检索结果-内蒙古大学图书馆

Unsupervised scene segmentation using sparse coding context

MACHINE VISION AND APPLICATIONS 2013年第2期24卷 243-254页

作者： Liu, Yen-Cheng Chen, Hwann-Tzong Natl Tsing Hua Univ Dept Comp Sci Hsinchu 30043 Taiwan

This paper presents an approach to image understanding on the aspect of unsupervised scene segmentation. With the goal of image understanding in mind, we consider 'unsupervised scene segmentation' a task of dividing a given image into semantically meaningful regions without using annotation or other human-labeled information. We seek to investigate how well an algorithm can achieve at partitioning an image with limited human-involved learning procedures. Specifically, we are interested in developing an unsupervised segmentation algorithm that only relies on the contextual prior learned from a set of images. Our algorithm incorporates a small set of images that are similar to the input image in their scene structures. We use the sparse coding technique to analyze the appearance of this set of images;the effectiveness of sparse coding allows us to derive a priori the context of the scene from the set of images. Gaussian mixture models can then be constructed for different parts of the input image based on the sparse-coding contextual prior, and can be combined into an Markov-random-field-based segmentation process. The experimental results show that our unsupervised segmentation algorithm is able to partition an image into semantic regions, such as buildings, roads, trees, and skies, without using human-annotated information. The semantic regions generated by our algorithm can be useful, as pre-processed inputs for subsequent classification-based labeling algorithms, in achieving automatic scene annotation and scene parsing.

关键词： Unsupervised image segmentation Semantic scene analysis sparse coding Markov random fields

来源：评论

学校读者我要写书评

暂无评论

Learning the sparse prior: Modern approaches

引用

Wiley Interdisciplinary Reviews: Computational Statistics 2024年第1期16卷 e1646-e1646页

作者： Peng, Guan-Ju Institute of Data Science and Information Computing National Chung Hsing University Taichung Taiwan

The sparse prior has been widely adopted to establish data models for numerous applications. In this context, most of them are based on one of three foundational paradigms: the conventional sparse representation, the convolutional sparse representation, and the multi-layer convolutional sparse representation. When the data morphology has been adequately addressed, a sparse representation can be obtained by solving the sparse coding problem specified by the data model. This article presents a comprehensive overview of these three models and their corresponding sparse coding problems and demonstrates that they can be solved using convex and non-convex optimization approaches. When the data morphology is not known or cannot be analyzed, it must be learned from training data, thereby formulating dictionary learning problems. This article addresses two different dictionary learning paradigms. In an unsupervised scenario, dictionary learning involves the alternating or joint resolution of sparse coding and dictionary updating. Another option is to create a recurrent neural network by unrolling algorithms designed to solve sparse coding problems. These networks can then be used in a supervised learning setting to facilitate the training of dictionaries via forward-backward optimization. This article lists numerous applications in various domains and outlines several directions for future research related to the sparse prior. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods Statistical and Graphical Methods of Data Analysis > Modeling Methods and Algorithms Statistical Models > Nonlinear Models. © 2024 Wiley Periodicals LLC.

关键词： algorithm unrolling convex and non-convex optimization convolutional sparse model dictionary learning multi-layer convolutional sparse model recurrent neural network sparse coding sparse prior

来源：评论

学校读者我要写书评

暂无评论

3D CG Image Noise Removal and Quality Assessment Based on sparse Dictionary Learning 3

3D CG Image Noise Removal and Quality Assessment Based on Sp...

引用

IEEE 3rd Global Conference on Life Sciences and Technologies (IEEE LifeTech)

作者： Kawabata, Norifumi Tokyo Univ Sci Dept Informat Sci 2641 Yamazaki Noda Chiba Japan

ISBN: (纸本)9781665418751

In this paper, first, we carried out dictionary learning to process the sparse coding in advance, and then, we added six types of noise for 3D CG images. Next, we processed noise removal based on sparse coding theory and dictionary learning. Before and after image processing, we discussed improvement of image quality evaluation value eventually by measuring PSNR.

关键词： sparse coding Dictionary Learning Noise Addition Noise Removal Image Quality Assessment

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Video Super-Resolution Using Beta Process and Bayesian Dictionary Learning 16th

Hyperspectral Video Super-Resolution Using Beta Process and ...

引用

16th International Symposium on Visual Computing (ISVC)

作者： Ghassab, Vahid Khorasani Bouguila, Nizar Concordia Univ Montreal PQ H3G 1M8 Canada

ISBN: (纸本)9783030904364;9783030904357

In this paper, we present an algorithm to super-resolve the acquired frames in a hyperspectral video using sparse coding and applying a Beta process. For this purpose, we apply Beta process in Bayesian dictionary learning and we will generate a sparse coding regarding the hyperspectral video super-resolution. The spatial super-resolution was followed by a spectral video restoration process using two different dictionaries which one of them is trained for spatial super-resolution and the other one is trained for the spectral restoration. We have experimented our proposed strategy over a large public hyperspectral video database including a 31-frame hyperspectral video (each frame has 33 bands from 400 nm to 720 nm wavelength with a 10 nm step) and compared the outcome with other state of the art methodologies. The proposed method is evaluated on RMSE, PSNR, SSIM and VSNR metrics. The comparison results prove that our proposed method outperforms other state of the art techniques.

