检索结果-内蒙古大学图书馆

The 2011 International Conference on Automation and Robotics(ICAR 2011)

作者： Chaobang Gao Jiliu Zhou Fangnian Lang Qiang Pu Chang Liu College of Computer Science and Technology Chengdu University School of Computer Science Sichuan University Key Laboratory of Pattern Recognition and Intelligent Information Processing

In this paper, we denote a color image by a quaternion function, then find edge points by solving the maximum of quaternion fractional directional differentiation(QFDD)'s norm. This method is called edge detection based on QFDD. Experiments indicate that the method has special advantages. Comparing with Canny, LOG, Sobel, and general fractional differentiation, we discover that QFDD has fewer false negatives in the textured regions and is also better at detecting edges which are partially defined by texture, which means we will obtain better results in the interesting regions by QFDD and these results are more consistent with the characteristics of human visual system.

关键词： quaternion fractional differentiation QFDD norm similarity

来源：评论

学校读者我要写书评

暂无评论

Sequence-level training for non-autoregressive neural machine translation

arXiv

引用

arXiv 2021年

作者： Shao, Chenze Feng, Yang Zhang, Jinchao Meng, Fandong Zhou, Jie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc

In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT and restricts its low-latency applications. Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously. Nevertheless, NAT still takes the word-level cross-entropy loss as the training objective, which is not optimal because the output of NAT cannot be properly evaluated due to the multimodality problem. In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. Firstly, we propose training NAT models to optimize sequence-level evaluation metrics (e.g., BLEU) based on several novel reinforcement algorithms customized for NAT, which outperforms the conventional method by reducing the variance of gradient estimation. Secondly, we introduce a novel training objective for NAT models, which aims to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The BoN training objective is differentiable and can be calculated efficiently without doing any approximations. Finally, we apply a three-stage training strategy to combine these two methods to train the NAT model. We validate our approach on four translation tasks (WMT14 En↔De, WMT16 En↔Ro), which shows that our approach largely outperforms NAT baselines and achieves remarkable performance on all translation tasks. The source code is available at https://***/ictnlp/Seq-NAT. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable Image Registration Approach for Multimodal Histological Images

引用

Computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National Institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

High Performance Reconfigurable Hardware system for real-time Image Processing

引用

Journal of systems Engineering and Electronics 2005年第3期000卷 502-509页

作者： Zhao Guangzhou Zhang Tianxu Wang Yuehuan Cao Zhiguo Zuo Zhengrong State Key Laboratory for Image Processing and Intelligent Control，Inst.for Pattern Recognition and Artificial Intelligence，Huazhong Univ.of Science and Technology，Wuhan 430074，P.R.China

A novel reconfigurable hardware system which uses both multi-DSP and FPGA to attain high performance and real-time image processing are presented. The system structure and working principle of mainly processing multi-DSP board, extended multi-DSP board are analysed. The outstanding advantage is that the communication among different board components of this system is supported by high speed link ports & serial ports for increasing the system performance and computational power. Then the implementation of embedded real-time operating systems (RTOS) by us is discussed in detail. In this system, we adopt two kinds of parallel structures controlled by RTOS for parallel processing of algorithms. The experimental results show that exploitive period of the system is short, and maintenance *** it is suitable for real-time image processing and can get satisfactory effect of image recognition.

关键词： rmulti-DSP field programmable gate arrays real-time image processing real time operating systems paralld structure

来源：评论

学校读者我要写书评

暂无评论

Oracle Character recognition using Unsupervised Discriminative Consistency Network

arXiv

引用

arXiv 2023年

作者： Wang, Mei Deng, Weihong Su, Sen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class similarity also make OrCR more challenging. In this paper, we propose a novel unsupervised domain adaptation method for OrCR, which enables to transfer knowledge from labeled handprinted oracle characters to unlabeled scanned data. We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency to make the predictions of scanned samples consistent under different perturbations, leading to the model robustness to abrasion, stain and distortion. Simultaneously, an unsupervised transition loss is proposed to learn more discriminative features on the scanned domain by optimizing both between-class and within-class transition probability. Extensive experiments show that our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%. © 2023, CC BY.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Fisher-Markov Selector via Manifold Regularization

Semi-supervised Fisher-Markov Selector via Manifold Regulari...

引用

2012 International Conference on Applied Informatics and Communication(ICAIC 2012)

作者： Dong Chen Lin Zhu JieYang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China

Feature subset selection is an important approach to deal with high-dimensional data. But selecting the best subset of data is NP hard. So most of feature selection methods cannot handle high-dimensional data efficiently, or they can only obtain local optimum instead of global optimum. In these cases, when the data consist of both labeled and unlabeled data, semi-supervised feature selection can make full use of data information. In this paper, we introduce a novel semi-supervised feature selection algorithm, which is a filter method based on Fisher-Markov selector, thus ours can achieve global optimum and computational efficiency under certain kernels.

