检索结果-内蒙古大学图书馆

29th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Spina, thiago Vallin Martins, Samuel Botter Falcao, Alexandre Xavier Univ Estadual Campinas Inst Comp Campinas SP Brazil

ISBN: (纸本)9781509035687

Interactive 3D object segmentation is an important and challenging activity in medical imaging, although it is tedious and error-prone to be done. Automatic segmentation methods aim to replace the user altogether, but require user interaction to produce training data sets of segmented masks and to make error corrections. We propose a complete framework for interactive medical image segmentation, which reduces user effort by automatically providing an initial segmentation result. We develop a Statistical Seed Model (SSM) to this end, that improves from seed sets selected by robot users when reconstructing masks of previously segmented images. the SSM outputs a seed set that may be used to automatically delineate a new test image. the seeds provide both an implicit object shape constraint and a flexible way of interactively correcting segmentation. We demonstrate that our framework decreases the amount of user interaction by a factor of three, when segmenting MR-images of the cerebellum.

关键词： Interactive Medical image Segmentation Object Models Robot Users Segmentation Resuming

来源：评论

学校读者我要写书评

暂无评论

Towards local control for image-based texture synthesis

Towards local control for image-based texture synthesis

引用

15th brazilian symposium on computer graphics and image processing

作者： Tonietto, L Walter, M Univ Vale Rio dos Sinos Ctr Ciencias Exatas & Tecnol PIPCA Mestrado Comp Aplicada Sao Leopoldo Brazil

ISBN: (纸本)076951846X

New advances in image based texture synthesis techniques allow the generation of arbitrarily sized textures based on a small sample. the generated textures are perceived as very similar to the given sample. One main drawback of these techniques, however, is that the synthesized result cannot be locally controlled, that is, we are able to synthesize a larger version of the sample but without much variation. We present in this paper a technique which improves on current fast texture synthesis techniques by allowing local control over the result. By local control we mean a final texture that is still perceived as a whole but presents variations in size of the basic elements. Our solution generates the final texture from a small collection of the same sample at different resolutions, adequately interpolated. We illustrate our results with some examples, including natural textures such as animal coat patterns, which exhibit local variations that can be adequately captured by our algorithm.

关键词： image texture

来源：评论

学校读者我要写书评

暂无评论

Combining wavelets and watersheds for robust multiscale image segmentation

引用

image AND VISION COMPUTING 2007年第1期25卷 24-33页

作者： Jung, Claudio Rosito Univ Vale Rio dos Sinos PIPCA Grad Sch Appl Comp BR-93022000 Sao Leopoldo RS Brazil

this paper proposes a new segmentation technique that combines multiresolution wavelet decompositions with the watershed transform. the wavelet transform is applied to the intensity image, producing detail and approximation coefficients. Gradient magnitudes of the approximation image at the coarsest resolution are computed, and an adaptive threshold is used to remove small gradient magnitudes. the watershed transform is then applied, and the segmented image is projected up to higher resolutions using inverse wavelet transforms. Typically, if a low resolution is chosen for the initial segmentation, large relevant objects will be captured;on the other hand, a higher initial resolution will lead to smaller (and more detailed) segmented objects. the low-pass filtering involved in the wavelet decomposition provides robust segmentation results for noisy images, even when the amount of noise is very large. (c) 2006 Elsevier B.V. All rights reserved.

关键词： segmentation watersheds wavelets multiresolution denoising region merging

来源：评论

学校读者我要写书评

暂无评论

A Zero-Shot image Enhancement Method Based on Human Skin Tone Reference 36

A Zero-Shot Image Enhancement Method Based on Human Skin Ton...

