检索结果-内蒙古大学图书馆

作者： Faccio, Thiago Amorim de Universidade Estadual Paulista

A tarefa de segmentação de imagem está presente em diversos programas e aplicativos ao alcance de qualquer usuário de tecnologia. Apesar disso, pouco se fala sobre o funcionamento desta ferramenta, isto é, como ela é realmente executada quando levado em consideração não simplesmente o ponto de vista gráfico, mas também o processo matemático e computacional por trás desse tipo de tarefa. Visto isso, este trabalho faz uma breve abordagem sobre a matemática e as metodologias que regem técnicas de Processamento Digital de imagens, com foco em métodos de Segmentação Interativa, e busca por meio do estudo de diferentes métodos clássicos, alcançar melhorias nos resultados deste tipo de tarefa. Tem-se como objetivo obter maior precisão na realização de segmentações através da análise de novas características extraídas da imagem, as quais são adotadas como elementos de entrada para o cálculo dos pesos do grafo associado à segmentação do método das Coordenadas de Laplace. A proposta analisou diferentes composições de features (bandas) de realce dos objetos e bordas de uma imagem, sendo essas bandas resultantes de técnicas como, por exemplo, modelos de mistura gaussiana, o algoritmo expectation–maximization, detector de bordas Canny, funções de distância local, entre outras. Assim, almejou-se atingir melhores resultados tanto do ponto de vista quantitativo, a partir de métricas de aferição de partições tais como o Rand Index (RI), Variation ou Information (VoI) e o Dice Coefficient (DICE), como também em termos qualitativos, seja para imagens com poucas marcações de entrada fornecidas pelo usuário ou com riqueza das *** segmentation is an omnipresent task in many programs and applications commonly used by technology users. Despite its systematic use, the segmentation task has several issues not properly exploited in terms of the mathematical background, i.e., how the segmentation works not only in the visual interpretation aspect, but also considering the mathematical

关键词： Segmentação interativa de imagens Análise de features Método das coordenadas de laplace Processamento digital de imagens Detector de bordas interactive image segmentation Features analysis Laplacian coordinates Digital image processing Edge detec

来源：评论

学校读者我要写书评

暂无评论

Interaktivní segmentace popředí/pozadí na mobilním telefonu

Interaktivní segmentace popředí/pozadí na mobilním tele...

引用

作者： Studený, Petr Brno University of Technology

Práce se zabývá technikami pro interaktivní segmentaci popředí a pozadí na mobilních zařízeních. Cílem je nalézt nebo vytvořit vhodné metody pro oddělen... 详细信息

Práce se zabývá technikami pro interaktivní segmentaci popředí a pozadí na mobilních zařízeních. Cílem je nalézt nebo vytvořit vhodné metody pro oddělení uživatelem označeného objektu od pozadí. V úvahu je brána zejména rychlost segmentace a kvalita výstupu. Jsou popsány principy již existujících metod pro interaktivní segmentaci, je diskutováno jejich využití na mobilních zařízeních. Je navržena a implementována vlastní metoda velmi rychlé segmentace použitá pro náhled z kamery mobilního zařízení v reálném čase.

关键词： Interaktivní segmentace obrazu mobilní zařízení nalezení řezu grafem získání vyhlazené alfa masky editace obrazu výřez objektu z obrazu matematická morfologie. interactive image segmentation mobile devices graph cut alpha matting image editing

来源：评论

学校读者我要写书评

暂无评论

Automatic Inside Point Localization with Deep Reinforcement Learning for interactive Object segmentation

引用

SENSORS 2021年第18期21卷 6100-6100页

作者： Li, Guoqing Zhang, Guoping Qin, Chanchan Cent China Normal Univ Coll Phys Sci & Technol 152 Luoyu Rd Wuhan 430079 Peoples R China Cent China Normal Univ Key Lab Quark & Lepton Phys MOE 152 Luoyu Rd Wuhan 430079 Peoples R China Guizhou Normal Univ Sch Big Data & Comp Sci Guiyang 550025 Peoples R China Guizhou Normal Univ Dept Educ Ctr RFID & WSN Engn Guiyang 550025 Peoples R China

In the task of interactive image segmentation, the Inside-Outside Guidance (IOG) algorithm has demonstrated superior segmentation performance leveraging Inside-Outside Guidance information. Nevertheless, we observe that the inconsistent input between training and testing when selecting the inside point will result in significant performance degradation. In this paper, a deep reinforcement learning framework, named Inside Point Localization Network (IPL-Net), is proposed to infer the suitable position for the inside point to help the IOG algorithm. Concretely, when a user first clicks two outside points at the symmetrical corner locations of the target object, our proposed system automatically generates the sequence of movement to localize the inside point. We then perform the IOG interactive segmentation method for precisely segmenting the target object of interest. The inside point localization problem is difficult to define as a supervised learning framework because it is expensive to collect image and their corresponding inside points. Therefore, we formulate this problem as Markov Decision Process (MDP) and then optimize it with Dueling Double Deep Q-Network (D3QN). We train our network on the PASCAL dataset and demonstrate that the network achieves excellent performance.