关键词： Feature selection, Dimensionality reduction, Manifold regularization, Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Images Semantic Segmentation Method Based on Improved Nested UNet

Remote Sensing Images Semantic Segmentation Method Based on ...

引用

2022 International Conference on Geographic Information and Remote Sensing Technology, GIRST 2022

作者： Li, Zhongyu Liu, Yang Kuang, Yin Wang, Huajun Liu, Cheng College of Geophysics Chengdu University of Technology Chengdu610059 China College of Computer Science Chengdu Normal University Chengdu611130 China Key Laboratory of interior Layout optimization and Security Institutions of Higher Education of Sichuan Province Sichuan Chengdu611130 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China

ISBN: (纸本)9781510662186

With the development of remote sensing technology, remote sensing images of buildings are of great significance in urban planning, disaster response, and other directions. When we use a neural network containing batch normalization layers for semantic segmentation, the neural network is sensitive to batch size and has low segmentation accuracy for occluded and dense buildings. This paper proposes a method for building segmentation in remote sensing images based on Nested UNet (UNet++) deep neural network. First, the UNet++ network is used to extract features, and the Group Normalization (GN) method is used instead of Batch Normalization (BN) to alleviate the model's sensitivity to batch size. Then the weighted combination of Cross-Entropy Loss (CELoss) and DiceLoss is used as the loss function to improve the feature extraction ability of the neural network for unbalanced buildings. Finally, experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet++-GN) improves Mean Intersection over Union (MIoU) and Mean Pixel Accuracy (Macc) by 12.16% and 2.92%, respectively, compared with the original model (UNet++-BN). © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

N-order difference heuristic model of fuzzy time series forecasting

N-order difference heuristic model of fuzzy time series fore...

引用

IEEE International Conference on intelligent Computing and intelligent systems (ICIS)

作者： Kai Chi Wen-Gang Che Pattern Recognition and Intelligent System School of Information Engineering and Automation Kunming University of Science and Technology China Key Laboratory of Computer Technology and Application of Yunnan Province Kunming University of Science and Technology China

Fuzzy time series forecasting model is an effective method to solve the nonlinear problems forecasting. However, most published fuzzy time series based models did not count the change trend implicit in historical datum. In this paper, authors proposed a novel method which applied heuristic information to the fuzzy time series model based on Fibonacci sequence. As an example, the USD/JPY exchange rate is tested in this model. The results show that this method not only improves the forecasting accuracy, but decreases the computational complexity.

关键词： Predictive models Technology forecasting Economic forecasting Uncertainty Fuzzy systems pattern recognition intelligent systems Automation Channel hot electron injection Laboratories

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character recognition

arXiv

引用

arXiv 2024年

作者： Wang, Mei Deng, Weihong Hu, Jiani Su, Sen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

The study of oracle characters plays an important role in Chinese archaeology and philology. However, the difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. In this paper, we develop a novel unsupervised domain adaptation (UDA) method, i.e., unsupervised attention regularization network (UARN), to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data. First, we experimentally prove that existing UDA methods are not always consistent with human priors and cannot achieve optimal performance on the target domain. For these oracle characters with flip-insensitivity and high inter-class similarity, model interpretations are not flip-consistent and class-separable. To tackle this challenge, we take into consideration visual perceptual plausibility when adapting. Specifically, our method enforces attention consistency between the original and flipped images to achieve the model robustness to flipping. Simultaneously, we constrain attention separability between the pseudo class and the most confusing class to improve the model discriminability. Extensive experiments demonstrate that UARN shows better interpretability and achieves state-of-the-art performance on Oracle-241 dataset, substantially outperforming the previously structure-texture separation network by 8.5%. © 2024, CC BY.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Objective resolution measurement in single particle reconstructions based on a new spectral signal-to-noise ratio estimation

Objective resolution measurement in single particle reconstr...

引用

第28届中国控制与决策会议

作者： Shuai Wang Biao Zhang Hong-Bin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (纸本)9781467397155

The resolution measurement of 3D reconstructed density map in single particle reconstruction is an important and still an open *** this paper,we propose a new protocol to measure the resolution just from the reconstructed density *** approach estimates spectral signal-to-noise ratio(SSNR) of 3D reconstructed map by computing the ratio of signal power to noise power in frequency *** power distributions of signal and noise are estimated from structure particle region and surrounding region segmented by applying a mask *** proposed protocol of calculating SSNR,which we term mask-SSNR(mSSNR),is independent of the reconstruction algorithms and can be used for density maps reconstructed with any reconstruction ***,the mSSNR neither needs to split the dataset into halves like the Fourier shell correlation(FSC) approach,nor any original images or intermediate data like other SSNR calculation methods in this *** mSSNR provides a direct calculation of SSNR based on its original definition,and is proven to be a better approach.

关键词： Electron microscopy Resolution measurement Spectral signal-to-noise ratio Signal processing

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：