检索结果-内蒙古大学图书馆

Signal, Information and Data processing (ICSIDP), IEEE International conference on

作者： Zhaofeng Chen Tianshuang Qiu Hongkai Wang School of Electronic Engineering Jiujiang University Jiujiang China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

statistical shape models (SSMs) play important roles in the analysis of medical images. SSMs of particular organs are built by learning statistical shape patterns of the target organs from medical images. As a prerequisite step of SSM construction, the anatomical correspondences between the training subjects have to be obtained, requiring nontrivial and tedious organ segmentation from the training images, as well as difficult registration of the segmented organ shapes. To tackle these problems, we design a novel strategy called merged intensity and landmark registration (MILR) which does not require segmentation of the target organ. The MILR method directly registers an organ shape template to the training images by simultaneously optimizing the template-to-image intensity similarity and the key anatomical landmark alignment. Compared to conventional correspondence calculation methods, the MILR method not only saves the time of organ segmentation but also ensures accurate alignment of important anatomical feature points, improving both the efficiency and accuracy of SSM construction. To verify this method, we constructed the human vertebral column SSM from volumetric CT images. We show results of correspondences by three validation metrics anatomical landmark distance (ALD), Dice similarity coefficient (DSC) and average surface distance (ASD)and the corresponding construction of SSMs by generalization ability and specificity of the human vertebral column from the CT images of 17 different subjects. The novel merged strategy, with merged deformation field reconstruction, shows competitive results against the conventional methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Wavelet-based Learning for Face Hallucination with Loop Architecture 33

A Wavelet-based Learning for Face Hallucination with Loop Ar...

引用

33rd IEEE International conference on Visual Communications and image processing (IEEE VCIP)

作者： Geng, Cong Chen, Li Zhang, Xiaoyun Zhou, Peng Gao, Zhiyong Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China

ISBN: (纸本)9781538644584

Face hallucination is a specific super-resolution problem which aims to generate high-resolution(HR) faces from low-resolution(LR) input. Recently, deep learning methods have been widely applied in single-image super resolution. Considering face images have great similarities in both pixel value and global structure, we propose a wavelet-based deep learning method with loop architecture for face hallucination. In contrast to existing wavelet-based methods that generate wavelet coefficients independently without considering relationships between them, we propose a three-stage method with loop architecture. This alternately updated loop structure explores the statistical relationships among wavelet coefficients and has a maximum use of information flow with a small number of parameters. Because of multi-resolution property of wavelet transform, we adopt a mixed input strategy to train images with different sizes to realize multi-scale face hallucination without retraining and adding extra subnetworks. Experiments demonstrate that our method can get a robust performance with multi-scale face hallucination.

关键词： face hallucination wavelet coefficients three-stage loop architecture multi-scale up-scaling

来源：评论

学校读者我要写书评

暂无评论

Research on the handwriting character recognition technology based on the image statistical characteristics 5th

Research on the handwriting character recognition technology...

引用

5th International conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017

作者： Sun, Yongfeng Guo, Zhonghua Qiu, Weijiang China Electric Power Research Institute No. 15 Xiaoying East Road Haidian District Beijing China

ISBN: (纸本)9789811308956

The research on the image pattern recognition has always been a hot topic. In this paper, the automatic identification technology of image is studied, the research contents include image preprocessing, image feature extraction and image content identification. BP neural network is used for the research on the image content identification. The processing methods in this article include the following steps, first, the pre-processing of the image. Including image de-noising and feature extraction;second, training the BP neural network with the processed handwriting character image;third, the recognition test of the unknown handwritten character. 95% recognition accuracy is realized, and the research has some practical application value. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Learning 2D Morphological Network for Old Document image Binarization

Learning 2D Morphological Network for Old Document Image Bin...

