Tania Centeno | Universidade Federal do Paraná (original) (raw)
Papers by Tania Centeno
Environmental Science and Engineering, 2000
ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of space... more ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of spaces through the course of time emerge more and more as a special interest issue in research about the environment. This evolution constitutes one of the major concerns in the domain of environmental space management. The landscape evolution of a regional area and the perspectives for a future state raise particularly important issue. What will the state of the region be in 15, 30 or 50 years? Time can produce transformations over a regional area such as emergence, disappearance or the union of spatial entities. These transformations are called temporal phenomena. We propose two different methods to predict the forestry development for the forthcoming years in the experimental area, which reveals these spatial transformations. The proposed methods are based on fuzzy logic and Cellular Automata (CA). The methods are supported by the analysis of the landscape dynamics of a test site located in a tropical rain forest country: the oriental piedmont of the Andes Mountains in Venezuela. This large area, at the scale of a Spot satellite image, is typical of tropical deforestation in a pioneer front. The presented approaches allow the geographer interested in environmental prospective problems to acquire type cartographical documents showing future conditions of a landscape. The experimental tests have showed promising results.
Computer Vision and Image Understanding
Electricity demand forecasts are required by companies who need to predict their customers’ deman... more Electricity demand forecasts are required by companies who need to predict their customers’ demand, and by those wishing to trade electricity as a commodity on financial markets. It is hard to find the right prediction method for a given application if not a prediction expert. Recent works show that Liquid State Machines (LSM’s) can be applied to the prediction of time series. The main advantage of the LSM is that it projects the input data in a high-dimensional dynamical space and therefore simple learning methods can be used to train the readout. In this paper we present an experimental investigation of an approach for the computation of time series prediction by employing Liquid State Machines (LSM) in the modeling of a predictor in a case study for short-term and long-term electricity demand forecasting. Results of this investigation are promising, considering the error to stop training the readout, the number of iterations of training of the readout and that no strategy of seas...
A detecção de descontinuidades em radiografias de soldas não é um trabalho trivial para a automat... more A detecção de descontinuidades em radiografias de soldas não é um trabalho trivial para a automatização via software. Há fatores que prejudicam a determinação de uma metodologia única em todas as imagens digitais, primeiramente, devido à complexidade em discernir defeitos que, em grande parte, têm características semelhantes a outras indicações que não constituem defeitos. Acrescenta-se a grande dificuldade a transpor, que é como agregar o conhecimento do inspetor laudista à ferramenta de laudo. Neste trabalho, foram pesquisadas na literatura diferentes soluções implementadas por diversos pesquisadores, além daquelas desenvolvidas pela equipe de autores deste artigo. As abordagens tradicionalmente existentes fazem uso de bancos de imagens uniformes e ‘bem comportadas’, próprias do ambiente acadêmico, as quais são muito diferentes das imagens obtidas em condições reais de trabalho, especialmente no campo. Assim, embora muitas técnicas que apresentam bons resultados acadêmicos tenham ...
Remote Sensing for Environmental Monitoring, GIS Applications, and Geology, 2002
ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of space... more ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of spaces in the course of time emerge more and more as a special interest issue in researches about the environment. This evolution constitutes one of the major concerns in the domain of environmental space management. The landscape evolution of a region area and the perspectives for a future state rises an issue particularly important. What will be the state of the region in 15, 30 or 50 years? Time can produce transformations over a region area like emergence, disappearance or union of spatial entities... These transformations are called temporal phenomena. We propose to predict the forestry evolution in the forthcoming years on an experimental area, which reveals these spatial transformations. The proposed method is based on the analysis of terrain landscape given a sequence of n satellite images, which represent the state of a region area in different years. For these purposes, we have developed a specific spatio-temporal prediction approach, linking results of forestry evolution analysis and fuzzy logic. The method is supported by the analysis of the landscape dynamics of a test-site located in a tropical rain country: the oriental piedmont of Andes Mountain in Venezuela. This large area - at the scale of a spot satellite image - is typical of tropical deforestation in a pioneer front. The presented approach allows the geographer interested in environmental prospective problems to get type cartographical documents showing future conditions of a landscape. The experimental tests have showed promising results.
Lecture Notes in Computer Science, 2008
Volume 3: Materials and Joining; Pipeline Automation and Measurement; Risk and Reliability, Parts A and B, 2006
ABSTRACT The current work contributes to the research in the area of pipelines non-destructive te... more ABSTRACT The current work contributes to the research in the area of pipelines non-destructive testing by presenting new methodologies for the automatic analysis of welds radiographs. Object recognition techniques based on genetic algorithms were used for the automatic weld bead detection. In addiction, we developed an image digital filter for the detection of defects in the weld bead zone. These methodologies were tested for 120 digital radiographs from carbon steel pipeline welded joints. These images were acquired by a storage phosphor system using double-wall radiographic exposing technique with single-wall radiographic viewing, according to the ASME V code. As a result, even defects that are hard to be detected by human vision are automatically highlighted and extracted from the whole image to be classified in the further stages of the weld inspection process.
