检索结果-内蒙古大学图书馆

IEEE visual communications and image processing (VCIP)

作者： Peng Ye Yongfang Wang Yumeng Xia School of Communication and Information Engineering Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

Saliency prediction can be treated as the activity of the human visual system (HVS). The most effective method should highly approximate the response of HVS to the perceived information. Motivated by that orientation selectivity (OS) mechanism occuring in primary visual cortex (PVC) tells us how the HVS extracts visual information for scene understanding, we propose a novel saliency model by combining an orientation selectivity based local feature called "excitement" map and a visual acuity based global feature called "acuity" map. Further, a saliency augmented operator based on visual error sensitivity is designed to enhance the saliency map. Experimental results on three benchmark databases demonstrate the superior performance of the proposed method compared to ten classical/ state-of-the-art algorithms.

关键词： visualization Feature extraction Sensitivity Predictive models image edge detection Computational modeling visual systems

来源：评论

学校读者我要写书评

暂无评论

SUPER-RESOLUTION BASED ON BACK-PROJECTION OF INTERPOLATED image 12

SUPER-RESOLUTION BASED ON BACK-PROJECTION OF INTERPOLATED IM...

引用

12th International conference on Advanced Technologies for communications (ATC)

作者： Kiatpapan, Sawiya Yamaguchi, Takuro Ikehara, Masaaki Keio Univ Grad Sch Sci & Technol Dept Elect & Elect Engn Tokyo Japan

ISBN: (纸本)9781728123929

image upscaling to obtain high quality digital image is one of the active research topics as it is applicable in the consumer electronics industries. Traditional image upscaling techniques have low computational complexity and applicable for real-time processing, but reconstructed image often contains artifacts and undesirable visual effect. The relationship between image interpolation and super-resolution leads our assumption that the interpolated image can be further optimized and may be considered as a part of super-resolution algorithm. In this paper, we propose a new image super-resolution method to combine fast image interpolation with iterative back-projection. This method does not require any external pre-trained datasets and has low computation time while the quality of the reconstructed image can be measured up to the high programming complexity methods such as the dictionary and deep convolutional neural networks.

关键词： super-resolution interpolation based back-projection

来源：评论

学校读者我要写书评

暂无评论

No-Reference Stereoscopic image Quality Assessment Based On visual Attention Mechanism

No-Reference Stereoscopic Image Quality Assessment Based On ...

引用

IEEE visual communications and image processing (VCIP)

作者： Sumei Li Ping Zhao Yongli Chang School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In this paper, we proposed an optimized model based on the visual attention mechanism(VAM) for no-reference stereoscopic image quality assessment (SIQA). A CNN model is designed based on dual attention mechanism (DAM), which includes channel attention mechanism and spatial attention mechanism. The channel attention mechanism can give high weight to the features with large contribution to final quality, and small weight to features with low contribution. The spatial attention mechanism considers the inner region of a feature, and different areas are assigned different weights according to the importance of the region within the feature. In addition, data selection strategy is designed for CNN model. According to VAM, visual saliency is applied to guide data selection, and a certain proportion of saliency patches are employed to fine tune the network. The same operation is performed on the test set, which can remove data redundancy and improve algorithm performance. Experimental results on two public databases show that the proposed model is superior to the state-of-the-art SIQA methods. Cross-database validation shows high generalization ability and high effectiveness of our model.

关键词： visualization Dams Stereo image processing Feature extraction Databases Data models image quality

来源：评论

学校读者我要写书评

暂无评论

Medical image enhancement using histogram equalization techniques

引用

AIP conference Proceedings 2023年第1期2591卷

作者： Zobeda Hatif Naji AL-Azzawi Wisam Hayder Mahdi Shaimaa Khamees Ahmed Waqas Saad Yasin 1Department of Computer Engineering College of Engineering University of Diyala Iraq 2Department of Communications Engineering College of Engineering University of Diyala Iraq

Due to the rapid development in digital technology, image enhancement has become a necessity to extract data and use it in many fields that may be medical, agricultural security, and many other fields. There are many image enhancement technique used in image processing. The proposed method have been presented in this paper attempt to improve the performance of histogram equalization with different kind of medical image by using Gaussian filter and gamma where combined together to improve the illumination, contrast of images ,reduce the noise, and also improve image quality coefficients. Try to measure the entropy of image and compare the result of output image with input image and to give desired result. The quality coefficients for the medical images processed with the HE and Gaussian filter and Gamma with certain value, according to the scientific proof. When the image quality was improved, the visual perception was improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improve image Captioning by Self-attention 1

引用

26th International conference on Neural Information processing (ICONIP) of the Asia-Pacific-Neural-Network-Society (APNNS)

作者： Li, Zhenru Li, Yaoyi Lu, Hongtao Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China

ISBN: (数字)9783030368029

ISBN: (纸本)9783030368029;9783030368012

The common attention mechanism has been widely adopted in prevalent image captioning frameworks. In most of the prior work, attention weights were only determined by visual features as well as the hidden states of Recurrent Neural Network (RNN), while the interaction of visual features was not modelled. In this paper, we introduce the self-attention into the current image captioning framework to leverage the nonlocal correlation among visual features. Moreover, we propose three distinctive methods to fuse the self-attention and the conventional attention mechanism. Extensive experiments on MSCOCO dataset show that the self-attention can empower the captioning model to achieve competitive performance with the state-of-the-art methods.

