检索结果-内蒙古大学图书馆

26th ACM Multimedia conference (MM)

作者： Huang, Ziqing Liu, Shiguang Tianjin Univ Sch Comp Sci & Technol Tianjin Peoples R China

ISBN: (纸本)9781450356657

image hashing is a novel technology of multimedia processing with wide applications. Robustness and discrimination are two of the most important objectives of image hashing. Different from existing hashing methods without a good balance with respect to robustness and discrimination, which largely restrict the application in image retrieval and copy detection, i.e., seriously reducing the retrieval accuracy of similar images, we propose a new hashing method which can preserve two kinds of complementary features (global feature via texture and local feature via DCT coefficients) to achieve a good balance between robustness and discrimination. Specifically, the statistical characteristics in gray-level co-occurrence matrix (GLCM) are extracted to well reveal the texture changes of an image, which is of great benefit to improve the perceptual robustness. Then, the normalized image is divided into image blocks, and the dominant DCT coefficients in the first row/column are selected to form a feature matrix. The Euclidean distance between vectors of the feature matrix is invariant to commonly-used digital operations, which helps make hash more compact. Various experiments show that our approach achieves a better balance between robustness and discrimination than the state-of-the-art algorithms.

关键词： image hashing Robustness and discrimination Dominant DCT coefficients Invariant vector distance

来源：评论

学校读者我要写书评

暂无评论

Analytical Realization of the EM Algorithm for Emission Positron Tomography 17th

Analytical Realization of the EM Algorithm for Emission Posi...

引用

17th International conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Cierniak, Robert Dobosz, Piotr Pluta, Piotr Filutowicz, Zbigniew Czestochowa Tech Univ Inst Computat Intelligence Armii Krajowej 36 PL-42200 Czestochowa Poland Univ Social Sci Inst Informat Technol PL-90113 Lodz Poland Clark Univ Worcester MA 01610 USA

ISBN: (纸本)9783319912622;9783319912615

The presented paper describes an analytical iterative approach to reconstruction problem for positron emission tomography (PET). The reconstruction problem is formulated taking into consideration the statistical properties of signals obtained by PET scanner and the analytical methodology of image processing. Computer simulations have been performed which prove that the reconstruction algorithm described here, does indeed significantly outperform conventional analytical methods on the quality of the images obtained.

关键词： image reconstruction from projections Positron emission tomography statistical iterative reconstruction algorithm

来源：评论

学校读者我要写书评

暂无评论

A micro-control capture images technology for the finger vein recognition based on adaptive image segmentation

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND processing SYSTEMS 2018年第10期24卷 4165-4178页

作者： Chiu, Chih-Cheng Liu, Tung-Kuan Lu, Weu-Ting Chen, Wen-Ping Chou, Jyh-Horng Natl Kaohsiung First Univ Sci & Technol Coll Engn PhD Program Engn Sci & Technol Kaohsiung Taiwan Natl Kaohsiung First Univ Sci & Technol Dept Mech & Automat Engn Kaohsiung Taiwan Kaohsiung Med Univ Grad Inst Clin Med Kaohsiung Taiwan Natl Kaohsiung Univ Appl Sci Dept Elect Engn Kaohsiung Taiwan Kaohsiung Med Univ Dept Healthcare Adm & Med Informat Kaohsiung Taiwan

The advantages of finger-vein recognition, compared to other biometric recognition technology commonly enlisted in identification needs such as ATM and door security, are uniqueness and living recognition, and so it has recently become one of major topics in biometric investigation. Through the irradiation of near-infrared rays, the finger-vein images are generated by blood vessels, and the texture of the image is created by the level of transparency between skeleton joints of the finger. Feature extraction of most finger-vein images employs global characteristics instead of local characteristics. This paper presents a local features method for dealing with the four segmentation of finger-vein images according to the physiological characteristics of finger. The four segmentation will be separated by a dynamic boundary line determined by the global vertical statistical quantity of the finger-vein image. Afterwards, each segmentation will be added with weighted values to enhance the fidelity of recognition. This study employs a total of 3816 finger-vein images generated by 106 adults in age of 20-60 years. The forefinger, middle finger, and little finger of each adult will be sampled for six images. Finally, the average recognition proposed by this study reaches 97%. The significant accuracy and contribution of this study is illustrated when compared to methods of global feature extraction (74.55%) and fixed-four regional segmentation feature extraction (86.48%).

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Photorealistic Style Transfer via Wavelet Transforms

Photorealistic Style Transfer via Wavelet Transforms

引用

International conference on Computer Vision (ICCV)

作者： Jaejun Yoo Youngjung Uh Sanghyuk Chun Byeongkyu Kang Jung-Woo Ha Clova AI Research NAVER Corp.