关键词： Hyperspectral video Super-resolution Beta process Bayesian dictionary learning sparse coding

来源：评论

学校读者我要写书评

暂无评论

New interdependence feature of EEG signals as a biomarker of timing deficits evaluated in Attention-Deficit/Hyperactivity Disorder detection

引用

MEASUREMENT 2022年 199卷

作者： Ghaderyan, Peyvand Moghaddam, Farima Khoshnoud, Shiva Shamsi, Mousa Sahand Univ Technol Fac Biomed Engn Computat Neurosci Lab Tabriz Iran Sahand Univ Technol Fac Biomed Engn Tabriz Iran Inst Frontier Areas Psychol & Mental Hlth Freiburg Germany

Similarity quantification is an important field of study in electroencephalogram (EEG)-based brain activity detection, in which the goal is to compute interdependence between certain cortical areas from inter-hemispheric or intra-hemispheric channel pairs. This study aims to propose a new interdependence EEG feature, namely Dynamic frequency warpping(DFW) based on dynamic analysis of frequency fluctuations as a hybrid feature extraction step. A new EEG classifier based on sparse coding has been developed for Attention Deficit Hyperactivity Disorder (ADHD) detection. It has been tested using EEG recordings of 14 ADHD children and 19 healthy controls during resting state and a time-reproduction task. The capability of the proposed method with an accuracy rate of 99.17% has been shown. Use of the DFW extracted from frontal channel pairs or beta frequency band not only improves the performance but also reduces the computational complexity due to the need to a subgroup of channels or a subband.

关键词： Machine learning Electroencephalogram Dynamic frequency warping sparse coding

来源：评论

学校读者我要写书评

暂无评论

3D CBIR with sparse coding for image-guided neurosurgery

引用

SIGNAL PROCESSING 2013年第6期93卷 1673-1683页

作者： Qian, Yu Hui, Rui Gao, Xiaohong Middlesex Univ Sch Sci & Technol London NW4 4BT England Gen Navy Hosp Dept Neurosurg Beijing Peoples R China

This research takes an application-specific approach to investigate, extend and implement the state of the art in the fields of both visual information retrieval and machine learning, bridging the gap between theoretical models and real world applications. During an image-guided neurosurgery, path planning remains the foremost and hence the most important step to perform an operation and ensures the maximum resection of an intended target and minimum sacrifice of health tissues. In this investigation, the technique of content-based image retrieval (CBIR) coupled with machine learning algorithms are exploited in designing a computer aided path planning system (CAP) to assist junior doctors in planning surgical paths while sustaining the highest precision. Specifically, after evaluation of approaches of sparse coding and K-means in constructing a codebook, the model of sparse codes of 3D SIFT has been furthered and thereafter employed for retrieving, The novelty of this work lies in the fact that not only the existing algorithms for 2D images have been successfully extended into 3D space, leading to promising results, but also the application of CBIR that is mainly in a research realm, to a clinical sector can be achieved by the integration with machine learning techniques. Comparison with the other four popular existing methods is also conducted, which demonstrates that with the implementation of sparse coding, all methods give better retrieval results than without while constituting the codebook, implying the significant contribution of machine learning techniques. Crown Copyright (C) 2012 Published by Elsevier B.V. All rights reserved.

关键词： CBIR Computer aided path planning Neurosurgery 3D SIFT sparse coding

来源：评论

学校读者我要写书评

暂无评论

Laplacian affine sparse coding with tilt and orientation consistency for image classification

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2013年第7期24卷 786-793页

作者： Zhang, Chunjie Wang, Shuhui Huang, Qingming Liang, Chao Liu, Ting Tian, Qi Univ Chinese Acad Sci Sch Comp & Control Engn Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Intell Info Proc Inst Comp Technol Beijing 100190 Peoples R China Wuhan Univ Natl Engn Res Ctr Multimedia Software Wuhan 430072 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China Univ Texas San Antonio Dept Comp Sci San Antonio TX 78249 USA

Recently, sparse coding has become popular for image classification. However, images are often captured under different conditions such as varied poses, scales and different camera parameters. This means local features may not be discriminative enough to cope with these variations. To solve this problem, affine transformation along with sparse coding is proposed. Although proven effective, the affine sparse coding has no constraints on the tilt and orientations as well as the encoding parameter consistency of the transformed local features. To solve these problems, we propose a Laplacian affine sparse coding algorithm which combines the tilt and orientations of affine local features as well as the dependency among local features. We add tilt and orientation smooth constraints into the objective function of sparse coding. Besides, a Laplacian regularization term is also used to characterize the encoding parameter similarity. Experimental results on several public datasets demonstrate the effectiveness of the proposed method. (C) 2013 Elsevier Inc. All rights reserved.

