检索结果-内蒙古大学图书馆

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Linares, Oscar Cuadros Botelho, Glenda Rodrigues, Francisco Neto, Joao Batista Univ Sao Paulo ICMC Sao Carlos SP Brazil UFT Palmas TO Brazil

ISBN: (纸本)9781467379625

Due to the subjective nature of the segmentation process, quantitative evaluation of image segmentation methods is still a difficult task. Humans perceive image objects in different ways. Consequently, human segmentations may come in different levels of refinement, ie, under- and over-segmentations. Popular segmentation error measures in the literature (Arbelaez and OCE) are supervised methods (also called empirical discrepancy methods), in which error is computed by comparing objects in segmentations with a reference (ground-truth) image produced by humans. Since reference images can be many, the key issue for a segmentation error measure is to be consistent in the presence of both under- and over-segmentation. In general, the term consistency refers to the ability of the error measure to be low, when comparing similar segmentations, or high, when faced with different segmentations, while capturing under- or over-segmentations. In this paper we propose a new object-based empirical discrepancy error measure, called Adjustable Object-based Measure (AOM). We introduce a penalty parameter which gives the method the ability to be more (or less) responsive in the presence of over-segmentation. Hence, we extend the notion of consistency so as to include the application's need in the process. Some applications require segmentation to be extremely accurate, hence under- or over-segmentation should be well penalised. Others, do not. By changing the penalty parameter, AOM can deliver more consistent results not only in reference to the under- or over-segmentation issue alone, but also according to the nature of the application. We compare our method with Arbelaez (used as standard measure in the benchmark of Berkeley Segmentation image Dataset) and OCE. Our results show that AOM not only is more consistent in the presence of over-segmentation, but is also faster to compute. Unlike Arbelaez and OCE, AOM also satisfies the metric axiom of symmetry.

关键词： error measure metric evaluation image segmentation

来源：评论

学校读者我要写书评

暂无评论

READS: A radiology-oriented electronic analysis and display station

引用

JOURNAL OF DIGITAL IMAGING 1997年第3期10卷 67-69页

作者： Erickson, BJ Ryan, WJ Gehring, DG MAYO CLIN & MAYO FDN DEPT INFORMAT SERVROCHESTERMN 55905

READS is a picture archiving and communications system (PACS) display program that is tailored to allow a radiologist to efficiently perform image review tasks. In this study, the image review process was observed and functional patterns were identified. these were used to define a design that was considered to represent the optimal balance of compromises for a low-cost review station that also allowed easy addition of new functionality. As a result, a program was designed and implemented that has been found to be acceptable for image review and for special image processing function development. Copyright (C) 1997 by W.B. Saunders Company.

关键词： PACS image processing image display

来源：评论

学校读者我要写书评

暂无评论

Methodology for the design of NN-based month-word recognizers written on brazilian bank checks

引用

image AND VISION COMPUTING 2007年第1期25卷 40-49页

作者： Kapp, Marcelo N. Freitas, Cinthia O. de A. Sabourin, Robert Ecole Technol Super Montreal PQ H3C 1K3 Canada Pontificia Univ Catolica Parana Curitiba Parana Brazil

the study of handwritten words is tied to the development of recognition methods to be used in real-world applications involving handwritten words, such as bank checks, postal envelopes, and handwritten texts, among others. In this work, the focus is handwritten words in the context of brazilian bank checks, specifically the months of the year, and no restrictions are placed on the types or styles of writing or the number of writers. A global feature set and two architectures of artificial neural networks (ANN) are evaluated for classification of the words. the objectives are to evaluate the performance of conventional and class-modular multiple-layer perceptron (MLP) architectures, to develop a rejection mechanism based on multiple thresholds, and to analyze the behavior of the feature set proposed in the two architectures. the experimental results demonstrate the superiority of the class-modular architecture over the conventional MLP architecture. A rejection mechanism with multiple thresholds demonstrates favorable performance in both architectures. the feature set analysis shows the importance of the structural primitives such as concavities and convexities, and perceptual primitives such as ascenders and descenders. the experimental results reveal a recognition rate of 81.75% without the rejection mechanism, and a reliability rate 91.52% with a rejection rate of 25.33%. (c) 2006 Elsevier B.V. All rights reserved.

关键词： neural networks rejection feature selection handwritten word recognition

来源：评论

学校读者我要写书评

暂无评论

processing Neocognitron of Face Recognition on High Performance Environment Based on GPU with CUDA Architecture

Processing Neocognitron of Face Recognition on High Performa...