引用

International conference on Document Analysis and Recognition

作者： Ranjan Mondal Deepayan Chakraborty Bhabatosh Chanda Indian Statistical Institute Kolkata

Document image binarization, especially old handwritten documents, is a very important yet challenging task. There are various bottlenecks for binarizing historical documents due to different types of degradation present imultaneously such as back impression, ink bleed through, faded colours, and wear and tear of the writing media. We consider these degradation as various types of noise in the document image. Here we have proposed a 2D morphological network which consists of basic morphological operation like dilation and erosion to perform our targeted task. The network also includes linear combination of output from dilation and erosion operations. The aforementioned 2D morphological network is applied for image binarization, where the structuring elements (SEs) and the weights of the linear combination layer are learned through back-propagation. The proposed network has been evaluated on DIBCO 2017 and H-DIBCO 2018 and ISI-Letter dataset. Our results show more convincing as compared to the results of other state-of-the-art methods. Though the network is developed for old handwritten documents, it may be tuned to work for image processing task. The source code can be found here https://***/ranjanZ/ICDAR_Binarization.

关键词： Two dimensional displays Task analysis Ink Neurons Degradation image color analysis

来源：评论

学校读者我要写书评

暂无评论

Leukemia Diagnosis using image processing and Computational Intelligence 22

Leukemia Diagnosis using Image Processing and Computational ...

引用

22nd IEEE International conference on Intelligent Engineering Systems (INES)

作者： Parvaresh, Hamed Sajedi, Hedieh Rahimi, Seyed Amirhosein Univ Tehran Coll Sci Sch Math Stat & Comp Sci Dept Comp Sci Tehran Iran

ISBN: (纸本)9781538611227

Acute Lymphoblastic Leukemia (ALL) is the most prevalent acute leukemia in adults after Acute Myeloid Leukemia, with a diffusion of over 6500 persons per year just in the United States. In this research, we propose a smart assistant determination method for ALL diagnosis using microscopic images. In this regard, K-means is employed to extract cell images after that wavelet transform is hired on cell images then statistical moments of the transformed image are computed to extract features. Afterward, a Chain Tabu search algorithm is proposed for feature selection of normal and abnormal cells to enable classifiers classifying ALL efficiently. Finally, Multi-Layer Perceptron (MLP) is used for classification. The proposed method is evaluated on ALL-IDB2. The proposed method achieved the accuracy of 98.88% and outperforms existed ALL diagnosis methods.

关键词： Feature extraction image segmentation image color analysis Wavelet transforms Support vector machines Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

IMPROVED AUDIO-VISUAL LAUGHTER DETECTION VIA MULTI-SCALE MULTI-RESOLUTION image TEXTURE FEATURES AND CLASSIFIER FUSION

IMPROVED AUDIO-VISUAL LAUGHTER DETECTION VIA MULTI-SCALE MUL...

引用

IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Akhtar, Zahid Bedoya, Stefany Falk, Tiago H. Univ Quebec EMT INRS Ste Foy PQ Canada

ISBN: (纸本)9781538646588

Efforts are afoot to design better context-aware human-computer interaction techniques that have knowledge of both their surrounding and the affective state of the user. One of the most important nonverbal behavioural cues for affective human-machine interaction is laughter. Automatic detection of laughter is an interesting, yet challenging problem, which in recent years has gained increased attention from both the academic and industrial communities. The majority of existing laughter detection systems rely on either audio or video modalities. Humans, however, typically rely on audio-visual cues during conversation and/or interaction, thus it is expected that improved results can be achieved if both modalities are used. In this work, we propose a multimodal framework that analyzes audio and video channels separately, then fuses their decisions. Conventional speech spectral and prosodic features are used, whereas new multi-scale multi-resolution binarized statistical image features are proposed due to their improved expressive power. Experiments with the publicly available MAHNOB Laughter database show that decision level fusion based on support vector machine classifiers leads to improved performance over single modality approaches, as well as over previously-proposed methods, all whilst requiring just a fraction of the computational power.

关键词： Laughter detection information fusion social signal processing spectral features BSIF features

来源：评论

学校读者我要写书评

暂无评论

Robust image Hashing Based on Hybrid Approach of Scale-Invariant Feature Transform and Local Binary Patterns 23

Robust Image Hashing Based on Hybrid Approach of Scale-Invar...