关键词： interactive image segmentation Markov Decision Process (MDP) Deep Reinforcement Learning (DRL) inside point localization Deep Q-Network (DQN)

来源：评论

学校读者我要写书评

暂无评论

MIDeepSeg: Minimally interactive segmentation of unseen objects from medical images using deep learning

引用

MEDICAL image ANALYSIS 2021年 72卷 102102-102102页

作者： Luo, Xiangde Wang, Guotai Song, Tao Zhang, Jingyang Aertsen, Michael Deprest, Jan Ourselin, Sebastien Vercauteren, Tom Zhang, Shaoting Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu Peoples R China SenseTime Res Shanghai Peoples R China Shanghai Jiao Tong Univ Sch Biomed Engn Shanghai Peoples R China Kings Coll London Sch Biomed Engn & Imaging Sci London England Univ Hosp Leuven Dept Radiol Leuven Belgium Univ Hosp Leuven Dept Obstet & Gynaecol Leuven Belgium UCL Inst Womens Hlth London England

segmentation of organs or lesions from medical images plays an essential role in many clinical applications such as diagnosis and treatment planning. Though Convolutional Neural Networks (CNN) have achieved the state-of-the-art performance for automatic segmentation, they are often limited by the lack of clinically acceptable accuracy and robustness in complex cases. Therefore, interactive segmentation is a practical alternative to these methods. However, traditional interactive segmentation methods require a large number of user interactions, and recently proposed CNN-based interactive segmentation methods are limited by poor performance on previously unseen objects. To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects. Specifically, we first encode user-provided interior margin points via our proposed exponentialized geodesic distance that enables a CNN to achieve a good initial segmentation result of both previously seen and unseen objects, then we use a novel information fusion method that combines the initial segmentation with only a few additional user clicks to efficiently obtain a refined segmentation. We validated our proposed framework through extensive experiments on 2D and 3D medical image segmentation tasks with a wide range of previously unseen objects that were not present in the training set. Experimental results showed that our proposed framework 1) achieves accurate results with fewer user interactions and less time compared with state-of-the-art interactive frameworks and 2) generalizes well to previously unseen objects. (c) 2021 Elsevier B.V. All rights reserved.

关键词： interactive image segmentation Convolutional neural network Geodesic distance Generalization

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Classification via Local Spline Regression

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2010年第11期32卷 2039-2053页

作者： Xiang, Shiming Nie, Feiping Zhang, Changshui Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Tsinghua Univ Dept Automat Tsinghua Natl Lab Informat Sci & Technol State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China

This paper presents local spline regression for semi-supervised classification. The core idea in our approach is to introduce splines developed in Sobolev space to map the data points directly to be class labels. The spline is composed of polynomials and Green's functions. It is smooth, nonlinear, and able to interpolate the scattered data points with high accuracy. Specifically, in each neighborhood, an optimal spline is estimated via regularized least squares regression. With this spline, each of the neighboring data points is mapped to be a class label. Then, the regularized loss is evaluated and further formulated in terms of class label vector. Finally, all of the losses evaluated in local neighborhoods are accumulated together to measure the global consistency on the labeled and unlabeled data. To achieve the goal of semi-supervised classification, an objective function is constructed by combining together the global loss of the local spline regressions and the squared errors of the class labels of the labeled data. In this way, a transductive classification algorithm is developed in which a globally optimal classification can be finally obtained. In the semi-supervised learning setting, the proposed algorithm is analyzed and addressed into the Laplacian regularization framework. Comparative classification experiments on many public data sets and applications to interactive image segmentation and image matting illustrate the validity of our method.

关键词： Semi-supervised classification local spline regression interactive image segmentation