关键词： Image classification Affine transformation sparse coding Laplacian matrix Tilt and orientation Smooth constraints Object categorization Bag-of-visual words model

来源：评论

学校读者我要写书评

暂无评论

Adaptive nearest neighbor reconstruction with deep contractive sparse filtering for fault diagnosis of roller bearings

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2022年第0期111卷 104749-104749页

作者： Qian, Weiwei Li, Shunming Lu, Jiantao Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Sch Future Technol Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Nanjing 210016 Peoples R China

Case-based intelligent fault diagnosis has had some notable successes in recent years. However, compared with parameter-based methods, they pay less attention to automatic and powerful feature extraction. Meanwhile, most approaches use k-nearest neighbor (KNN) algorithms or related variants, which fail in adaptive nearest neighbor location. To deal with these shortcomings, an algorithm called adaptive nearest neighbor reconstruction (ANNR) is proposed, which can take advantage of both parameter- and case-based diagnosis methods. Firstly, ANNR offers sparse and robust feature extraction by designed deep contractive sparse filtering (DCSF), which fuses a local contractive term to learn robust feature manifolds. Secondly, to locate the nearest neighbors for diverse testing samples adaptively, a case-based reconstruction algorithm is developed to obtain correlation vectors between training and testing samples. Finally, according to correlation vector of each testing sample, its optimized nearest neighbors are located, enabling precise feature classification. Extensive experiments were conducted on two roller bearing vibration signal datasets and verified its effectiveness.

关键词： Intelligent fault diagnosis Roller bearing Deep sparse contractive filtering Adaptive nearest neighbor Local contractive sparse coding

来源：评论

学校读者我要写书评

暂无评论

Maximal Dependence Capturing as a Principle of Sensory Processing

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2022年 16卷 857653页

作者： Raj, Rishabh Dahlen, Dar Duyck, Kyle Yu, C. Ron Stowers Inst Med Res Kansas City MO 64110 USA Univ Kansas Med Ctr Dept Anat & Cell Biol Kansas City KS 66103 USA

Sensory inputs conveying information about the environment are often noisy and incomplete, yet the brain can achieve remarkable consistency in recognizing objects. Presumably, transforming the varying input patterns into invariant object representations is pivotal for this cognitive robustness. In the classic hierarchical representation framework, early stages of sensory processing utilize independent components of environmental stimuli to ensure efficient information transmission. Representations in subsequent stages are based on increasingly complex receptive fields along a hierarchical network. This framework accurately captures the input structures;however, it is challenging to achieve invariance in representing different appearances of objects. Here we assess theoretical and experimental inconsistencies of the current framework. In its place, we propose that individual neurons encode objects by following the principle of maximal dependence capturing (MDC), which compels each neuron to capture the structural components that contain maximal information about specific objects. We implement the proposition in a computational framework incorporating dimension expansion and sparse coding, which achieves consistent representations of object identities under occlusion, corruption, or high noise conditions. The framework neither requires learning the corrupted forms nor comprises deep network layers. Moreover, it explains various receptive field properties of neurons. Thus, MDC provides a unifying principle for sensory processing.

关键词： object recognition (OR) computational modeling invariant representation sparse recovery (SR) redundancy reduction redundancy capturing sparse coding grandmother cell

来源：评论

学校读者我要写书评

暂无评论

Joint Gaussian dictionary learning and tomographic reconstruction

引用

INVERSE PROBLEMS 2022年第10期38卷 105010-105010页

作者： Zickert, Gustav Oktem, Ozan Yarman, Can Evren KTH Royal Inst Technol Dept Math SE-10044 Stockholm Sweden Etud & Prod Schlumberger 1 Rue Henri Becquerel F-92140 Clamart France

This paper studies ill-posed tomographic imaging problems where the image is sparsely represented by a non-negative linear combination of Gaussians. Our main contribution is to develop a scheme for directly recovering the Gaussian mixture representation of an image from tomographic data, which here is modeled as noisy samples of the parallel-beam ray transform. An important aspect of this non-convex reconstruction problem is the choice of initial guess. We propose an initialization procedure that is based on a filtered back projection type of operator tailored for the Gaussian dictionary. This operator can be evaluated efficiently using an approximation of the Riesz-potential of an anisotropic Gaussian which is based on an exact closed form expression for the Riesz-potential of an isotropic Gaussian. The proposed method is evaluated on simulated data.

关键词： dictionary learning inverse problem tomography task adapted reconstruction image reconstruction sparse coding regularization

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：