single image super-resolution (SR) consistently shows superior performance compared to the traditional SR methods. However, most of these methods assume that the blur kernel used to generate the low-resolution (LR) image is known and fixed (e.g. bicubic). Since blur kernels involved in real-life scenarios are complex and unknown, per-formance of these SR methods is greatly reduced for real blurry images. Reconstruction of high-resolution (HR) images from randomly blurred and noisy LR images remains a challenging task. Typical blind SR approaches involve two sequential stages: i) kernel estimation; ii) SR image reconstruction based on estimated kernel. However, due to the ill-posed nature of this problem, an iterative refinement could be beneficial for both kernel and SR image estimate. With this observation, in this paper, we propose an image SR method based on deep learning with iterative kernel estimation and image reconstruction. Simulation results show that the proposed method outperforms state-of-the-art in blind image SR and produces visually superior results as well.

关键词： Deep learning visual communication Simulation Superresolution Estimation Noise measurement Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Flame image Segmentation Algorithm Based on Motion and Color Saliency

Flame Image Segmentation Algorithm Based on Motion and Color...

引用

7th International Conference on communications, Signal processing, and Systems (CSPS)

作者： Li, Yuyan Wang, Lin Dalian Maritime Univ Acad Informat Sci & Technol Dalian 116026 Peoples R China

ISBN: (纸本)9789811365041;9789811365034

This paper proposed a flame segmentation algorithm based on the saliency of motion and color. First, feature point detection is performed on the video image using the scale-invariant feature transform (SIFT) algorithm, and the optical flow field of moving object in the adjacent frame is acquired by the optical flow method. According to the optical flow vector difference between the target pixel point and the surrounding neighborhood pixels, the motion saliency map is obtained based on the Munsell color system. Then, the LSI flame color statistical model based on the Lab and HSI space is used to extract color saliency map of video images. Finally, under the Bayes framework, the motion saliency map and the color saliency map are fused in an interactive manner to obtain the final flame segmentation map. Experimental results show that the proposed algorithm can effectively segment the flame image in different scenarios.

关键词： visual saliency Flame segmentation Optical flow LSI color statistics model

来源：评论

学校读者我要写书评

暂无评论

image Super-Resolution Based on Multi-scale Fusion Network

Image Super-Resolution Based on Multi-scale Fusion Network

引用

7th International Conference on communications, Signal processing, and Systems (CSPS)

作者： Lin, Leping Huang, Huiling Ouyang, Ning Guilin Univ Elect Technol Key Lab Cognit Radio & Informat Proc Minist Educ Guilin 541004 Guangxi Peoples R China Guilin Univ Elect Technol Sch Informat & Commun Guilin 541004 Guangxi Peoples R China

ISBN: (纸本)9789811365041;9789811365034

It is important and necessary to obtain high-frequency information and texture details in the image reconstruction applications, such as image super-resolution. Hence, it is proposed the multi-scale fusion network (MCFN) in this paper. In the network, three pathways are designed for different receptive fields and scales, which are expected to obtain more texture details. Meanwhile, the local and global residual learning strategies are employed to prevent overfitting and to improve reconstruction quality. Compared with the classic convolutional neural network-based algorithms, the proposed method achieves better numerical and visual effects.

关键词： Multi-pathways Residual learning Multi-scale Receptive field Texture details

来源：评论

学校读者我要写书评

暂无评论

Reduced-Reference Stereoscopic image Quality Assessment Based on Entropy of Gradient Primitives 5

Reduced-Reference Stereoscopic Image Quality Assessment Base...

引用

5th IEEE International Conference on Signal and image processing, ICSIP 2020

作者： Ma, Jian Zhao, Xinxin Xu, Youxin Anhui University School of Internet China Anhui Xinhua University School of Electronics and Communications Engineering China Marvell Technology Group Ltd. Bermuda

ISBN: (纸本)9781728168968

Stereoscopic image quality assessment (SIQA) has always been challenging due to the remarkable distinction between human monocular and binocular vision. This paper proposes a novel gradient-based dictionary learning method for SIQA, which effectively integrates the gradients are sparser than the image itself. Specifically, we first compute the gradient maps of each view image of stereopair by applying contrast sensitivity of human visual system (HVS) and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. Afterwards, the binocular perceptual information of gradient (GBPI) is represented by the distribution statistics of visual primitives in gradient maps of left and right views' images, which are extracted by sparse representation. Furthermore, the entropy of gradient maps of each views' images are utilized to represent monocular cue. Their mutual information is used to represent binocular cue. The difference of the reference and distorted images' GBPIs is taken as quality-ware features. Finally, the kernel ridge regressing (KRR) is utilized to simulate a nonlinear relationship between the quality-ware features and human opinions. The performance of the proposed metric is evaluated over the LIVE 3D phase ii asymmetric datasets, and shown to be competitive with the state-of-the-art SIQA algorithms. © 2020 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Systems in Math Classroom Through Computer Vision Traditional Techniques 1st

Face Recognition Systems in Math Classroom Through Computer ...

