检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and Security

作者： Xin Zheng Qingqing Xu Peipei Pan Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

In many application fields, an appropriate high-quality fast image upsampling method is required. Although many interpolation-based upsampling methods have been proposed, the quality of result images is not satisfactory. Some of them are very fast, but produce poor quality images, the others can produce high quality images, but the methods in them are slow. In our paper, we proposed a fast statistical image upsampling method based on CUDA, it can obtain high quality images based on reducing the input resolution-grids dependency artifacts. Thus, we can rebuild low resolution images' sharp edges fast and get high-quality upsampled images in real time. We have applied this method in the multi-resolution texture generation of large scale terrain rendering. Experiments prove that our method can receive ideal effects in real time.

关键词： Graphics processing units Mathematical model image edge detection image resolution Markov processes Standards Computational modeling

来源：评论

学校读者我要写书评

暂无评论

image Completion with Automatic Structure Propagation

Image Completion with Automatic Structure Propagation

引用

International Conference on Computational Intelligence and Security

作者： Peipei Pan Xin Zheng Qingqing Xu Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

In this paper, we propose a novel approach for image completion with automatic structure propagation. This method integrates two stages: Firstly, it extends the salient structure lines from the known regions to the unknown by following a local self-similarity assumption on natural images. Then guided by the structure information, it restores the missing region by patch-based texture synthesis. Experiment results demonstrate a better effect of our method than that of the previous patch-based texture synthesis image completion algorithm.

关键词： image edge detection image segmentation image reconstruction image resolution Filling image restoration Sun

来源：评论

学校读者我要写书评

暂无评论

Object Detector based on Enhanced Multi-scale Feature Fusion Pyramid Network

Object Detector based on Enhanced Multi-scale Feature Fusion...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Luan Zhao Xiaofeng Zhang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Constructing the pyramidal architecture for the feature is currently a very effective way to obtain feature information of objects at different scales. Although the feature pyramid can realize the recognition and detection of multi-scale objects in the object detection task well, it still has some limitations. Since the feature information of different levels is often not from the same layer of the network, it is difficult to obtain the feature of different objects information at a certain scale from a certain level feature map of the pyramid network. To solve this problem, we present a novel object detection architecture, named Enhanced Multi-scale Feature Fusion Pyramid Network (EMFFPNet). Our network consists of Enhanced Multi-scale Feature Fusion Module (EMFFM) and Predictor Optimization Module (POM). In EMFFM, Features at different levels can be fused into the Enhanced features as outputs, which are more representative and deterministic. In order to enable the enhanced features to play their respective roles in the pyramid network, we assign different weights to fusion features of different levels in POM. We perform the experiments on the COCO detection benchmark. The experimental results indicate that the performance of our model is much better than the state-of-the-art model.

关键词： Object detection Predictive models Feature extraction Task analysis Information technology Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Gait recognition Algorithm GCGait based on Skeleton 3

Gait Recognition Algorithm GCGait based on Skeleton

引用

3rd IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Ma, Ru Zhang, Jikai Jia, Mengyu Lv, Xiaoqi Inner Mongolia University of Science and Technology School of Information Engineering Baotou China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou China Inner Mongolia University of Technology School of Information Engineering Hohhot China

ISBN: (纸本)9781665490788

To solve the problem of low accuracy of gait recognition in complex scenes, a novel skeleton-based gait recognition algorithm, GCGait, is proposed. Taking human posture as the input of gait feature, the interference caused by wearing changes and other factors is reduced. To extract sufficient input features, multi-branch input is used in the early stage of the model. By introducing the multi-attention mechanism, the network can learn the semantic information of the non-directly connected joints, excavate the most discriminative features from complex videos, and further improve the recognition performance. In order to reduce the influence of cross view, the fusion loss function is used in the experiment. Experimental results show that the average recognition rate of the proposed algorithm on the CASIA-B dataset is improved by 5.2%, and the average recognition accuracy on the OU-MVLP dataset is increased by 66.3%, which proves the effectiveness of the proposed method. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Optimal classification of epileptic EEG signals using neural networks and harmony search methods

