Alexandre Fieno | IFSULDEMINAS - Academia.edu (original) (raw)

Papers by Alexandre Fieno

JOURNAL OF ELECTRONIC IMAGING, 2018

In this paper, we report the results of a set of psychophysical experiments that measure the perc... more In this paper, we report the results of a set of psychophysical experiments that measure the perceptual strengths of videos with different combinations of blockiness, blurriness, and packet-loss artifacts and the overall annoyance. Participants were instructed to search each video for impairments and rate the strength of their individual features (artifacts). A repeated measure Anova (RM-ANOVA) performed on the data showed that artifact physical strengths have a significant effect on annoyance judgments. We tested and reported a set of linear models on the experimental data and we found that all these models give a good description of the relation between individual artifact perceptual strengths and the overall annoyance. In other words, all models presented a very good correlation with the experimental data, showing that annoyance can be modeled as a multidimensional function of the individual artifact perceptual strengths. Additionally, results show that there are interactions among artifact signals.

Bookmarks Related papers MentionsView impact

XXXIV SIMPO´ SIO BRASILEIRO DE TELECOMUNICAC¸O˜ ES E PROCESSAMENTO DE SINAIS, 2016

In the last few years, there has been a growing interest in automatic methods (metrics) that blin... more In the last few years, there has been a growing interest in automatic methods (metrics) that blindly estimate the quality of digital videos, specially in applications where the videos are digitally transmitted over wired or wireless channels and the original (reference) video signal is not available at the receiver. Currently, there are few methods that are able to identify and estimate the strength of temporal artifacts (e.g. packet-loss and jerkiness) introduced during a digital transmission. In this paper, we present a blind (no-reference) video quality assessment metric that estimates the impact of packet-loss artifacts on quality. The proposed algorithm performs a comparison of inter and intra-block correlations, considering blocks of sizes 8 × 8, 16 × 16, and 32×32. The proposed metric was tested on a database containing videos with packet-loss artifacts with different strengths and time durations. Results show that the proposed metric is able to estimate the impact that packet-loss artifacts have on the overall perceived quality, outperforming several metrics available in the literature.

Bookmarks Related papers MentionsView impact

Journal of Electronic Imaging, 2018

Although compression and transmission artifacts are likely to appear simultaneously in digital vi... more Although compression and transmission artifacts are likely to appear simultaneously in digital videos, their annoyance has been traditionally studied and modeled in isolation. So, while blockiness, blurriness, and packet-loss metrics exist, hardly any attempt has been made at modeling their joint impact on visual perception. In this paper, we evaluate the perceptual impact of those three artifacts on video quality. Based on data from three different experiments, in which a pool of participants evaluated videos impaired with packet-loss, blurriness and blockiness (in isolation and in combination), we analyze how the different artifacts combine to produce annoyance and propose several models for predicting the annoyance of videos impaired with combinations of packet-loss, blurriness and blockiness.

Bookmarks Related papers MentionsView impact

QOMEX - Seventh International Workshop on Quality of Multimedia Experience, 2015

In this paper, we propose a subjective video quality assessment method called video quality ruler... more In this paper, we propose a subjective video quality assessment method called video quality ruler (VQR) that can be employed to determine the perceived quality of video sequences. The described method is an extension of the ISO 20462, which is a method to assess image quality. The VQR method provides an interface with a set of pictures. The subjects assess the video using these pictures as a scale and compare the subjective perceived video quality with their perceived quality. The pictures are calibrated to form a numerical scale in units of just noticeable differences (JNDs), which allows to analyze and compare both subjective video and image stimuli. To evaluate the effectiveness of the proposed method, we compare the VQR method with a well-used single stimulus (SS) method. The results show that proposed method can be used to quantify the overall video quality with higher efficiency and with a less biased results than the SS method.

