检索结果-内蒙古大学图书馆

Fast DCT-I, DCT-III, and DCT-IV via Moments

Eurasip Journal on Applied Signal processing 2005年第12期2005卷 1902-1909页

作者： Liu, J.G. Liu, Y.Z. Wang, G.Y. Key Laboratory of Education Huazhong University of Science and Technology Ministry for Image Processing and Intelligence Control Wuhan 430074 China Department of Computer Science and Engineering China University of Geosciences Wuhan 430074 China Key Laboratory of State Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology China Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology China

This paper presents a novel approach to compute DCT-I, DCT-III, and DCT-IV. By using a modular mapping and truncating, DCTs are approximated by linear sums of discrete moments computed fast only through additions. This enables us to use computational techniques developed for computing moments to compute DCTs efficiently. We demonstrate this by applying our earlier systolic solution to this problem. The method can also be applied to multidimensional DCTs as well as their inverses. © 2005 Hindawi Publishing Corporation.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

Object detection algorithm based on mixed dilated convolution pyramid 3

Object detection algorithm based on mixed dilated convolutio...

引用

3rd International Conference on Computer Vision and pattern Analysis, ICCPA 2023

作者： Yu, Tingjian Yuan, Zemin Huang, Tao Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510667563

To address the problem that FPN in the one-stage object detection algorithm loses a large amount of semantic information after upsampling and downsampling fusion, leading to difficulties in detecting small objects in dense scenes. This paper proposes a new FPN structure, Residual dilated FPN(RdFPN), compared to the traditional FPN, which uses multiple Dilated Block instead of the standard convolution in the FPN horizontal structure to mix the receptive fields of different layers in the feature map and expand the object size range of the feature map, while improving the network's ability to extract features at different scales. Experimental results show that RdFPN improves the mAP of the one-stage object detection algorithms RetinaNet, FCOS, and GFL by 0.9%, 0.7%, and 0.8% on the MS COCO dataset, enough to improve the overall performance of the detector. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Kernel based weighted group sparse representation classifier

Kernel based weighted group sparse representation classifier

引用

15th International Conference on Human-Computer Interaction, HCI International 2013

作者： Xu, Bingxin Guo, Ping Chen, C. L. Philip Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Faculty of Science and Technology University of Macau China

ISBN: (纸本)9783642393419

Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, SRC can not well classify the data when they are in the overlap feature space. In addition, SRC treats different samples equally and ignores the cooperation among samples belong to the same class. In this paper, a kernel based weighted group sparse classifier (KWGSC) is proposed. Kernel trick is not only used for mapping the original feature space into a high dimensional feature space, but also as a measure to select members of each group. The weight reflects the importance degree of training samples in different group. Substantial experiments on benchmark databases have been conducted to investigate the performance of proposed method in image classification. The experimental results demonstrate that the proposed KWGSC approach has a higher classification accuracy than that of SRC and other modified sparse representation classification. © 2013 Springer-Verlag.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Improvement and invariance analysis of Zernike moments 1

Improvement and invariance analysis of Zernike moments

引用

1st International Conference on Communications, Circuits and Systems, ICCCAS 2002

作者： Bin, Ye Xiong, Peng Jia State Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology WuhanHubei430074 China

ISBN: (纸本)0780375475

An improved Zernike moment using a region-based shape descriptor is presented. The improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not have. The experimental results show that the improved Zernike moment has better invariant properties than the unimproved Zernike moment using a region-based shape descriptor. © 2002 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Improved Embedding Model for Zero-Shot Classification based on Attention Mechanism 5

An Improved Embedding Model for Zero-Shot Classification bas...

引用

5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Wu, Zongfeng Li, Qishen Yu, Xiao Peng, Xu Nanchang Hangkong University School of Information Engineering Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China

It is well-known that the auxiliary information plays a key role in zero-shot classification. However, most of the existing popular methods do not make effective use of auxiliary information. To address this issue, we propose an improved embedding model for zero-shot classification based on attention mechanism, called EMAM. In the proposed EMAM, we first add an attention mechanism to effectively extract the key information of auxiliary information in zero-shot classification. Then optimizes the objective function to improve the recognition rate of this model. Finally the experimental comparison is implemented on the standard zero-shot learning datasets. The experimental results demonstrate that our proposed EMAM not only verifies its validity, but also achieves good results. © 2021 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Dense Pedestrian Detection Based on Multiple Link Feature Pyramid Networks 3

Dense Pedestrian Detection Based on Multiple Link Feature Py...