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT2) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a 1024x1024 resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, pre-trained models and supplementary documents are all available at https://***/ClovaAI/WCT2.

关键词： Decoding Wavelet transforms Distortion Network architecture image resolution image reconstruction

来源：评论

学校读者我要写书评

暂无评论

PoseFix: Model-agnostic General Human Pose Refinement Network

PoseFix: Model-agnostic General Human Pose Refinement Networ...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition

作者： Gyeongsik Moon Ju Yong Chang Kyoung Mu Lee Department of ECE ASRI Seoul National University Department of EI Kwangwoon University

ISBN: (纸本)9781728132945

Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose. The pose refinement was performed mainly through an end-to-end trainable multi-stage architecture in previous methods. However, they are highly dependent on pose estimation models and require careful model design. By contrast, we propose a model-agnostic pose refinement method. According to a recent study, state-of-the-art 2D human pose estimation methods have similar error distributions. We use this error statistics as prior information to generate synthetic poses and use the synthesized poses to train our model. In the testing stage, pose estimation results of any other methods can be input to the proposed method. Moreover, the proposed model does not require code or knowledge about other methods, which allows it to be easily used in the post-processing step. We show that the proposed approach achieves better performance than the conventional multi-stage refinement models and consistently improves the performance of various state-of-the-art pose estimation methods on the commonly used benchmark. The code is available in1.

关键词： pose estimation Refining two dimentional images model design tuple statistical analysis Codes Human

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Sparse Reconstruction Based Multi-feature Saliency for Target Detection in SAR images

Hierarchical Sparse Reconstruction Based Multi-feature Salie...

引用

Asian and Pacific conference on Synthetic Aperture Radar (APSAR)

作者： Lu Li Lan Du Zhaocheng Wang National Laboratory of Radar Signal Processing Xidian University Xi'an China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

The utilization of clutter information is useful for target detection. However, the clutter statistical modeling, used in conventional constant false alarm rate (CFAR) methods, is usually difficult for a real synthetic aperture radar (SAR) image. And though intensity feature is basic for target detection, only using intensity feature is insufficient considering the speckle noise. To address these problems, we propose a novel hierarchical sparse reconstruction based multi-feature saliency method to detect targets in SAR images. The proposed method hierarchically generates saliency maps using sparse reconstruction based on clutter templates on instance feature and structural feature separately. The clutter templates sampled from the pure clutter SAR images contains the clutter information. Though the sparse reconstruction based on clutter templates, we can fully utilize clutter information without clutter statistical modeling. Moreover, the proposed method jointly uses the instance feature and the structure feature, making the saliency detection more robust to speckle noise. We evaluate the proposed method on the miniSAR real data. The experimental results demonstrate that the proposed method outperforms conventional SAR target detection methods in terms of the precision, recall and F1-score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Selection approach using KNN supervised learning for Content-Based image Retrieval

Feature Selection approach using KNN supervised learning for...

引用

First International conference of Intelligent Computing and Engineering (ICOICE)

作者： Fahd A. Alqasemi Hamza Q. Alabbasi Fathi G. Sabeha Ahmed Alawadhi Sanad Kahlid Ammar Zahary University of Science and Technology Yemen Sana'a Yemen Faculty of computer and IT Sana'a University And Faculty of Engineering and IT Azal University for Human Development Sana'a Yemen

ISBN: (数字)9781728144870

ISBN: (纸本)9781728144887

Digital images have a serious influence over all the world, since, images have a very tangible importance, which impacts several people needs, this gave image retrieval researches this importance. So, Content-based image retrieval (CBIR) became one of the challenges in information retrieval and image processing fields, its services needs to apply for both business and science domains. In this paper we have proposed a CBIR approach that based on statistical methods feature selection via k-nearest neighbor (KNN) technique. Hence, supervised learning is employed for CBIR to train WANG database images, then the query image was the tested sample, and among predicted class we have filtered the final results. Number of randomly selected query images have been tested via this approach, with a variation of CBIR criteria, which have varied among image types, category query, and threshold distances. The average results have presented in three result groups, some RGB images results have showed good evaluation, in term of precisions measure, also grayscale and RGB images have varied values; on the evaluation of f-measures results, which have changed according some different CBIR factors. Proposed feature selection have made CBIR simpler and effective, this have been showed in high precision evaluation in final results.