Volume 2: Integrity Management; Poster Session; Student Paper Competition, 2006
Page 1. Proceedings of IPC'06 6th International Pipeline Conference September 25-29, 2006, C... more Page 1. Proceedings of IPC'06 6th International Pipeline Conference September 25-29, 2006, Calgary, Alberta, Canada IPC2006-10462 AUTOMATIC DETECTION OF PIPELINE COMPONENTS IN RADIOGRAPHS FOR CORROSION MONITORING ...
Remote Sensing for Geography, Geology, Land Planning, and Cultural Heritage, 1996
Lecture Notes in Computer Science, 2005
Page 1. F. Rothlauf et al. (Eds.): EvoWorkshops 2005, LNCS 3449, pp. 284293, 2005. © Springer-Ve... more Page 1. F. Rothlauf et al. (Eds.): EvoWorkshops 2005, LNCS 3449, pp. 284293, 2005. © Springer-Verlag Berlin Heidelberg 2005 Object Detection for Computer Vision Using a Robust Genetic Algorithm Tania Mezzadri Centeno ...
Proceedings of the 27th Annual ACM Symposium on Applied Computing - SAC '12, 2012
Several interpolation methods for preserving edges were proposed in literature. This work present... more Several interpolation methods for preserving edges were proposed in literature. This work presents a new interpolation technique simple and easy to implement based on clustering which aims to increase the resolution of a gray scale image preserving edges. Results showed that the technique is quite competitive and meets the stated goals.
Computer Vision and Image Understanding, 2006
... also emphasize that, since only items within a weld are of interest, it is preferred to extra... more ... also emphasize that, since only items within a weld are of interest, it is preferred to extract theweld from each ... article presents a new approach, based on object detection and recognition techniques, for the first step of this image analysis process, ie, segmentation of the ...
ABSTRACT This paper describes a system that integrates three-dimensional re-construction methods ... more ABSTRACT This paper describes a system that integrates three-dimensional re-construction methods and rapid prototyping techniques, providing a more efficient design of medical models from tomographic im-ages using cost-effective manufacturing techniques. The similarity between the CT and MRI cross-sectional images and the 2D data used in rapid prototyping encourages the integration of these two technologies. The use of rapid prototyping systems can provide many advantages for medical applications, allowing surgical plan-ning, visualization of specific anatomy, implant design and pros-thesis fabrication. A fast and robust reconstruction method is pro-posed to approximate the external surfaces of complex objects. An automatic interface is also provided to convert the resulting images into a format that is recognized by the rapid prototyping machines. Several synthesized and real objects are used to demonstrate the performance of our method.
Environmental Science and Engineering, 2000
ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of space... more ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of spaces through the course of time emerge more and more as a special interest issue in research about the environment. This evolution constitutes one of the major concerns in the domain of environmental space management. The landscape evolution of a regional area and the perspectives for a future state raise particularly important issue. What will the state of the region be in 15, 30 or 50 years? Time can produce transformations over a regional area such as emergence, disappearance or the union of spatial entities. These transformations are called temporal phenomena. We propose two different methods to predict the forestry development for the forthcoming years in the experimental area, which reveals these spatial transformations. The proposed methods are based on fuzzy logic and Cellular Automata (CA). The methods are supported by the analysis of the landscape dynamics of a test site located in a tropical rain forest country: the oriental piedmont of the Andes Mountains in Venezuela. This large area, at the scale of a Spot satellite image, is typical of tropical deforestation in a pioneer front. The presented approaches allow the geographer interested in environmental prospective problems to acquire type cartographical documents showing future conditions of a landscape. The experimental tests have showed promising results.
Computer Vision and Image Understanding
Electricity demand forecasts are required by companies who need to predict their customers’ deman... more Electricity demand forecasts are required by companies who need to predict their customers’ demand, and by those wishing to trade electricity as a commodity on financial markets. It is hard to find the right prediction method for a given application if not a prediction expert. Recent works show that Liquid State Machines (LSM’s) can be applied to the prediction of time series. The main advantage of the LSM is that it projects the input data in a high-dimensional dynamical space and therefore simple learning methods can be used to train the readout. In this paper we present an experimental investigation of an approach for the computation of time series prediction by employing Liquid State Machines (LSM) in the modeling of a predictor in a case study for short-term and long-term electricity demand forecasting. Results of this investigation are promising, considering the error to stop training the readout, the number of iterations of training of the readout and that no strategy of seas...
A detecção de descontinuidades em radiografias de soldas não é um trabalho trivial para a automat... more A detecção de descontinuidades em radiografias de soldas não é um trabalho trivial para a automatização via software. Há fatores que prejudicam a determinação de uma metodologia única em todas as imagens digitais, primeiramente, devido à complexidade em discernir defeitos que, em grande parte, têm características semelhantes a outras indicações que não constituem defeitos. Acrescenta-se a grande dificuldade a transpor, que é como agregar o conhecimento do inspetor laudista à ferramenta de laudo. Neste trabalho, foram pesquisadas na literatura diferentes soluções implementadas por diversos pesquisadores, além daquelas desenvolvidas pela equipe de autores deste artigo. As abordagens tradicionalmente existentes fazem uso de bancos de imagens uniformes e ‘bem comportadas’, próprias do ambiente acadêmico, as quais são muito diferentes das imagens obtidas em condições reais de trabalho, especialmente no campo. Assim, embora muitas técnicas que apresentam bons resultados acadêmicos tenham ...