Journal of Software

引用

Journal of Software 2014年第1期9卷 230-239页

作者： Gao, Xiao-Zhi Wang, Jing Tanskanen, Jarno M. A. Bie, Rongfang Wang, Xiaolei Guo, Ping Zenger, Kai College of Information Engineering Shanghai Maritime University China Department of Automation and Systems Technology Aalto University School of Electrical Engineering Finland Laboratory of Image Processing and Pattern Recognition Beijing Normal University China Department of Biomedical Engineering Tampere University of Technology Finland School of Foundational Education Peking University Health Science Center China

In this paper, the Harmony Search (HS)-aided BP neural networks are used for the classification of the epileptic electroencephalogram (EEG) signals. It is well known that the gradient descent-based learning method can result in local optima in the training of BP neural networks, which may significantly affect their approximation performances. Three HS methods, the original version and two new variations recently proposed by the authors of the present paper, are applied here to optimize the weights in the BP neural networks for the classification of the epileptic EEG signals. Simulations have demonstrated that the classification accuracy of the BP neural networks can be remarkably improved by the HS method-based training. © 2014 ACADEMY PUBLISHER.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Maintaining imbalance highly dependent medical data using dirichlet process data generation

Maintaining imbalance highly dependent medical data using di...

引用

International Conference on Digital Information Management (ICDIM)

作者： Tieta Antaresti Mohamad Ivan Fanany Aniati Murni Arymurthy Pattern Recognition Image Processing and Content-Based Image Retrieval Laboratory Faculty of Computer Science Universitas Indonesia Depok Indonesia

The existence of imbalanced data between one class and another class is an important issue to be considered in a classification problem. One of the well-known data balancing technique is the artificial oversampling, which increase the size of datasets. In this research, multinomial classification was applied to classify some recorded features obtained from a single ECG (electrocardiograph) sensor. Therefore, a Dirichlet process, a dirichlet distribution of cumulative distribution function of each data partition, was needed to model the distribution of the new generated data by also considering the statistical properties of the previous data. Data balancing process had given the result of 77.21% classification accuracy (CA), and 90.9% area under ROC curve (AUC).

关键词： Electrocardiography Accuracy Diseases Data models Bayesian methods Sleep apnea Machine learning

来源：评论

学校读者我要写书评

暂无评论

Element-Wise Layer Normalization for Continuous Signal Representation 23

Element-Wise Layer Normalization for Continuous Signal Repre...

引用

15th International Conference on Digital image processing, ICDIP 2023

作者： Chen, Weifeng Ding, Hui He, Zhifen Li, Bo Liu, Bin Wang, Kang School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Jiangxi Science and Technology Infrastructure Center Jiangxi Computing Center Jiangxi Computing Center Nanchang China

ISBN: (纸本)9798400708237

Implicit neural representation (INR), sometimes also referred to coordinate-based representation or fitting, has gained the state-of-the-art performance in numerous research fields including computer vision and computer graphics due to the powerful continuous representation ability. Recent researches indicate that Fourier embedding is critical for INR to fit realistic images with high-frequency details. However, is Fourier embedding all we need for high-frequency coordinate (image) fitting? In this paper, we revisit the problem of coordinate fitting from a novel perspective of distribution mapping. Fourier embedding, as a preprocessing step of coordinate fitting, essentially performs the operation of mapping the uniform coordinate distribution to a normal distribution, and makes the learning of mapping function between two similar smooth distribution become easier. However, the number of discrete Fourier basis function affects the fitting performance dramatically and cannot be determined automatically. Based on the above analysis, a simple yet efficient INR coordinate fitting method is proposed in this paper, which demonstrates that the Fourier embedding is not the only way to improve INR. The proposed method only adds an element-wise layer normalization (ELN) module to the vanilla multi-layer perception (MLP) with ReLU activation. Experimental results on public database demonstrate that the proposed method outperforms the state-of-the-art methods using Fourier embedding. © 2023 ACM.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

MixerSR: A New Feature Extraction Paradigm for Single image Super-Resolution 23

MixerSR: A New Feature Extraction Paradigm for Single Image ...