引用

36th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Oliveira, Diulhio Lopes, Alexandre Luquezi, Vitor Galassi Nogueira, Carlos Eduardo Schiezaro, Mauricio Liu, Dennis Pedrini, Helio Venturus Innovat & Technol BR-13086530 Campinas SP Brazil Univ Estadual Campinas Inst Comp BR-13083852 Campinas SP Brazil Compal Elect Inc Taipei 11492 Taiwan

ISBN: (纸本)9798350338737;9798350338720

In this work, we introduce a zero-shot method for color enhancement in images containing people. this method is based on photo edition techniques used by professional editors, where these professionals adjust the RGB curves, which affects the image colors globally. the hypothesis adopted in this investigation is that, when there are people present in an image, they become the most important element of the scene, so one of the main aspects of color adjustment is to make their skin tones look more realistic and natural, which should please most of the viewers. the proposed method employs a pipeline of classical algorithms of computer vision to mimic the process applied by professional photo editors. Experiments performed on the Adobe-MIT 5k dataset, a widely used dataset on image enhancement, show that our approach has similar performance compared to supervised data-driven state-of-art methods.

关键词： image enhancement skin tone deep learning zero-shot method

来源：评论

学校读者我要写书评

暂无评论

Measuring the influence of painters through artwork facial features 35

Measuring the influence of painters through artwork facial f...

引用

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

作者： Dalmoro, Bruna Monteiro, Charles Musse, Soraia Raupp Pontif Catholic Univ Rio Grande Do Sul Grad Program Comp Sci Porto Alegre Brazil Pontif Catholic Univ Rio Grande Do Sul Grad Program Hist Porto Alegre Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Computational aesthetics is a subfield of computer vision that seeks to understand the human aesthetic perception of images and image sequences. the main objective is to create systems that allow different aesthetic decisions, trying to approximate the judgment of a human being about the images. In this work, we explore the problem of identifying influence among artists based on visual features detected in their artworks. In particular, we are interested in investigating the similarity of faces in paintings to design the artists' influence. In our methodology, we propose four groups of features to characterize the faces, and we show that the similarity of faces to finding artists' influence, shows promising results when compared to the recently proposed methods.

关键词： Visualization computer vision Feature extraction image sequences Faces Facial features Painting

来源：评论

学校读者我要写书评

暂无评论

Handwriting Synthesis from Public Fonts 30

Handwriting Synthesis from Public Fonts

引用

30th Conference on graphics, Patterns and images (SIBGRAPI)

作者： Balreira, Dennis G. Walter, M. Univ Fed Rio Grande do Sul Inst Informat Porto Alegre RS Brazil

ISBN: (纸本)9781538622193

Handwriting synthesis generates renderings of text which look like they were written by a human but are in fact synthesized by a model. From an input sample of the desired handwriting, we introduce an algorithm that finds the best match between characters using as source for the output text the large collection of publicly available fonts designed to look like handwriting. For each character in the desired output text, we find the best match among the public fonts using a metric that matches both the shape and appearance of the input real character. Once we have the set of best characters we build the output sentence or paragraph by concatenation of individual characters. Our results show that even though human calligraphy is highly individual and specialized, visually similar renderings are possible for many applications that do not demand full similarity. On a user study with 12 subjects, our synthesis results were considered, on average, 71% similar to the input samples.

关键词： Shape CAPTCHAs Writing Rendering (computer graphics) Handwriting recognition Portals Skeleton

来源：评论

学校读者我要写书评

暂无评论

A Comparative Evaluation of Transformer-Based Vision Encoder-Decoder Models for brazilian Portuguese image Captioning 37

A Comparative Evaluation of Transformer-Based Vision Encoder...

引用

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

作者： Bromonschenkel, Gabriel Oliveira, Hilark Paixao, thiago M. Inst Fed Espirito Santo IFES Programa Posgrad Comp Aplicada PPComp Serra Brazil

ISBN: (纸本)9798350376043;9798350376036

image captioning refers to the process of creating a natural language description for one or more images. this task has several practical applications, from aiding in medical diagnoses through image descriptions to promoting social inclusion by providing visual context to people with impairments. Despite recent progress, especially in English, low-resource languages like brazilian Portuguese face a shortage of datasets, models, and studies. this work seeks to contribute to this context by fine-tuning and investigating the performance of vision language models based on the Transformer architecture in brazilian Portuguese. We leverage pre-trained vision model checkpoints (ViT, Swin, and DeiT) and neural language models (BERTimbau, DistilBERTimbau, and GPorTuguese-2). Several experiments were carried out to compare the efficiency of different model combinations using the #PraCegoVer-63K, a native Portuguese dataset, and a translated version of the Flickr30K dataset. the experimental results demonstrated that configurations using the Swin, DistilBERTimbau, and GPorTuguese-2 models generally achieved the best outcomes. Furthermore, the #PraCegoVer-63K dataset presents a series of challenges, such as descriptions made up of multiple sentences and the presence of proper names of places and people, which significantly decrease the performance of the investigated models.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Text/non-text classification of connected components in document images 30