Bookmarks Related papers MentionsView impact

CILAMCE - Iberian Latin American Congress on Computational Methods In Engineering, 2006

Resumo: O crescente desenvolvimento da pesquisa no reconhecimento de face humana tem tido uma for... more Resumo: O crescente desenvolvimento da pesquisa no reconhecimento de face humana tem tido uma forte influência em várias aplicações comerciais, aplicações em identificação criminal e em sistemas de segurança. Vários algoritmos foram propostos a fim de resolver alguns desafios encontrados no sistema de recuperação, como variações de pose, iluminação, diferenças de idade, expressão facial e o método PCA-Principal Component Analysis-proposto por Turk e Pentland em 1991, é clássico no estudo de faces e tem como objetivo procurar as componentes principais da distribuição de faces ou os autovetores da matriz covariância do conjunto de faces. Cada autovetor representa a variação entre as faces e pode ser visto como um conjunto de características. Neste trabalho é avaliado o desempenho do método PCA em relação à iluminação. Também é avaliado como perturbações na imagem consulta, podem alterar os resultados da busca. Vários experimentos foram realizados e uma medida de precisão e revocação é calculada ilustrando o desempenho do PCA sujeito às condições analisadas. Palavras-chave: PCA, iluminação, reconhecimento de face, precisão.

Bookmarks Related papers MentionsView impact

Proceedings of SPIE - The International Society for Optical Engineering, 2015

In digital video systems, impairments introduced during the capture, coding/decoding processes, d... more In digital video systems, impairments introduced during the capture, coding/decoding processes, delivery and display might reduce the perceived quality of the visual content. Recent developments in the area of visual quality have focused on trying to incorporate aspects of gaze patterns into the design of visual quality metrics, mostly using the assumption that visual distortions appearing in less salient areas might be less visible and, therefore, less annoying. Most of these studies, however, have considered the presence of a single artifact (e.g. blockiness or blur) impairing the image. In practice, this is not the case, as multiple artifacts may overlap, and their combined appearance may be strong enough to deviate saliency from its natural pattern. In this work, our focus is on measuring the impact and the influence of combinations of artifacts on the video saliency. For this purpose, we tracked eye-movements of participants in a subjective quality assessment experiment during a free-viewing and a quality assessment tasks. Results show that the gaze locations change from pristine videos to impaired videos. These changes seem to be more related to the quality level and content of videos than to the specific combination of artifacts.

Bookmarks Related papers MentionsView impact

XV Encontro Nacional de Inteligência Artificial e Computacional, 2018

A computer vision approach to classify garbage into recycling categories could be an efficient wa... more A computer vision approach to classify garbage into recycling categories could be an efficient way to process waste. This project aims to take garbage waste images and classify them into four classes: glass, paper, metal and, plastic. We use a garbage image database that contains around 400 images for each class. The models used in the experiments are Pre-trained VGG-16 (VGG16), AlexNet, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and, Random Forest (RF). Experiments showed that our models reached accuracy around 93%.

