2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)最新文献

Fast Spatial-Temporal Transformer Network 快速时空变压器网络

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00018

R. Escher, Rodrigo Andrade de Bem, P. L. J. Drews

引用次数: 1

Data Augmentation Guidelines for Cross-Dataset Transfer Learning and Pseudo Labeling 跨数据集迁移学习和伪标记的数据增强指南

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00036

Fernando Pereira dos Santos, Gabriela Thume, M. Ponti

引用次数: 1

Automatic Segmentation of Posterior Fossa Structures in Pediatric Brain MRIs 儿童脑mri后窝结构的自动分割

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00025

Hugo Oliveira, L. Penteado, Jose Luiz Maciel, S. Ferraciolli, M. Takahashi, I. Bloch, R. M. C. Junior

{"title":"Automatic Segmentation of Posterior Fossa Structures in Pediatric Brain MRIs","authors":"Hugo Oliveira, L. Penteado, Jose Luiz Maciel, S. Ferraciolli, M. Takahashi, I. Bloch, R. M. C. Junior","doi":"10.1109/sibgrapi54419.2021.00025","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00025","url":null,"abstract":"Pediatric brain MRI is a useful tool in assessing the healthy cerebral development of children. Since many pathologies may manifest in the brainstem and cerebellum, the objective of this study was to have an automated segmentation of pediatric posterior fossa structures. These pathologies include a myriad of etiologies from congenital malformations to tumors, which are very prevalent in this age group. We propose a pediatric brain MRI segmentation pipeline composed of preprocessing, semantic segmentation and post-processing steps. Segmentation modules are composed of two ensembles of networks: generalists and specialists. The generalist networks are responsible for locating and roughly segmenting the brain areas, yielding regions of interest for each target organ. Specialist networks can then improve the segmentation performance for underrepresented organs by learning only from the regions of interest from the generalist networks. At last, post-processing consists in merging the specialist and generalist networks predictions, and performing late fusion across the distinct architectures to generate a final prediction. We conduct a thorough ablation analysis on this pipeline and assess the superiority of the methodology in segmenting the brain stem, 4th ventricle and cerebellum. The proposed methodology achieved a macro-averaged Dice index of 0.855 with respect to manual segmentation, with only 32 labeled volumes used during training. Additionally, average distances between automatically and manually segmented surfaces remained around 1mm for the three structures, while volumetry results revealed high agreement between manually labeled and predicted regions.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126615404","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: 3

Combination of Optical Character Recognition Engines for Documents Containing Sparse Text and Alphanumeric Codes 包含稀疏文本和字母数字代码文档的光学字符识别引擎组合

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00048

Iago Correa, P. L. J. Drews, R. Rodrigues

{"title":"Combination of Optical Character Recognition Engines for Documents Containing Sparse Text and Alphanumeric Codes","authors":"Iago Correa, P. L. J. Drews, R. Rodrigues","doi":"10.1109/sibgrapi54419.2021.00048","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00048","url":null,"abstract":"Many companies that buy machines, parts, or tools retain documents such as notes, receipts, forms, or instruction manuals over the years, and they may find themselves in need of digitizing these accumulated documents. Thus, when using optical character recognition (OCR) systems in these documents, it is possible to note that these systems can present two main difficulties. The first is to locate the sparse text in a noncontinuous way, and the second is to match words that are closer to codes and less to words in human language. Although there are many works in the literature about sparse texts, such as forms and tables, there is usually not much concern about the issue with codes in which one can not rely on dictionaries or even both problems together. Therefore, to correct this issue without having to search for extensive databases or conduct training and development of new models, this work proposed to take advantage of pre-trained models of OCR such as from the Tesseract engine or the Google Cloud’s Vision API. In order to do so, we proposed the exploration of combination strategies, including a new one based on median string. The experimental results achieved up to 3.09% improvement in character accuracy and 1.16% in word accuracy in comparison to the best individual performances from the engines when our method based on string combination was adopted.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"2020 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121460664","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

A System for Visual Analysis of Objects Behavior in Surveillance Videos 一种监控视频中物体行为的视觉分析系统

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00032

Cibele Mara Fonseca, J. G. Paiva

{"title":"A System for Visual Analysis of Objects Behavior in Surveillance Videos","authors":"Cibele Mara Fonseca, J. G. Paiva","doi":"10.1109/sibgrapi54419.2021.00032","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00032","url":null,"abstract":"Closed-circuit television (CCTV) surveillance systems are employed in different scenarios to prevent a variety of threats, producing a large volume of video footage. Several surveillance tasks consist of detecting/tracking moving objects in the scene to analyze their behavior and comprehend their role in events that occur in the video. Such analysis is unfeasible if manually performed, due to the large volume of long duration videos, as well as due to intrinsic human limitations, which may compromise the perception of multiple strategic events. Most of smart surveillance approaches designed for moving objects analysis focus only on the detection/tracking process, providing a limited comprehension of objects behavior, and rely on automatic procedures with no/few user interaction, which may hamper the comprehension of the produced results. Visual analytics techniques may be useful to highlight behavior patterns, improving the comprehension of how the objects contribute to the occurrence of observed events in the video. In this work, we propose a video surveillance visual analysis system for identification/ exploration of objects behavior and their relationship with events occurrence. We introduce the Appearance Bars layout to perform a temporal analysis of each object presence in the scene, highlighting the involved dynamics and spatial distribution, as well as its interaction with other objects. Coordinated with other support layouts, these bars represent multiple aspects of the objects behavior during video extent. We demonstrate the utility of our system in surveillance scenarios that shows different aspects of objects behavior, which we relate to events that occur in the videos.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116014798","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