引用

20th International symposium on computer Architecture and High Performance Computing

作者： Poli, Gustavo Saito, Jose Hiroki Mari, Joao F. Zorzan, Marcelo R. Univ Fed Sao Carlos Dept Comp BR-13560 Sao Carlos SP Brazil

ISBN: (纸本)9780769534237

this work presents an implementation of Neocognitron Neural Network, using a high performance computing architecture based on GPU (graphics processing Unit). Neocognitron is an artificial neural network, proposed by Fukushima and collaborators, constituted of several hierarchical stages of neuron layers, organized in. two-dimensional matrices called cellular planes. For the high performance computation of Face Recognition application using Neocognitron it was used CUDA (Compute Unified Device Architecture) as API (Application Programming Interface) between the CPU and the GPU, from GeForce 8800 GTX of NVIDIA company, with 128 ALU's. As face image databases it was used a face database created at UFS-Car and the CMU-PIE (Carnegie Mellon University Pose, Illumination and Expression) database. the load balancing was achieved through the use of cellular connections as threads organized in blocks, following the CUDA philosophy), of development. the results showed the feasibility of this type of device as a massively parallel data processing tool, and that smaller the granularity and the data dependency of the parallel processing, better is its performance.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Selection of windows for W-operator combination from entropy based ranking 28

Selection of windows for W-operator combination from entropy...

引用

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Dornelles, Marta M. Hirata, Nina S. T. Univ Estadual Santa Cruz Dept Exact & Technol Sci Ilheus BA Brazil Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil

ISBN: (纸本)9781467379625

When training morphological operators that are locally defined with respect to a neighborhood window, one must deal with the tradeoff between window size and statistical precision of the learned operator. More precisely, too small windows result in large restriction errors due to the constrained operator space and, on the other hand, too large windows result in large variance error due to often insufficient number of samples. A two-level training method that combines a number of operators designed on distinct windows of moderate size is an effective way to mitigate this issue. However, in order to train combined operators, one must specify not only how many operators will be combined, but also the windows for each of them. To date, a genetic algorithm that searches for window combinations has produced the best results for this problem. In this work we propose an alternative approach that is computationally much more efficient. the proposed method consists in efficiently reducing the search space by ranking windows of a collection according to an entropy based measure estimated from input-output joint probabilities. Computational efficiency comes from the fact that only few operators need to be trained. Experimental results show that this method produces results that outperform the best results obtained with manually selected combinations and are competitive with results obtained with the genetic algorithm based solution. the proposed approach is, thus, a promising step towards fully automating the process of binary morphological operator design.

关键词： binary image morphological operator design W-operator combination conditional entropy sequential forward selection

来源：评论

学校读者我要写书评

暂无评论

Coordinate multi-robotic system for image taking and visualization via photogrammetry 14

Coordinate multi-robotic system for image taking and visuali...

引用

14th Latin American Robotics symposium and 5th brazilian symposium on Robotics, LARS-SBR 2017

作者： De Souza, Arthur Rosa Raad, Rita Batista, Murillo Rehder Romero, Roseli Aparecida Francelin Institute of Mathematics and Computer Sciences São Paulo São Carlos Brazil

ISBN: (纸本)9781538609569

the growth of 3D visualization devices, such as holograms and virtual reality, is followed by the increase of demand for 3D models. One cheap and straightforward way of creating them is by photogrammetry. However, taking the necessary photographs is tedious and imprecise, because many different shooting angles and heights are required. Also, there may be need of doing models of objects placed on hazardous environments. In this paper, our objective is to create a multirobot system capable of taking multiple bi-dimensional images of an object for further generation of a 3D representation of this object. this approach has the benefit of scalability, increasing security and reliability. © 2017 IEEE.

关键词： Photogrammetry

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Patch Partitioning for image Inpainting Based on Visual Transformers 35

Multi-Scale Patch Partitioning for Image Inpainting Based on...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Campana, Jose Luis Flores Decker, Luis Gustavo Lorgus Roberto e Souza, Marcos Maia, Helena de Almeida Pedrini, Helio Univ Estadual Campinas Inst Comp BR-13083852 Campinas SP Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

image inpainting is a challenging task that aims to reconstruct missing pixels with semantically coherent content and realistic texture using available information. Modern inpainting works rely on neural networks to generate realistic images. However, due to their limited receptive field in convolution operators, they may produce distorted content when a large region needs to be filled. Recent methods have employed transformers to deal with this problem, but their high computational cost makes it difficult to work with global image information. To address this, we propose a multi-scale patch partitioning strategy to subdivide feature maps into non-overlapping patches, and a transformer with a variable number of heads to control the computational cost growth according to the number of patches. Smaller patches enable a broader image coverage, helping to recover structural information, whereas larger patches lead to a reduced computational cost. In contrast to the fixed and small sizes employed in other literature methods, here we explore different patch sizes in the transformer blocks to achieve a good balance between the computational cost and the number of pixel references used in the reconstruction. Extensive experiments on three datasets show that our method achieves very competitive results compared to the state of the art, reaching the best scores in various scenarios, especially for metrics based on human perception. Moreover, our model presented the smallest size. Our qualitative results suggest that the proposed method is able to reconstruct structural content such as parts of human faces.