Bookmarks Related papers MentionsView impact

XIV Symposium on Virtual and Augmented Reality, 2012

The application of computer games in education has evolved significantly in recent times, conside... more The application of computer games in education has evolved significantly in recent times, considering its appeal to the student and the capacity of higher concentration during its execution, resulting in a more consistent learning. The main objective of this project is to develop a game that applies Virtual Reality to the teaching of Computer Maintenance, by creating a learning object that promotes student interaction with the developed 3D environment where the student (user) will handle a hardware device. This action can be performed using the mouse or the joystick from a Playstation-this part of the prototype has already been developed. The game will return to the user on the proper handling due to static electricity and the correct connection to the motherboard, interspersed with the "Virtual Quiz", a virtual questionnaire, sequence of questions concerning the situations experienced by the student with the learning object, in a game in which the teacher himself can supply the quiz. It can become a strong ally to the Computer Maintenance teacher and can be used both in the classroom and in distance education. The game genre chosen was the Serious Game and the directives considered for the project were based on flow. I. INTRODUÇÃO Os objetos de aprendizagem (OA) [1] podem ser compreendidos como "qualquer recurso digital que possa ser utilizado para o suporte ao ensino". Os OA podem ser criados em qualquer mídia ou formato, podendo ser simples como uma animação ou uma apresentação em slides, ou complexos como uma simulação em linguagem orientada a objeto ou recursos tridimensionais. Estes últimos são os recursos utilizados neste projeto, em que cada nível do jogo será composto por objetos tridimensionais que serão manuseados pelo usuário. A Realidade Virtual (RV) [2] é uma interface avançada do usuário para acessar aplicações executadas no computador, onde o usuário pode navegar e interagir, em tempo real, em um ambiente tridimensional gerado por computador. A disciplina Manutenção de Computadores tem como objetivo capacitar profissionais para realizar atividades que exijam a compreensão sobre o funcionamento dos componentes computacionais e suas inter-relações, instalar e configurar computadores [3] entre outras importantes atividades realizadas nesta área. O presente trabalho apresenta como um dos seus principais objetivos modelar e desenvolver novas representações virtuais dos diversos dispositivos físicos de hardware, como um novo processador ou uma nova placa de vídeo. Um grande benefício deste trabalho seria a diminuição dos custos referentes a manter equipamentos de hardware sempre atualizados, como por exemplo, sempre ter todos os novos processadores lançados no mercado. O custo seria muito elevado e até mesmo proibitivo para a maioria das instituições de ensino. O gênero de jogo escolhido foi o Serious Game e as diretivas consideradas para o projeto foram baseadas no flow, ambos serão contemplados no próximo tópico. O objetivo de ferramentas virtuais de treinamento é proporcionar a aquisição ou o aprimoramento de habilidades ou conceitos, destacando-se a necessidade de verificar se houve progresso no desempenho do aprendiz. O processo de determinar se as mudanças no desempenho do treinamento estão de acordo com o planejado é a avaliação, que é fundamentada na medição. Na medição torna-se necessário encontrar um meio de garantir que o que se imagina que acontece, realmente aconteça, envolvendo também o julgamento de valores [4]. Através da motivação de estudantes e usuários de forma geral, baseada na experiência de primeira pessoa vivenciada pelos mesmos, apontadas por pesquisadores como uma das principais vantagens da utilização de técnicas de RV [5] para fins educacionais. Um aluno em sua residência não teria os recursos necessários para estudar manutenção de computadores como placa mãe, processadores, discos rígidos, memórias, placas de rede, vídeo entre outros inúmeros dispositivos relacionados, destacando-se então a motivação deste estudo. Neste caso, o jogo virtual permitirá que o aluno possa estudar, praticar e aperfeiçoar suas técnicas de manutenção corretiva e preventiva bem como o reconhecimento e manuseio destes dispositivos. O presente estudo apresenta como objetivo principal o desenvolvimento de um jogo através de objetos de aprendizagem utilizando Realidade Virtual para o ensino de manutenção de computadores para alunos de ensino técnico e superior tanto no ensino presencial quanto a distância. II. FUNDAMENTOS CORRELATOS O gênero de jogo escolhido foi o Serious Game, segundo [6] são jogos que têm como propósito o ensino ou treinamento, podendo incluir elementos lúdicos e de entretenimento. Muitos desses jogos são desenvolvidos em ambientes virtuais, criados a partir da Realidade Virtual.