来源：评论

学校读者我要写书评

暂无评论

EnNet: Enhanced interactive Information Network with Zero-Order Optimization

引用

SENSORS 2024年第19期24卷 6361页

作者： Shao, Yingzhao Chen, Yanxin Yang, Pengfei Cheng, Fei Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Key Lab Smart Human Comp Interact & Wearable Techn Xian 710071 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710126 Peoples R China

interactive image segmentation extremely accelerates the generation of high-quality annotation image datasets, which are the pillars of the applications of deep learning. However, these methods suffer from the insignificance of interaction information and excessively high optimization costs, resulting in unexpected segmentation outcomes and increased computational burden. To address these issues, this paper focuses on interactive information mining from the network architecture and optimization procedure. In terms of network architecture, the issue mentioned above arises from two perspectives: the less representative feature of interactive regions in each layer and the interactive information weakened by the network hierarchy structure. Therefore, the paper proposes a network called EnNet. The network addresses the two aforementioned issues by employing attention mechanisms to integrate user interaction information across the entire image and incorporating interaction information twice in a design that progresses from coarse to fine. In terms of optimization, this paper proposes a method of using zero-order optimization during the first four iterations of training. This approach can reduce computational overhead with only a minimal reduction in accuracy. The experimental results on GrabCut, Berkeley, DAVIS, and SBD datasets validate the effectiveness of the proposed method, with our approach achieving an average NOC@90 that surpasses RITM by 0.35.

关键词： interactive image segmentation self-attention mechanism global features fine-grained features semi-supervised optimization

来源：评论

学校读者我要写书评

暂无评论

AGUnet: Annotation-guided U-net for fast one-shot video object segmentation

引用

PATTERN RECOGNITION 2021年 110卷 107580-107580页

作者： Yin, Yingjie Xu, De Wang, Xingang Zhang, Lei Chinese Acad Sci Inst Automat Res Ctr Precis Sensing & Control Beijing 100190 Peoples R China Hong Kong Polytech Univ Dept Comp Hung Hom Kowloon Hong Kong Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

The problem of semi-supervised video object segmentation has been popularly tackled by fine-tuning a general-purpose segmentation deep network on the annotated frame using hundreds of iterations of gra-dient descent. The time-consuming fine-tuning process, however, makes these methods difficult to use in practical applications. We propose a novel architecture called Annotation Guided U-net (AGUnet) for fast one-shot video object segmentation (VOS). AGUnet can quickly adapt a model trained on static images to segmenting the given target in a video by only several iterations of gradient descent. Our AGUnet is inspired by interactive image segmentation, where the interested target is segmented by using user annotated foreground. However, in AGUnet we use a fully-convolutional Siamese network to automatically annotate the foreground and background regions and fuse such annotation information into the skip connection of a U-net for VOS. Our AGUnet can be trained end-to-end effectively on static images instead of video sequences as required by many previous methods. The experiments show that AGUnet runs much faster than current state-of-the-art one-shot VOS algorithms while achieving competitive accuracy, and it has high generalization capability. (c) 2020 Elsevier Ltd. All rights reserved.

关键词： Fully-convolutional Siamese network U-net interactive image segmentation Video object segmentation

来源：评论

学校读者我要写书评

暂无评论

Human Part segmentation in Depth images with Annotated Part Positions

引用

SENSORS 2018年第6期18卷 1900-1900页

作者： Hynes, Andrew Czarnuch, Stephen Mem Univ Dept Elect & Comp Engn St John NF A1B 3X5 Canada

We present a method of segmenting human parts in depth images, when provided the image positions of the body parts. The goal is to facilitate per-pixel labelling of large datasets of human images, which are used for training and testing algorithms for pose estimation and automatic segmentation. A common technique in image segmentation is to represent an image as a two-dimensional grid graph, with one node for each pixel and edges between neighbouring pixels. We introduce a graph with distinct layers of nodes to model occlusion of the body by the arms. Once the graph is constructed, the annotated part positions are used as seeds for a standard interactive segmentation algorithm. Our method is evaluated on two public datasets containing depth images of humans from a frontal view. It produces a mean per-class accuracy of 93.55% on the first dataset, compared to 87.91% (random forest and graph cuts) and 90.31% (random forest and Markov random field). It also achieves a per-class accuracy of 90.60% on the second dataset. Future work can experiment with various methods for creating the graph layers to accurately model occlusion.

关键词： human parts interactive image segmentation occlusion grid graph

来源：评论

学校读者我要写书评

暂无评论

"GrabCut" - interactive foreground extraction using iterated graph cuts

引用

ACM TRANSACTIONS ON GRAPHICS 2004年第3期23卷 309-314页

作者： Rother, C Kolmogorov, V Blake, A Microsoft Res Cambridge Cambridge England

The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (colour) information, e.g. Magic Wand, or edge (contrast) information, e.g. Intelligent Scissors. Recently, an approach based on optimization by graph-cut has been developed which successfully combines both types of information. In this paper we extend the graph-cut approach in three respects. First, we have developed a more powerful, iterative version of the optimisation. Secondly, the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result. Thirdly, a robust algorithm for "border matting" has been developed to estimate simultaneously the alpha-matte around an object boundary and the colours of foreground pixels. We show that for moderately difficult examples the proposed method outperforms competitive tools.

关键词： interactive image segmentation graph cuts image editing foreground extraction alpha matting

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：