关键词： image inpainting visual transformers multi-scale patch partitioning

来源：评论

学校读者我要写书评

暂无评论

Employing a fully convolutional neural network for road marking detection 14

Employing a fully convolutional neural network for road mark...

引用

14th Latin American Robotics symposium and 5th brazilian symposium on Robotics, LARS-SBR 2017

作者： Horita, Luiz Ricardo T. Grassi, Valdir Electrical Engineering with the Intelligent Systems Laboratory Department of Electrical and Computer Engineering University of São Paulo São Carlos Brazil

ISBN: (纸本)9781538609569

Since road markings are one of the main landmarks used for traffic guidance, perceiving them may be a crucial task for autonomous vehicles. In visual approaches, road marking detection consists in detecting pixels of an image that corresponds to a road marking. Recently, most approaches have aimed on detecting lane markings only, and few of them proposed methods to detect other types of road markings. Moreover, most of those approaches are based on local gradient, which provides noisy detections caused by cluttered images. In this paper, we propose an alternative approach based on a deep Fully Convolutional Neural Network (FCNN) with an encoder-decoder architecture for road marking detection and segmentation. the experimental results reveal that the proposed approach can detect any road marking type in a high level of accuracy, resulting in a smooth segmentation. © 2017 IEEE.

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Video Skimming with Adaptive Hierarchical Shot Detection 37

Unsupervised Video Skimming with Adaptive Hierarchical Shot ...

引用

37th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Cardoso, Leonardo Vilela Werneck, July F. M. Guimaraes, Silvio Jamil E. Patrocinio, Zenilton K. G., Jr. Pontifical Catholic Univ Minas Gerais PUC Minas Lab Image & Multimedia Data Sci IMSci Belo Horizonte MG Brazil

ISBN: (纸本)9798350376043;9798350376036

Video skimming involves generating a concise representation that captures all its significant information. However, conventional skimming techniques often fail to capture different shots in a video due to their inability to detect scene modifications and incorporate the hierarchical structure of video content. this work proposes an unsupervised hierarchical method for video skimming, called Hierarchical Time-aware Skimming - HieTaSkim, in which video content is modeled as a graph, and an adaptive strategy is employed to produce hierarchical graph cuts. those cuts are used to identify the most relevant video segments or keyshots, allowing the extraction of frames' sequences that convey the video's central message and resulting in a more effective and accurate video summary. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art unsupervised methods for video skimming, achieving in the SumMe dataset an F-score of 39.9 which represents an improvement of 10% at least.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Domain Generalization in Medical image Segmentation via Meta-Learners 35

Domain Generalization in Medical Image Segmentation via Meta...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Oliveira, Hugo Cesar, Roberto M., Jr. Gama, Pedro H. T. dos Santos, Jefersson A. Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte Brazil Univ Stirling Comp Sci & Math Stirling Scotland

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Automatic and semi-automatic radiological image segmentation can help physicians in the processing of real-world medical data for several tasks such as detection/diagnosis of diseases and surgery planning. Current segmentation methods based on neural networks are highly data-driven, often requiring hundreds of laborious annotations to properly converge. the generalization capabilities of traditional supervised deep learning are also limited by the insufficient variability present in the training dataset. One very proliferous research field that aims to alleviate this dependence on large numbers of labeled data is Meta-Learning. Meta-Learning aims to improve the generalization capabilities of traditional supervised learning by training models to learn in a label efficient manner. In this tutorial we present an overview of the literature and proposed ways of merging this body of knowledge with deep segmentation architectures to produce highly adaptable multi-task meta-models for few-shot weakly-supervised semantic segmentation. We introduce a taxonomy to categorize Meta-Learning methods for both classification and segmentation, while also discussing how to adapt potentially any few-shot meta-learner to a weakly-supervised segmentation task.

关键词： meta-learning few-shot learning semantic segmentation medical imaging domain generalization

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：