Bookmarks Related papers MentionsView impact

XV Jornada de Matemática de Catalão, 2004

Resumo. Este trabalho tem como objetivo passar uma introdução sobre os sistemas de Marca D´Água D... more Resumo. Este trabalho tem como objetivo passar uma introdução sobre os sistemas de Marca D´Água Digital, quais as propriedades destes sistemas, onde estes sistemas são utilizados e com quais finalidades são aplicados, descrevemos também quais são os principais tipos de processamentos que são usados em dados marcados como forma de ataque. Fazemos uma comparação entre métodos O uso de dados digitais sofreu grande aumento nos últimos anos, o principal propulsor deste aumento foi o surgimento da internet, que nos trouxe muitas vantagens como conectar pessoas de todo o mundo e proporcionar a todos meios livres para publicação, distribuição, reprodução e manipulação de trabalhos digitais, permitindo que os autores publiquem seus trabalhos e se tornem conhecidos por estes. Porém este surgimento também nos gerou alguns problemas, onde um destes problemas é a proteção de direitos autorais, pois os autores obtiveram facilidade para publicar seus trabalhos, porém na internet não só a publicação é facilitada, mas a manipulação, a reprodução e a distribuição destes trabalhos também. Com isso os autores frequentemente se deparavam com cópias não autorizadas de seus trabalhos e não tinham como provar que era de sua autoria, pois este trabalho não tinha nenhum sinal que pudesse designar quem era o verdadeiro autor. Com o intuito de resolver estes problemas surgiram os sistemas de Marca D'Água Digital, que basicamente inserem um código identificador ao dado digital, este sinal deve permanecer no dado mesmo após algum processamento ser aplicado sobre o mesmo, mas posteriormente este código poderá ser extraído ou detectado, pelo proprietário do trabalho para que assim possa ser provado quem é o verdadeiro autor do trabalho (Martínez, e Viola, 2000 e Mohanty, 1999). Existem sistemas de Marca D'Água Visíveis que geralmente são usadas apenas como sinal de advertência e sistemas de Marca D'Água Invisíveis que são usadas principalmente para garantir direitos autorais ou autenticidade de dados digitais, suas utilidades são determinadas de acordo com suas propriedades (frágeis ou robustas). Neste trabalho estaremos descrevendo uma introdução a Marca D'Água Digital, o artigo está dividido nas seguintes seções: 1. Introdução, 2. Comparando Criptografia, Esteganografia e Marca D'Água Digital, 3. Classificação e Propriedades Básicas das Marcas D'Água Digitais, 4. Aplicações de Marca D'Água Digital, 5. Principais Métodos de Inserção de Marca D'Água, 6. Conclusão e 7. Bibliografia. Estaremos dando ênfase a sistemas de Marca D'Água Digital aplicadas a imagens digitais, por este motivo algumas vezes o termo imagem será utilizado quando nos referirmos a mídias digitais.

Bookmarks Related papers MentionsView impact

Bookmarks Related papers MentionsView impact

Workshop do Programa de Pós-graduação em Informática, 2012

As the most of the waste generated on the big cities are recyclable, it is necessary to establish... more As the most of the waste generated on the big cities are recyclable, it is necessary to establish a selective collection manner for correctly classifying them. The different kinds of bins available for recycling may confuse a not well-disciplined user who do not know where (in which trash) should discard his waste. This paper proposes a novel system, named IRSOM, to assist the common users on this task. It is based on Self-Organizing Maps (SOM) with Content-based Image Retrieval (CBIR) for automated sorting of waste from selective collection. Our system aims to assist the user by recognizing the waste to be dropped indicating the proper bin with acceptable precision, thus becoming a smart tool for helping social problems and environmental education else well.

Bookmarks Related papers MentionsView impact

IEEE Transactions on Multimedia, 2016

Understanding the perceptual impact of compression artifacts in video is one of the keys for desi... more Understanding the perceptual impact of compression artifacts in video is one of the keys for designing better coding schemes and appropriate visual quality control chains. Although compression and transmission artifacts, such as block-iness, blurriness and packet-loss, appear simultaneously in digital videos, traditionally they have been studied in isolation. In this paper, we report the results of three subjective quality assessment experiments aimed at studying perceptual characteristics of a set of artifacts common in digital videos. With this goal, first we study the annoyance of each of three artifacts (blockiness, blurriness and packet-loss) in isolation and then in combination. Based on the subjective evaluations, we design several models of the annoyance caused by the joint presence of these three artifacts on digital video. Index Terms-Video quality assessment, compression artifacts, subjective quality, human visual system modeling.