Text/non-text classification of connected components in docu...

引用

30th Conference on graphics, Patterns and images (SIBGRAPI)

作者： Julca-Aguilar, Frank D. Maia, Ana L. L. M. Hirata, Nina S. T. Univ Sao Paulo Inst Math & Stat Dept Comp Sci Sao Paulo Brazil State Univ Feira de Santana UEFS Dept Exact Sci Feira De Santana Brazil

ISBN: (纸本)9781538622193

Text segmentation is an important problem in document analysis related applications. We address the problem of classifying connected components of a document image as text or non-text. Inspired from previous works in the literature, besides common size and shape related features extracted from the components, we also consider component images, without and with context information, as inputs of the classifiers. Multi-layer perceptrons and convolutional neural networks are used to classify the components. High precision and recall is obtained with respect to both text and non-text components.

关键词： Feature extraction Training image segmentation Shape Data mining Neural networks Layout

来源：评论

学校读者我要写书评

暂无评论

Using 3D Texture and Margin Sharpness Features on Classification of Small Pulmonary Nodules 29

Using 3D Texture and Margin Sharpness Features on Classifica...

引用

29th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Felix, Ailton Oliveira, Marcelo Machado, Aydano Raniery, Jose Fed Univ Alagoas UFAL IC Maceio Alagoas Brazil Univ Sao Paulo Ribeirao Preto Med Sch FMRP Sao Paulo Brazil

ISBN: (纸本)9781509035687

the lung cancer is the reason of a lot of deaths on population around the world. An early diagnosis brings a most curable and simpler treatment options. Due to complexity diagnosis of small pulmonary nodules, computer-Aided Diagnosis (CAD) tools provides an assistance to radiologist aiming the improvement in the diagnosis. Extracting relevant image features is of great importance for these tools. In this work we extracted 3D Texture Features (TF) and 3D Margin Sharpness Features (MSF) from the Lung image Database Consortium (LIDC) in order to create a classification model to classify small pulmonary nodules with diameters between 3-10mm. We used three machine learning algorithm: k-Nearest Neighbor (k-NN), Multilayer Perceptron (MLP) and Random Forest (RF). these algorithms were trained by different set of features from the TF and MSF. the classification model with MLP algorithm using the selected features from the integration of TF and MSF achieved the best AUC of 0.820.

关键词： lung cancer small nodules early diagnosis computer-aided diagnosis texture features margin sharpness features classification machine learning

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Holistic Skin Detection 34

Domain Adaptation for Holistic Skin Detection

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Dourado, Aloisio Guth, Frederico de Campos, Teofilo Li Weigang Univ Brasilia UnB Dept Ciencia Comp CIC Brasilia DF Brazil

ISBN: (纸本)9781665423540

Human skin detection in images is a widely studied topic of computer Vision for which it is commonly accepted that analysis of pixel color or local patches may suffice. However, we found that the lack of contextual information may hinder the performance of local approaches. In this paper, we present a comprehensive evaluation of holistic and local Convolutional Neural Network (CNN) approaches on in-domain and cross-domain experiments and compare them with state-of-the-art pixel-based approaches. We also propose combining inductive transfer learning and unsupervised domain adaptation methods evaluated on different domains under several amounts of labelled data availability. We show a clear superiority of CNN over pixel-based approaches even without labeled training samples on the target domain and provide experimental support for the superiority of holistic over local approaches for human skin detection.

关键词： Training graphics computer vision image color analysis Transfer learning Skin Convolutional neural networks

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：