关键词： Feature extraction image retrieval image color analysis Gray-scale Task analysis Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Open Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti 1

引用

25th International conference on Neural Information processing (ICONIP)

作者： Gordienko, Nikita Gang, Peng Gordienko, Yuri Zeng, Wei Alienin, Oleg Rokovyi, Oleksandr Stirenko, Sergii Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Kiev Ukraine Huizhou Univ Sch Informat Sci & Technol Huizhou Peoples R China

ISBN: (数字)9783030042219

ISBN: (纸本)9783030042219;9783030042202

Machine learning techniques are presented for automatic recognition of the historical letters (XI-XVIII centuries) carved on the stoned walls of St. Sophia cathedral in Kyiv (Ukraine). A new image dataset of these carved Glagolitic and Cyrillic letters (CGCL) was assembled and pre-processed for recognition and prediction by machine learning methods. The dataset consists of more than 4000 images for 34 types of letters. The explanatory data analysis of CGCL and notMNIST datasets shown that the carved letters can hardly be differentiated by dimensionality reduction methods, for example, by t-distributed stochastic neighbor embedding (tSNE) due to the worse letter representation by stone carving in comparison to hand writing. The multinomial logistic regression (MLR) and a 2D convolutional neural network (CNN) models were applied. The MLR model demonstrated the area under curve (AUC) values for receiver operating characteristic (ROC) are not lower than 0.92 and 0.60 for notMNIST and CGCL, respectively. The CNN model gave AUC values close to 0.99 for both notMNIST and CGCL (despite the much smaller size and quality of CGCL in comparison to notMNIST) under condition of the high lossy data augmentation. CGCL dataset was published to be available for the data science community as an open source resource.

关键词： Machine learning Explanatory data analysis t-distributed stochastic neighbor embedding Stone carving dataset notMNIST Multinomial logistic regression Convolutional neural network Deep learning Data augmentation

来源：评论

学校读者我要写书评

暂无评论

image encryption using chaotic 3-D Arnold’s cat map and logistic map 2nd

Image encryption using chaotic 3-D Arnold’s cat map and log...

引用

2nd International conference on Computer Vision and image processing, CVIP 2017

作者： Musanna, Farhan Rani, Asha Kumar, Sanjeev Department of Mathematics IIT Roorkee Roorkee India Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee247667 India

ISBN: (纸本)9789811078972

image encryption is different from that of traditional texts or binary data because of some inherent properties of images such as large data capacity, i.e., enormous size and high redundancy (statistical and psycho-visual), making them difficult to handle by traditional methods. In recent years, chaos theory has been explored to find efficient ways to develop secure image cryptosystems. Due to the desirable properties of mixing and sensitivity to initial conditions and parameters (butterfly effect), chaotic systems have found great deal in the domain of image encryption. In this paper, the 2-D chaotic cat map is generalized to its 3-D map counterpart for designing a real-time secure and reliable symmetric encryption design. This new scheme deploys the 3-D Arnold’s cat map to shuffle the positions of image pixels and uses the other chaotic logistic map to perplex the relationship between the plain-image and the cipher-image, thereby significantly enhancing the robustness to differential and statistical attacks. Experimental tests are carried out with comprehensive analysis, demonstrating the high security of the scheme. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

statistical Bayesian method for reliability evaluation based on ADT data 2

Statistical Bayesian method for reliability evaluation based...

引用

2nd International conference on Reliability Engineering (ICRE)

作者： Lu, Dawei Wang, Lizhi Sun, Yusheng Wang, Xiaohong Beihang Univ Sch Reliabil & Syst Engn Beijing Peoples R China Beihang Univ Unmanned Syst Inst Beijing Peoples R China

Accelerated degradation testing (ADT) is frequently conducted in the laboratory to predict the products' reliability under normal operating conditions. Two kinds of methods, degradation path models and stochastic process models, are utilized to analyze degradation data and the latter one is the most popular method. However, some limitations like imprecise solution process and estimation result of degradation ratio still exist, which may affect the accuracy of the acceleration model and the extrapolation value. Moreover, the conducted solution of this problem, Bayesian method, lose key information when unifying the degradation data. In this paper, a new data processing and parameter inference method based on Bayesian method is proposed to handle degradation data and solve the problems above. First, Wiener process and acceleration model is chosen;Second, the initial values of degradation model and parameters of prior and posterior distribution under each level is calculated with updating and iteration of estimation values;Third, the lifetime and reliability values are estimated on the basis of the estimation parameters;Finally, a case study is provided to demonstrate the validity of the proposed method. The results illustrate that the proposed method is quite effective and accuracy in estimating the lifetime and reliability of a product.

关键词： Reliability

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：