Bookmarks Related papers MentionsView impact

Journal of Electronic Imaging, 2018

Objective Video Quality Metrics are designed to be as reliable as the subjective quality assessme... more Objective Video Quality Metrics are designed to be as reliable as the subjective quality assessments on which they are calibrated and validated. However, existing standard methodologies for subjective video quality assessment provide low reliable results for some conditions. In this study, we investigate whether an extension of the Quality Ruler experimental methodology, originally defined for images and shown to be more reliable than, e.g., standard Single Stimulus methods, can be adapted to reliably assess the quality of videos. The Video Quality Ruler methodology allows subjects to assess video quality using a set of reference anchor images (the ruler), spanning a wide range of quality altogether, but closely spaced in function of quality one from the other. Subjects are asked to compare the quality of the displayed test video with the quality of these anchor images, displayed on a tablet, and indicate which of the reference images matches in quality the test video. As a result, the video quality assessment task is reduced to a set of visual comparisons between video and reference image quality. In this paper, we describe how to adapt the original Quality Ruler methodology to video quality assessment, and we compare the proposed methodology with two other, widely used experimental methodologies: the Single Stimulus (SS) and the Double Stimulus (DS) method. Our results show that VQR is a reliable method to assess video quality according to a multitude of criteria.

Bookmarks Related papers MentionsView impact

The application of computer games in education has evolved significantly in recent times, conside... more The application of computer games in education has evolved significantly in recent times, considering its appeal to the student and the capacity of higher concentration during its execution, resulting in a more consistent learning. The main objective of this project is to develop a game that applies Virtual Reality to the teaching of Computer Maintenance, by creating a learning object that promotes student interaction with the developed 3D environment where the student (user) will handle a hardware device. This action can be performed using the mouse or the joystick from a Playstation – this part of the prototype has already been developed. The game will return to the user on the proper handling due to static electricity and the correct connection to the motherboard, interspersed with the "Virtual Quiz", a virtual questionnaire, sequence of questions concerning the situations experienced by the student with the learning object, in a game in which the teacher himself can supply the quiz. It can become a strong ally to the Computer Maintenance teacher and can be used both in the classroom and in distance education. The game genre chosen was the Serious Game and the directives considered for the project were based on flow.

Bookmarks Related papers MentionsView impact

As the most of the waste generated on the big cities are recyclable, it is necessary to establish... more As the most of the waste generated on the big cities are recyclable, it is necessary to establish a selective collection manner for correctly classifying them. The different kinds of bins available for recycling may confuse a not well-disciplined user who do not know where (in which trash) should discard his waste. This paper proposes a novel system, named IRSOM, to assist the common users on this task. It is based on Self- Organizing Maps (SOM) with Content-based Image Retrieval (CBIR) for automated sorting of waste from selective collection. Our system aims to assist the user by recognizing the waste to be dropped indicating the proper bin with acceptable precision, thus becoming a smart tool for helping social problems and environmental education else well.

Bookmarks Related papers MentionsView impact

Thesis Chapters by Alexandre Fieno

The main causes for the reducing of visual quality in digital imaging systems are the unwanted pr... more The main causes for the reducing of visual quality in digital imaging systems are the unwanted presence of degradations introduced during processing and transmission steps. However, measuring the quality of a video implies in a direct or indirect comparison between test video and reference video. In most applications, psycho-physical experiments with human subjects are the most reliable means of determining the quality of a video. Although more reliable, these methods are time consuming and difficult to incorporate into an automated quality control service. As an alternative, objective metrics, i.e. algorithms, are generally used to estimate video quality quality automatically. To develop an objective metric, it is important understand how the perceptual characteristics of a set of artifacts are related to their physical strengths and to the perceived annoyance. Then, to study the characteristics of different types of artifacts commonly found in compressed videos (i.e. blockiness, blurriness, and packet-loss) we performed six psychophysical experiments to independently measure the strength and overall annoyance of these artifact signals when presented alone or in combination. We analyzed the data from these experiments and proposed several models for the overall annoyance based on combinations of the perceptual strengths of the individual artifact signals and their interactions. Inspired by experimental results, we proposed a no-reference video quality metric based in several features extracted from the videos (e.g. DCT information, cross-correlation of sub-sampled images, average absolute differences between block image pixels, intensity variation between neighbouring pixels, and visual attention). A non-linear regression model using a support vector (SVR) technique is used to combine all features to obtain an overall quality estimate. Our metric performed better than the tested artifact metrics and for some full-reference metrics.

