Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI)最新文献_第4页

Classificação da densidade mamária em mamografias utilizando redes neurais convolucionais 用卷积神经网络对乳房x光片中的乳房密度进行分类

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8325

M. F. Carvalho, Alexei Manso Correa Machado

引用次数: 1

Development of Embedded Algorithm for Visual Simultaneous Localization and Mapping 嵌入式视觉同步定位与映射算法的开发

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8319

P. Rosa, Onias C. B. Silveira, J. D. Melo, L. Moreira, L. R. L. Rodrigues

引用次数: 1

Classificação de Imagens de Raio-x de Torax com Reconhecimento Visual da IBM Cloud para Diagnóstico de Pneumonia 用于肺炎诊断的IBM云视觉识别Torax x射线图像分类

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8330

Raianny Proença de Camargo De Oliveira, Guilherme Rodrigues Sganderla, C. Mauricio, F. F. F. Peres

{"title":"Classificação de Imagens de Raio-x de Torax com Reconhecimento Visual da IBM Cloud para Diagnóstico de Pneumonia","authors":"Raianny Proença de Camargo De Oliveira, Guilherme Rodrigues Sganderla, C. Mauricio, F. F. F. Peres","doi":"10.5753/sibgrapi.est.2019.8330","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2019.8330","url":null,"abstract":"A capacidade de aprender por meio de exemplos e formular predições são as principais características do Machine Learning, uma subárea da inteligência artificial. Existem diversos frameworks disponíveis que utilizam Machine Learning para solução dos mais variados tipos de problemas, como para reconhecer e classificar objetos em uma imagem. Utilizando os serviços fornecidos por IBM Watson Visual Recognition que emprega algoritmos de deep learning, uma subárea de Machine learning, um modelo foi criado e aplicado no dataset Chest X-Ray Images for Classification. Os resultados obtidos com o modelo criado foram comparados com a classificação geral fornecida pela IBM. Os serviços utilizados da Watson Visual Recognition são os disponibilizados para o plano do tipo Lite, um plano gratuito. Este trabalho discute como esta limitação afetou os resultados e descreve a eficiência da ferramenta nesta versão. Mesmo com as limitações o modelo obtido reconheceu corretamente um pulmão saudável em 75% das imagens de teste e classificou corretamente 93,34% das imagens de radiografias de tórax que retratam pneumonia.","PeriodicalId":119031,"journal":{"name":"Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115824328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Detecção de Desfolha de Soja Utilizando Redes Neurais Convolucionais 利用卷积神经网络检测大豆落叶

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8317

Patrik Olã Bressan, Wesley Nunes Gonçalves

引用次数: 1

Unsupervised Selective Rank Fusion on Content-Based Image Retrieval 基于内容的图像检索中的无监督选择性秩融合

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8303

Lucas Pascotti Valem, D. C. G. Pedronette

{"title":"Unsupervised Selective Rank Fusion on Content-Based Image Retrieval","authors":"Lucas Pascotti Valem, D. C. G. Pedronette","doi":"10.5753/sibgrapi.est.2019.8303","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2019.8303","url":null,"abstract":"Mainly due to the evolution of technologies to store and share images, the growth of image collections have been remarkable for years. Therefore, developing effective methods to index and retrieve such extensive available visual information is indispensable. The CBIR (Content-Based Image Retrieval) systems are one of the main solutions for image retrieval tasks. These systems are mainly supported by the use of different visual descriptors and machine learning methods. Despite the relevant advances in the area, mainly driven by deep learning technologies, accurately computing the similarity between images remains a complex task in various scenarios due to the well known semantic gap problem. As distinct features produce complementary ranking results with different effectiveness performance, a promising solution consists in combining them. However, how to decide which visual features to combine is a very challenging task. This work proposes three novel methods for selecting and combining ranked lists by estimating their effectiveness in an unsupervised way. The approaches were evaluated in five different image collections and several descriptors, achieving results comparable or superior to the state-of-the-art in most of the evaluated scenarios.","PeriodicalId":119031,"journal":{"name":"Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122143135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Use of reorderable matrices and heatmaps to support data analysis of students transcripts 使用可重新排序的矩阵和热图来支持学生成绩单的数据分析

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-10-09 DOI: 10.5753/sibgrapi.est.2019.8334

Rafael Tavares Carvalho Barros, Thiago Gonçalves Mendes, C. D. Silva

引用次数: 2

Digital Video Stabilization: Algorithms and Evaluation 数字视频稳定:算法和评估

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2019-06-26 DOI: 10.5753/sibgrapi.est.2019.8299

M. R. Souza, H. Pedrini

引用次数: 10

Human Activity Recognition based on Wearable Sensors using Multiscale DCNN Ensemble 基于多尺度DCNN集成的可穿戴传感器人体活动识别

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2018-10-18 DOI: 10.5753/sibgrapi.est.2019.8310

Jessica Sena, W. R. Schwartz

{"title":"Human Activity Recognition based on Wearable Sensors using Multiscale DCNN Ensemble","authors":"Jessica Sena, W. R. Schwartz","doi":"10.5753/sibgrapi.est.2019.8310","DOIUrl":"https://doi.org/10.5753/sibgrapi.est.2019.8310","url":null,"abstract":"Sensor-based Human Activity Recognition (HAR) provides valuable knowledge to many areas. Recently, wearable devices have gained space as a relevant source of data. However, there are two issues: large number of heterogeneous sensors available and the temporal nature of the sensor data. To handle these issues, we propose a multimodal approach that processes each sensor separately and, through an ensemble of Deep Convolution Neural Networks (DCNN), extracts information from multiple temporal scales of the sensor data. In this ensemble, we use a convolutional kernel with a different height for each DCNN. Considering that the number of rows in the sensor data reflects the data captured over time, each kernel height reflects a temporal scale from which we can extract patterns. Consequently, our approach is able to extract information from simple movement patterns such as a wrist twist when picking up a spoon, to complex movements such as the human gait. This multimodal and multi-temporal approach outperforms previous state-of-the-art works in seven important datasets using two different protocols. In addition, we demonstrate that the use of our proposed set of kernels improves sensor-based HAR in another multi-kernel approach, the widely employed inception network.","PeriodicalId":119031,"journal":{"name":"Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"55 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131726734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

An Efficient Hierarchical Layered Graph Approach for Multi-Region Segmentation 一种高效的分层图多区域分割方法

Anais Estendidos da Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 1900-01-01 DOI: 10.5753/sibgrapi.est.2019.8301

L. C. Leon, K. Ciesielski, P. A. Miranda

引用次数: 0