关键词： image captioning Self-attention

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition in Videos: An CNN-LSTM based Model for Video Classification

Facial Expression Recognition in Videos: An CNN-LSTM based M...

引用

International conference on Electronics, Information and communications (ICEIC)

作者： Muhammad Abdullah Mobeen Ahmad Dongil Han Vision and Image Processing Lab Sejong University Seoul South Korea

ISBN: (数字)9781728162898

ISBN: (纸本)9781728162904

Facial Expressions are an integral part of human communication. Therefore, correct classification of facial expression in image and video data has been an important quest for researchers and software development industry. In this paper we propose the video classification method using Recurrent Neural Networks (RNN) in addition to Convolution Neural Networks (CNN) to capture temporal as well spatial features of a video sequence. The methodology is tested on The Ryerson Audio-visual Database of Emotional Speech and Song (RAVDESS). Since no other results were available on this dataset using only visual analysis, the proposed method provides the first benchmark of 61% test accuracy on given dataset.

关键词： convolutional neural nets emotion recognition face recognition feature extraction image capture image classification image sequences recurrent neural nets video signal processing visual databases recurrent neural nets Facial Recognition visual databases image capture Video signal processing emotion recognition image sequences image classification Feature extraction Facial Expression Videotapes expression recognition Personal Communication

来源：评论

学校读者我要写书评

暂无评论

Underwater image Enhancement Based on the Iteration of a Generalization of Dark Channel Prior 34

Underwater Image Enhancement Based on the Iteration of a Gen...

引用

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

作者： Ueki, Yosuke Ikehara, Masaaki Keio Univ. EEE Dept. Yokohama Kanagawa223-8522 Japan

ISBN: (纸本)9781728137230

Underwater image enhancement is important for images captured in underwater because underwater images often suffer from color cast, low contrast and degraded visibility due to the absorption and scattering of light in water. In this paper, we propose a novel algorithm for underwater image restoration based on a generalization of the dark channel prior (GDCP). Though there are various types of underwater images, we especially focus on underwater images with depth because these images are not enhanced well by current algorithms. The proposed algorithm is composed of the iteration of GDCP and image fusion. Additionally, we introduce the new ambient light estimation to adapt to more types of images. Experimental results show that proposed algorithm is effective for various types of underwater images, especially for the images with depth. © 2019 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep feature guided image retargeting 34

Deep feature guided image retargeting

引用

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

作者： Wu, Jinan Xie, Rong Song, Li Liu, Bo Shanghai Jiao Tong University Institute of Image Communication and Network Engineering China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China University of Technology School of Computer Science Sydney Australia

ISBN: (纸本)9781728137230

image retargeting is the technique to display images via devices with various aspect ratios and sizes. Traditional content-Aware retargeting methods rely on low-level features to predict pixel-wise importance and can hardly preserve both the structure lines and salient regions of the source image. To address this problem, we propose a novel adaptive image warping approach which integrates with deep convolutional neural network. In the proposed method, a visual importance map and a foreground mask map are generated by a pre-Trained network. The two maps and other constraints guide the warping process to yield retargeted results with less distortions. Extensive experiments in terms of visual quality and a user study are carried out on the widely used RetargetMe dataset. Experimental results show that our method outperforms current state-of-Art image retargeting methods. © 2019 IEEE.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Graph Grouping Loss for Metric Learning of Face image Representations

Graph Grouping Loss for Metric Learning of Face Image Repres...

引用

IEEE visual communications and image processing (VCIP)

作者： Nakamasa Inoue Tokyo Institute of Technology Japan

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

This paper proposes Graph Grouping (GG) loss for metric learning and its application to face verification. GG loss predisposes image embeddings of the same identity to be close to each other, and those of different identities to be far from each other by constructing and optimizing graphs representing the relation between images. Further, to reduce the computational cost, we propose an efficient way to compute GG loss for cases where embeddings are L 2 normalized. In experiments, we demonstrate the effectiveness of the proposed method for face verification on the VoxCeleb dataset. The results show that the proposed GG loss outperforms conventional losses for metric learning.

关键词： Measurement Faces Training Feature extraction Videos Face recognition image edge detection

来源：评论

学校读者我要写书评

暂无评论

Predicting the visual saliency of the people with VIMS 34

Predicting the visual saliency of the people with VIMS

引用

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

作者： Yang, Jiawei Zhai, Guangtao Duan, Huiyu Shanghai Jiao Tong University Institute of Image Communication and Network Engineering Shanghai China

ISBN: (纸本)9781728137230

As is known to us, visually induced motion sickness (VIMS) is often experienced in a virtual environment. Learning the visual attention of people with VIMS contributes to related research in the field of virtual reality (VR) content design and psychology. In this paper, we first construct a saliency prediction for people with VIMS (SPPV) database, which is the first of its kind. The database consists of 80 omnidirectional images and the corresponding eye tracking data collected from 30 individuals. We analyze the performance of five state-of-The-Art deep neural networks (DNN)-based saliency prediction algorithms with their original networks and the fine-Tuned networks on our database. We predict the atypical visual attention of people with VIMS for the first time and obtain relatively good saliency prediction results for VIMS controls so far. © 2019 IEEE.

关键词： Deep neural networks

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：