引用

3rd International Conference on Computer Vision and pattern Analysis, ICCPA 2023

作者： Huang, Tao Yang, Siyu Yu, Tingjian Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510667563

Pedestrian detection is widely employed in a variety of industries, including security, autonomous driving, and pedestrian flow statistics. However, because most pedestrians in real-world scenes are densely distributed with occlusion issues, scale variation and pose variability, majority pedestrian detection algorithms have low detection accuracy and a high miss detection rate. In this paper, we propose a new FPN neck module, Multiple Link Feature Pyramid Networks (MLFPN) for dense pedestrian detection, which innovative information transfer pathways and incorporation of Poly-Scale Convolution (PSconv) capable of long-range interaction into feature extraction tasks to reduce feature information loss and enhanced representation of effective pedestrian features, achieving 0.6MR-2, 0.35AP, and 0.21JI improvements on CrowdHuman dataset, improving detection accuracy and reducing missed detection rates. © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cross-GAN: Unsupervised image-to-image Translation 6

Cross-GAN: Unsupervised Image-to-Image Translation

引用

6th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2022

作者： Peng, Xu Li, Qishen Wu, Taida Yuan, Sihao Nanchang Hangkong University School of Information Engineering Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China

ISBN: (纸本)9781665431859

In recent years, unsupervised image-to-image translation is a topic in computer graphics. This paper proposes a new architecture to translate the image through the idea of sharing and decoupling, termed as Cross-GAN, which can better extract the style in the process of translation, and does not change the original outline and background. We improve the cycle consistency loss and reconstruction loss for the unique properties of the model to make the image more realistic. Because GAN[1] only generates the target style image by inputting the content image, and the information of the target domain image is not used in the training process. We input style images and content images through cross-input. The style images play a guiding role in the generator, and the effect of image are better by fusing style features and content features. Due to the fact that the image of the target domain is input, it is easy to produce the phenomenon of over-fitting. In order to prevent over-fitting training, we improve the cycle consistency loss and reuse the input encoder to make the model more compact. © 2022 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Object detection algorithm based on residual deformable convolution pyramid 4

Object detection algorithm based on residual deformable conv...

引用

4th International Conference on Computer Vision and pattern Analysis, ICCPA 2024

作者： Huang, Bin Wang, Sanqian Li, Linjie Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang*** China School of Software Nanchang Hangkong University Nanchang*** China

ISBN: (纸本)9781510682528

Considering the challenges associated with robots in optoelectronic imaging applications, typically require real-time and accurate recognition and localization of targets, especially in complex environments. Due to the potential challenges of noise, blurring, or dense targets in the images obtained by optoelectronic imaging systems, traditional object detection algorithms may face issues such as semantic information loss and difficulty in detecting small targets. By introducing residual deformable convolution structures, feature representation can be enhanced in optoelectronic imaging systems, and the shape of the convolution kernel can be dynamically adjusted to adapt to the non rigid deformation of the target, thereby better capturing the detailed features of small targets. Experimental results exhibit that RAFPN enhances the mAP of object detection algorithms RetinaNet, Faster R-CNN, and GFL by 1.2%, 0.9%, and 1.1% respectively on the MS COCO dataset, effectively enhancing the performance of object detection algorithms in optoelectronic imaging. © 2024 SPIE.

关键词： Optoelectronic devices

来源：评论

学校读者我要写书评

暂无评论

Dynamic Action recognition under Simulated Prosthetic Vision

Dynamic Action Recognition under Simulated Prosthetic Vision

引用

2020 International Conference on Networking and Network Applications, NaNA 2020

作者： Zhao, Ying Xu, Dantong Wang, Tie Ren, Yanchun Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information Engineering Inner Mongolia University of Science and Technology Baotou Inner Mongolia

ISBN: (纸本)9781728189543

Purpose. To assess the recognition pattern of dynamic action by visual prosthesis' wearers. Methods. Twenty volunteers (classified by gender and experience) were recruited to carried out action recognition test in simulated prosthetic vision. Twenty-three common dynamic actions video clips usually see in daily life were selected and formed the experimental action set which was divided into three parts including combined actions, simple actions and difficult actions in turn. The action animations made by 3D Studio Max were recorded by Banicam to convert to MP4 video format and processed to phosphene video clips by MATLAB in different resolutions (16 × 16, 24 × 24, 32 × 32, 48 × 48, 64 × 64, 128 × 128). Result. Comparing the recognition results, male group and female group had no significant difference. 48 × 48 resolution was the considerable latent capacity which subjects had stable performance. After a period of study, the performance of prosthesis wearers could be improved significantly. © 2020 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

A novel video face clustering algorithm based on divide and conquer strategy

A novel video face clustering algorithm based on divide and ...

引用

12th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2012

作者： Gou, Gaopeng Huang, Di Wang, Yunhong Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media Beihang University Beijing China

ISBN: (纸本)9783642326943

Video-based face clustering is a very important issue in face analysis. In this paper, a framework for video-based face clustering is proposed. The framework contains two steps. First, faces are detected from videos and divided into subgroups using temporal continuity information and SIFT (Scale Invariant Feature Transform) features. Second, the typical samples are selected from these subgroups in order to remove some non-typical faces. A similarity matrix is then constructed using these typical samples in the subgroups. The similarity matrix is further processed by our method to generate the face clustering results of that video. Our algorithm is validated using the SPEVI datasets. The experiments demonstrated promising results from our algorithm. © 2012 Springer-Verlag.

关键词： Clustering algorithms

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：