Bookmarks Related papers MentionsView impact

Dissertation, 2006

With the augment of criminal activities as bank robbery, kidnapping, etc., the needs of identifyi... more With the augment of criminal activities as bank robbery, kidnapping, etc., the needs of identifying a person in a safe manner became indispensable. Several algorithms have been proposed with the aim of resolving some of the challenges found in the retrieval systems as pose, illumination, age and facial expression effects. A very well diffused method in face recognition is the PCA - Principal Component Analysis, proposed by Turk and Pentland in 1991. The PCA method has as the main goal to seek the principal components of faces distribution, which means, the eigenvectors of the covariance matrix of the face set, where each eigenvector represents the variation among the faces (auto faces) that can be seen as a feature set. This work dedicates to the performance of the PCA method in face retrieval, taking into consideration the use of different poses, facial expression and illumination effects. The PCA is also evaluated when the query face has some of its features modified (i.e. noise, occlusion, cutting, etc). An analysis is done taking into consideration how these modified features could change the retrieval results, besides the illumination and poses influence. The performance of PCA method is also evaluated considering which ones and the quantity of eigenvalues to be selected by the algorithm, with the aim of reaching good retrieval results. With the aim of verifying the illumination problem, a smooth filter is used in a set of faces and then the PCA method is applied in this set of images considering only those images pieces that have texture and noise presence, derived of the difference between the original and the smoothed image. The main goal is to improve the face retrieval under several illumination conditions.

Bookmarks Related papers MentionsView impact

JOURNAL OF ELECTRONIC IMAGING, 2018

In this paper, we report the results of a set of psychophysical experiments that measure the perc... more In this paper, we report the results of a set of psychophysical experiments that measure the perceptual strengths of videos with different combinations of blockiness, blurriness, and packet-loss artifacts and the overall annoyance. Participants were instructed to search each video for impairments and rate the strength of their individual features (artifacts). A repeated measure Anova (RM-ANOVA) performed on the data showed that artifact physical strengths have a significant effect on annoyance judgments. We tested and reported a set of linear models on the experimental data and we found that all these models give a good description of the relation between individual artifact perceptual strengths and the overall annoyance. In other words, all models presented a very good correlation with the experimental data, showing that annoyance can be modeled as a multidimensional function of the individual artifact perceptual strengths. Additionally, results show that there are interactions among artifact signals.

Bookmarks Related papers MentionsView impact

XXXIV SIMPO´ SIO BRASILEIRO DE TELECOMUNICAC¸O˜ ES E PROCESSAMENTO DE SINAIS, 2016

In the last few years, there has been a growing interest in automatic methods (metrics) that blin... more In the last few years, there has been a growing interest in automatic methods (metrics) that blindly estimate the quality of digital videos, specially in applications where the videos are digitally transmitted over wired or wireless channels and the original (reference) video signal is not available at the receiver. Currently, there are few methods that are able to identify and estimate the strength of temporal artifacts (e.g. packet-loss and jerkiness) introduced during a digital transmission. In this paper, we present a blind (no-reference) video quality assessment metric that estimates the impact of packet-loss artifacts on quality. The proposed algorithm performs a comparison of inter and intra-block correlations, considering blocks of sizes 8 × 8, 16 × 16, and 32×32. The proposed metric was tested on a database containing videos with packet-loss artifacts with different strengths and time durations. Results show that the proposed metric is able to estimate the impact that packet-loss artifacts have on the overall perceived quality, outperforming several metrics available in the literature.