引用

1st International Conference on Applied Technologies (ICAT)

作者： Granda, Luis Barba-Guaman, Luis Torres-Carrion, Pablo Cordero, Jorge Univ Tecn Particular Loja Grp Invest Inteligencia Artificial Aplicada Loja Ecuador

ISBN: (纸本)9783030425203;9783030425197

The methods and techniques of detection of the human face and facial recognition have presented a great impulse in recent years, thanks to the advance in areas such as artificial vision and machine learning. Although deep neural network techniques are in vogue, traditional techniques allow you to create applications that do not consume many resources from computing devices. In this research, we present a facial recognition system that implements the Eigenfaces method, developed in C # of Microsoft visual Studio and open-source video processing libraries such as OpenCV as EmguCV. The application is divided into two sections: the first called register where, through an integrated camera, images of the user's face or other means such as video and stored images are captured, and the second section is known as recognition where the user is compared with all the records of the data set, indicating whether this is registered and the recognition percentage. The project was implemented with a universe of the size of twenty-five users, of which six are men (24%) and nineteen are women (76%), developing tests for five weeks.

关键词： Facial recognition Computer vision Eigenfaces image processing

来源：评论

学校读者我要写书评

暂无评论

Stereo image quality assessment based on sparse binocular fusion convolution neural network 34

Stereo image quality assessment based on sparse binocular fu...

引用

34th IEEE International Conference on visual communications and image processing, VCIP 2019

作者： Li, Sumei Han, Xu Zubair, Muhammad Ma, Shuai Tianjin University School of Electrical and Information Engineering Tianjin China Tianjin University School of Electrical and Information Engineering Pakhtunkhwa Pakistan

ISBN: (纸本)9781728137230

In this paper, a sparse binocular fusion convolution neural network is proposed to evaluate the quality of stereo image. In order to simulate the long-Term fusion and processing of the left and right views in the brain visual pathway, the network combines the two views of the stereo image four times, and the information processing is carried out through convolution together with the fusion operation. In addition, in order to overcome the computational-intensive and memory-intensive problems of convolution neural networks, a structural sparsity learning (SSL) method is used to regularize the proposed convolution neural network. The experimental results demonstrate that our proposed method performs effectively and efficiently. And the proposed method can achieve 2.0× speedups on LIVE I database and 2.3× speedup on LIVE ii database on the basis of improved performance. © 2019 IEEE.

关键词： Binoculars

来源：评论

学校读者我要写书评

暂无评论

Comparison of Facial Emotion Recognition Based on image visual Features and EEG Features 4th

Comparison of Facial Emotion Recognition Based on Image Visu...

引用

4th International Conference on Cognitive Systems and Information processing (ICCSIP)

作者： Long, Yanfang Wanzeng, Kong B. Ling, Wenfen Yang, Can Zhu, Jieyong Hangzhou Dianzi Univ Hangzhou 310018 Zhejiang Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (纸本)9789811379864;9789811379857

Automatic facial emotion recognition plays an important role in human-computer interaction. Although humans can recognize emotions with little or no effort, reliable emotion recognition by machines is always a challenge. To explore the doubt that whether machines can discriminate better than humans or not, we proposed two different ideas about facial emotion recognition. One is based on image visual features, the other is based on EEG signals which were recorded when the subject is watching facial emotion pictures. Correspondingly, the Deep Convolutional Neural Network (DCNN) model is adopted to enable the machine to learn visual features from facial emotion pictures automatically. The Gated Recurrent Unit (GRU) model is used to extract specific emotional EEG features from EEG signals. These two methods were verified on the Chinese Facial Affective Picture System (CFAPS) and our developed Emotion EEG data (EMOT), and the recognition performance based on EEG features was found to be significantly better than the image visual.

关键词： Deep learning EEG Facial emotion recognition

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：