引用

23rd IEEE International conference on Digital Signal processing, DSP 2018

作者： Wang, Ping Jiang, Aimin Cao, Yuan Gao, Yuan Tan, Rongjun He, Haixia Zhou, Mingrui College of Internet of Things Engineering Hohai University Changzhou China

ISBN: (纸本)9781538668115

image hash functions find extensive applications in content authentication, database search, and digital forensic. Robust image hash has been widely investigated to authenticate the reliability of images transmitted by a trustless channel. In this paper, we propose a novel image hashing algorithm which is robust to content-reserved and multiple manipulations. To achieve the perceptual robustness and sensitivity, the proposed scheme combines scale-invariant feature transform (SIFT) with local binary pattern (LBP). SIFT extracts plenty of descriptors which are robust to geometric distortion and luminance transformation. LBP generates hash values that contain local information and are sensitive to content manipulation. We further investigate the performance of proposed scheme and other existing algorithms via statistical analysis of recognition rate, and the results show that our method outperforms conventional methods. © 2018 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Robust Optimisation Monte Carlo

arXiv

引用

arXiv 2019年

作者： Ikonomov, Borislav Gutmann, Michael U. School of Informatics University of Edinburgh

This paper is on Bayesian inference for parametric statistical models that are defined by a stochastic simulator which specifies how data is generated. Exact sampling is then possible but evaluating the likelihood function is typically prohibitively expensive. Approximate Bayesian Computation (ABC) is a framework to perform approximate inference in such situations. While basic ABC algorithms are widely applicable, they are notoriously slow and much research has focused on increasing their efficiency. Optimisation Monte Carlo (OMC) has recently been proposed as an efficient and embarrassingly parallel method that leverages optimisation to accelerate the inference. In this paper, we demonstrate an important previously unrecognised failure mode of OMC: It generates strongly overconfident approximations by collapsing regions of similar or near-constant likelihood into a single point. We propose an efficient, robust generalisation of OMC that corrects this. It makes fewer assumptions, retains the main benefits of OMC, and can be performed either as post-processing to OMC or as a stand-alone computation. We demonstrate the effectiveness of the proposed Robust OMC on toy examples and tasks in inverse-graphics where we perform Bayesian inference with a complex image renderer. Copyright © 2019, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Analysis of local binary pattern for emphysema classification in lung CT image

Analysis of local binary pattern for emphysema classificatio...

引用

International conference on Electronics, Computers and Artificial Intelligence (ECAI)

作者： Eva Tuba Ivana Strumberger Nebojsa Bacanin Milan Tuba Singidunum University Belgrade Serbia

ISBN: (数字)9781728116242

ISBN: (纸本)9781728116259

Medical digital images and methods for their processing and automatic analysis have been used for faster and more precise diagnosis. Computer-aided diagnosis systems are widely used by specialists as help for detecting and analyzing suspicions regions in medical digital images. Various types of medical digital images and numerous diseases that can be detected on them make this wide research field. One of the diseases that can be detected in lung CT images is chronic obstructive pulmonary disease or emphysema. In this paper we analyzed the capabilities of texture descriptors, local binary pattern, for detecting and classification of emphysema. Three different types of local binary pattern are used. Instead of using a whole local binary pattern operator output, statistical measurements have been used. Support vector machine optimized by elephant herding optimization algorithm was used for classification. Based on the obtained results, it can be concluded that six statistical information of uniform local binary pattern achieve the best classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polarimetric SAR image Classification by Multitask Sparse Representation Learning 7

Polarimetric SAR Image Classification by Multitask Sparse Re...

引用

7th International conference on Digital Home (ICDH)

作者： Li, Bo Li, Ying Chen, Minxia Nanchang Hangkong Univ Sch Math & Informat Sci Nanchang Jiangxi Peoples R China

ISBN: (纸本)9781538694961

Classification is an important and difficult problem in Polarimetric SAR (POLSAR) image processing. Most existing classification methods combine multiple features (scattering parameters or statistical distribution) to improve the performance. However, based on the observation that various regions have different characteristics due to the different scattering mechanism, which implies that different features should be used for certain pixels rather than using the combination of various features for the whole image, so that simple combinations will result in numerous error classifications. In this paper, a novel POLSAR classification method based on multitask learning with multiple features is proposed. Firstly, different types of features are extracted, and then POLSAR classification problem is formulated as a multitask joint sparse representation learning problem. The strength of different features are employed by using of a joint sparse norm. Finally, experimental results on real POLSAR data show that our method outperforms several state-of-the-art algorithms.

关键词： Feature extraction Scattering Task analysis Dictionaries Training image segmentation image color analysis

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：