Remote Sensing for Environmental Monitoring, GIS Applications, and Geology, 2002
ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of space... more ABSTRACT Spatial evolutions of anthropized ecosystems and the progressive transformation of spaces in the course of time emerge more and more as a special interest issue in researches about the environment. This evolution constitutes one of the major concerns in the domain of environmental space management. The landscape evolution of a region area and the perspectives for a future state rises an issue particularly important. What will be the state of the region in 15, 30 or 50 years? Time can produce transformations over a region area like emergence, disappearance or union of spatial entities... These transformations are called temporal phenomena. We propose to predict the forestry evolution in the forthcoming years on an experimental area, which reveals these spatial transformations. The proposed method is based on the analysis of terrain landscape given a sequence of n satellite images, which represent the state of a region area in different years. For these purposes, we have developed a specific spatio-temporal prediction approach, linking results of forestry evolution analysis and fuzzy logic. The method is supported by the analysis of the landscape dynamics of a test-site located in a tropical rain country: the oriental piedmont of Andes Mountain in Venezuela. This large area - at the scale of a spot satellite image - is typical of tropical deforestation in a pioneer front. The presented approach allows the geographer interested in environmental prospective problems to get type cartographical documents showing future conditions of a landscape. The experimental tests have showed promising results.
Lecture Notes in Computer Science, 2008
Volume 3: Materials and Joining; Pipeline Automation and Measurement; Risk and Reliability, Parts A and B, 2006
ABSTRACT The current work contributes to the research in the area of pipelines non-destructive te... more ABSTRACT The current work contributes to the research in the area of pipelines non-destructive testing by presenting new methodologies for the automatic analysis of welds radiographs. Object recognition techniques based on genetic algorithms were used for the automatic weld bead detection. In addiction, we developed an image digital filter for the detection of defects in the weld bead zone. These methodologies were tested for 120 digital radiographs from carbon steel pipeline welded joints. These images were acquired by a storage phosphor system using double-wall radiographic exposing technique with single-wall radiographic viewing, according to the ASME V code. As a result, even defects that are hard to be detected by human vision are automatically highlighted and extracted from the whole image to be classified in the further stages of the weld inspection process.
Volume 2: Integrity Management; Poster Session; Student Paper Competition, 2006
Page 1. Proceedings of IPC'06 6th International Pipeline Conference September 25-29, 2006, C... more Page 1. Proceedings of IPC'06 6th International Pipeline Conference September 25-29, 2006, Calgary, Alberta, Canada IPC2006-10462 AUTOMATIC DETECTION OF PIPELINE COMPONENTS IN RADIOGRAPHS FOR CORROSION MONITORING ...
Remote Sensing for Geography, Geology, Land Planning, and Cultural Heritage, 1996
Lecture Notes in Computer Science, 2005
Page 1. F. Rothlauf et al. (Eds.): EvoWorkshops 2005, LNCS 3449, pp. 284293, 2005. © Springer-Ve... more Page 1. F. Rothlauf et al. (Eds.): EvoWorkshops 2005, LNCS 3449, pp. 284293, 2005. © Springer-Verlag Berlin Heidelberg 2005 Object Detection for Computer Vision Using a Robust Genetic Algorithm Tania Mezzadri Centeno ...
Proceedings of the 27th Annual ACM Symposium on Applied Computing - SAC '12, 2012
Several interpolation methods for preserving edges were proposed in literature. This work present... more Several interpolation methods for preserving edges were proposed in literature. This work presents a new interpolation technique simple and easy to implement based on clustering which aims to increase the resolution of a gray scale image preserving edges. Results showed that the technique is quite competitive and meets the stated goals.
Computer Vision and Image Understanding, 2006
... also emphasize that, since only items within a weld are of interest, it is preferred to extra... more ... also emphasize that, since only items within a weld are of interest, it is preferred to extract theweld from each ... article presents a new approach, based on object detection and recognition techniques, for the first step of this image analysis process, ie, segmentation of the ...
ABSTRACT This paper describes a system that integrates three-dimensional re-construction methods ... more ABSTRACT This paper describes a system that integrates three-dimensional re-construction methods and rapid prototyping techniques, providing a more efficient design of medical models from tomographic im-ages using cost-effective manufacturing techniques. The similarity between the CT and MRI cross-sectional images and the 2D data used in rapid prototyping encourages the integration of these two technologies. The use of rapid prototyping systems can provide many advantages for medical applications, allowing surgical plan-ning, visualization of specific anatomy, implant design and pros-thesis fabrication. A fast and robust reconstruction method is pro-posed to approximate the external surfaces of complex objects. An automatic interface is also provided to convert the resulting images into a format that is recognized by the rapid prototyping machines. Several synthesized and real objects are used to demonstrate the performance of our method.