Bookmarks Related papers MentionsView impact

Journal of Electronic Imaging, 2018

Although compression and transmission artifacts are likely to appear simultaneously in digital vi... more Although compression and transmission artifacts are likely to appear simultaneously in digital videos, their annoyance has been traditionally studied and modeled in isolation. So, while blockiness, blurriness, and packet-loss metrics exist, hardly any attempt has been made at modeling their joint impact on visual perception. In this paper, we evaluate the perceptual impact of those three artifacts on video quality. Based on data from three different experiments, in which a pool of participants evaluated videos impaired with packet-loss, blurriness and blockiness (in isolation and in combination), we analyze how the different artifacts combine to produce annoyance and propose several models for predicting the annoyance of videos impaired with combinations of packet-loss, blurriness and blockiness.

Bookmarks Related papers MentionsView impact

QOMEX - Seventh International Workshop on Quality of Multimedia Experience, 2015

In this paper, we propose a subjective video quality assessment method called video quality ruler... more In this paper, we propose a subjective video quality assessment method called video quality ruler (VQR) that can be employed to determine the perceived quality of video sequences. The described method is an extension of the ISO 20462, which is a method to assess image quality. The VQR method provides an interface with a set of pictures. The subjects assess the video using these pictures as a scale and compare the subjective perceived video quality with their perceived quality. The pictures are calibrated to form a numerical scale in units of just noticeable differences (JNDs), which allows to analyze and compare both subjective video and image stimuli. To evaluate the effectiveness of the proposed method, we compare the VQR method with a well-used single stimulus (SS) method. The results show that proposed method can be used to quantify the overall video quality with higher efficiency and with a less biased results than the SS method.

Bookmarks Related papers MentionsView impact

CILAMCE - Iberian Latin American Congress on Computational Methods In Engineering, 2006

Resumo: O crescente desenvolvimento da pesquisa no reconhecimento de face humana tem tido uma for... more Resumo: O crescente desenvolvimento da pesquisa no reconhecimento de face humana tem tido uma forte influência em várias aplicações comerciais, aplicações em identificação criminal e em sistemas de segurança. Vários algoritmos foram propostos a fim de resolver alguns desafios encontrados no sistema de recuperação, como variações de pose, iluminação, diferenças de idade, expressão facial e o método PCA-Principal Component Analysis-proposto por Turk e Pentland em 1991, é clássico no estudo de faces e tem como objetivo procurar as componentes principais da distribuição de faces ou os autovetores da matriz covariância do conjunto de faces. Cada autovetor representa a variação entre as faces e pode ser visto como um conjunto de características. Neste trabalho é avaliado o desempenho do método PCA em relação à iluminação. Também é avaliado como perturbações na imagem consulta, podem alterar os resultados da busca. Vários experimentos foram realizados e uma medida de precisão e revocação é calculada ilustrando o desempenho do PCA sujeito às condições analisadas. Palavras-chave: PCA, iluminação, reconhecimento de face, precisão.

Bookmarks Related papers MentionsView impact

Proceedings of SPIE - The International Society for Optical Engineering, 2015

In digital video systems, impairments introduced during the capture, coding/decoding processes, d... more In digital video systems, impairments introduced during the capture, coding/decoding processes, delivery and display might reduce the perceived quality of the visual content. Recent developments in the area of visual quality have focused on trying to incorporate aspects of gaze patterns into the design of visual quality metrics, mostly using the assumption that visual distortions appearing in less salient areas might be less visible and, therefore, less annoying. Most of these studies, however, have considered the presence of a single artifact (e.g. blockiness or blur) impairing the image. In practice, this is not the case, as multiple artifacts may overlap, and their combined appearance may be strong enough to deviate saliency from its natural pattern. In this work, our focus is on measuring the impact and the influence of combinations of artifacts on the video saliency. For this purpose, we tracked eye-movements of participants in a subjective quality assessment experiment during a free-viewing and a quality assessment tasks. Results show that the gaze locations change from pristine videos to impaired videos. These changes seem to be more related to the quality level and content of videos than to the specific combination of artifacts.