Towards a Simple and Efficient Object-based Superpixel Delineation Framework 一个简单有效的基于对象的超像素描绘框架

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00054

F. Belém, B. Perret, J. Cousty, S. Guimarães, A. Falcão

引用次数: 2

Reducing the need for bounding box annotations in Object Detection using Image Classification data 使用图像分类数据减少目标检测中对边界框注释的需求

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00035

Leonardo Blanger, N. Hirata, Xiaoyi Jiang

引用次数: 0

BORDE: Boundary and Sub-Region Denormalization for Semantic Brain Image Synthesis 语义脑图像合成的边界和子区域非规范化

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00020

Israel N. Chaparro-Cruz, Javier A. Montoya-Zegarra

{"title":"BORDE: Boundary and Sub-Region Denormalization for Semantic Brain Image Synthesis","authors":"Israel N. Chaparro-Cruz, Javier A. Montoya-Zegarra","doi":"10.1109/sibgrapi54419.2021.00020","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00020","url":null,"abstract":"Medical images are often expensive to acquire and offer limited use due to legal issues besides the lack of consistency and availability of image annotations. Thus, the use of medical datasets can be restrictive for training deep learning models. The generation of synthetic images along with their corresponding annotations can therefore aid to solve this issue. In this paper, we propose a novel Generative Adversarial Network (GAN) generator for multimodal semantic image synthesis of brain images based on a novel denormalization block named BOundary and sub-Region DEnormalization (BORDE). The new architecture consists of a decoder generator that allows: (i) an effectively sequential propagation of a-priori semantic information through the generator, (ii) noise injection at different scales to avoid mode-collapse, and (iii) the generation of rich and diverse multimodal synthetic samples along with their contours. Our model generates very realistic and plausible synthetic images that when combined with real data helps to improve the accuracy in brain segmentation tasks. Quantitative and qualitative results on challenging multimodal brain imaging datasets (BraTS 2020 [1] and ISLES 2018 [2]) demonstrate the advantages of our model over existing image-agnostic state-of-the-art techniques, improving segmentation and semantic image synthesis tasks. This allows us to prove the need for more domain-specific techniques in GANs models.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116342598","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

Non-local medians filter for joint Gaussian and impulsive image denoising 非局部中值滤波用于联合高斯和脉冲图像去噪

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00029

A. Levada

引用次数: 0

Simplifying Horizon Picking Using Single-Class Semantic Segmentation Networks 用单类语义分割网络简化水平选取

2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) Pub Date : 2021-10-01 DOI: 10.1109/sibgrapi54419.2021.00046

Danilo Calhes, F. Kobayashi, Andréa Britto Mattos, M. Macedo, Dário A. B. Oliveira

{"title":"Simplifying Horizon Picking Using Single-Class Semantic Segmentation Networks","authors":"Danilo Calhes, F. Kobayashi, Andréa Britto Mattos, M. Macedo, Dário A. B. Oliveira","doi":"10.1109/sibgrapi54419.2021.00046","DOIUrl":"https://doi.org/10.1109/sibgrapi54419.2021.00046","url":null,"abstract":"Seismic image processing plays a significant role in geological exploration as it conditions much of the interpretation performance. The interpretation process comprises several tasks, and Horizon Picking is one of the most time-consuming. Thereat, several works proposed methods for picking horizons automatically, mostly focusing on increasing the accuracy of data-driven approaches, by employing, for instance, semantic segmentation networks. However, these works often rely on a training process that requires several annotated samples, which are known to be scarce in the seismic domain, due to the overwhelming effort associated with manually picking several horizons in a seismic cube. This paper aims to evaluate the simplification of the labeling process required for training, by using training samples composed of disconnected horizons tokens, therefore relaxing the requirement of annotating the full set of horizons from each training sample, as commonly observed in previous works employing semantic segmentation networks. We assessed two state-of-art neural networks for general-purpose domains (PSP-Net and Deeplab V3+) using public seismic data (Netherlands F3 Block dataset). Our results report a minor impact in the performance using our proposed incomplete token training scheme compared to the complete one, moreover, we report that these networks outperform the current state-of-art for horizon picking from small training sets. Thus, our approach proves to be advantageous for the interpreter, given that using partial results instead of providing a full annotation can reduce the user effort during the labeling process required for training the models.","PeriodicalId":197423,"journal":{"name":"2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128077690","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