引用

15th International Conference on Digital image processing, ICDIP 2023

作者： Ding, Hui Chen, Weifeng He, Zhifen Li, Bo Liu, Bin Wang, Kang School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Jiangxi Science and Technology Infrastructure Center and Jiangxi Computing Center Jiangxi Computing Center Nanchang China

ISBN: (纸本)9798400708237

Single-image super-resolution (SR) tasks have achieved fancy success in recent years by leveraging deep convolution neural network (CNN). Although CNNs obtain powerful representation capabilities of reconstructing a high-resolution (HR) image from its corresponding low-resolution (LR) observation, it is hard to apply these accomplishments to real world for its large number of parameters that bring about huge computing resource cost. To solve this problem, many researchers turn their directions to lightening the network by delicate designs while keeping the performance in the high level. In this paper, we propose a new method to further reduce the parameters by using the new feature extraction paradigm called Mixer which only contains Multi-Layer Perceptron (MLP). Compared to convolutional operations, Mixer operation has the same representation capabilities with fewer parameters. In this paper, three typical lightweight networks, where we replace the convolutional operation with Mixer, are used to show the excellent ability. Our experimental results demonstrate that Mixer can help these lightweight networks further reduce the number of parameters by up to 38% while keep their performance in the same level. © 2023 ACM.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Smart Mathematic Morphology Method for recognition and Understanding of Airfield

引用

Wuhan University Journal of Natural Sciences 2005年第5期10卷 867-872页

作者： WANG Zhi-cheng TIAN Yan TIAN Jin-wen LIU Jian LIANG Chao-sheng TAO Wen-bin State Education Commission Key Laboratory for Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan430074 Hubei China Department of Electronics and Information Engineering Huazhong University of Science and Technology Wuhan 430074 Hubei China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 Hubei China

A method used for recognition and understanding of airfield based on mathematical morphology is proposed in this paper. The new approach can he divided into three steps. First, to extract the typical geometric structure features of airfield, a segmentation method called recursive Otsu algorithm is employed on an airfield image. Second, thinning and shrinking algorithms are utilized to obtain the contour of airfield with single pixel and to remove diffused small particles. Finally, Radon transform is adopted to extract two typical and important components, primary and secondary runways of airfield exactly. At the same time, region growing algorithm is exploited to get the other components such as parking apron and garages. The experimental results demonstrate that the proposed method gives good performance.

关键词： mathematical morphology shrinking algorithm Radon transform Region growing

来源：评论

学校读者我要写书评

暂无评论

image-to-Class Metric based on Category Traversal for Few-shot Learning 10

Image-to-Class Metric based on Category Traversal for Few-sh...

引用

10th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2022

作者： Yuan, Sihao Li, Qishen Huang, Hua Li, Qiufeng School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China Jiangxi China

ISBN: (数字)9781665422079

ISBN: (纸本)9781665422079

The purpose of few-shot learning is to learn a classification model with good generalization performance. When there is only one sample or several samples, the model can also be quickly generalized to new categories. In this paper, we use the method based on metric learning to complete the few-shot learning image classification task. In this method, we introduce a feature learning module to improve the representation ability of the feature extraction network. Through category traversal, the module extracts the intra-class common features and inter-class unique features of images. Finally, by comparing the similarity between the input image and the local descriptors of each category, the classification task is completed by the image-to-class measure. This metric is achieved by k-NN search in the local descriptors, in this way, we can make full use of all the local features of a category, thus expressing the distribution of this class more richly and effectively. © 2022 IEEE.

关键词： image classification

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：