Bookmarks Related papers MentionsView impact

XV Encontro Nacional de Inteligência Artificial e Computacional, 2018

A computer vision approach to classify garbage into recycling categories could be an efficient wa... more A computer vision approach to classify garbage into recycling categories could be an efficient way to process waste. This project aims to take garbage waste images and classify them into four classes: glass, paper, metal and, plastic. We use a garbage image database that contains around 400 images for each class. The models used in the experiments are Pre-trained VGG-16 (VGG16), AlexNet, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and, Random Forest (RF). Experiments showed that our models reached accuracy around 93%.

Bookmarks Related papers MentionsView impact

XIV Symposium on Virtual and Augmented Reality, 2012

The application of computer games in education has evolved significantly in recent times, conside... more The application of computer games in education has evolved significantly in recent times, considering its appeal to the student and the capacity of higher concentration during its execution, resulting in a more consistent learning. The main objective of this project is to develop a game that applies Virtual Reality to the teaching of Computer Maintenance, by creating a learning object that promotes student interaction with the developed 3D environment where the student (user) will handle a hardware device. This action can be performed using the mouse or the joystick from a Playstation-this part of the prototype has already been developed. The game will return to the user on the proper handling due to static electricity and the correct connection to the motherboard, interspersed with the "Virtual Quiz", a virtual questionnaire, sequence of questions concerning the situations experienced by the student with the learning object, in a game in which the teacher himself can supply the quiz. It can become a strong ally to the Computer Maintenance teacher and can be used both in the classroom and in distance education. The game genre chosen was the Serious Game and the directives considered for the project were based on flow. I. INTRODUÇÃO Os objetos de aprendizagem (OA) [1] podem ser compreendidos como "qualquer recurso digital que possa ser utilizado para o suporte ao ensino". Os OA podem ser criados em qualquer mídia ou formato, podendo ser simples como uma animação ou uma apresentação em slides, ou complexos como uma simulação em linguagem orientada a objeto ou recursos tridimensionais. Estes últimos são os recursos utilizados neste projeto, em que cada nível do jogo será composto por objetos tridimensionais que serão manuseados pelo usuário. A Realidade Virtual (RV) [2] é uma interface avançada do usuário para acessar aplicações executadas no computador, onde o usuário pode navegar e interagir, em tempo real, em um ambiente tridimensional gerado por computador. A disciplina Manutenção de Computadores tem como objetivo capacitar profissionais para realizar atividades que exijam a compreensão sobre o funcionamento dos componentes computacionais e suas inter-relações, instalar e configurar computadores [3] entre outras importantes atividades realizadas nesta área. O presente trabalho apresenta como um dos seus principais objetivos modelar e desenvolver novas representações virtuais dos diversos dispositivos físicos de hardware, como um novo processador ou uma nova placa de vídeo. Um grande benefício deste trabalho seria a diminuição dos custos referentes a manter equipamentos de hardware sempre atualizados, como por exemplo, sempre ter todos os novos processadores lançados no mercado. O custo seria muito elevado e até mesmo proibitivo para a maioria das instituições de ensino. O gênero de jogo escolhido foi o Serious Game e as diretivas consideradas para o projeto foram baseadas no flow, ambos serão contemplados no próximo tópico. O objetivo de ferramentas virtuais de treinamento é proporcionar a aquisição ou o aprimoramento de habilidades ou conceitos, destacando-se a necessidade de verificar se houve progresso no desempenho do aprendiz. O processo de determinar se as mudanças no desempenho do treinamento estão de acordo com o planejado é a avaliação, que é fundamentada na medição. Na medição torna-se necessário encontrar um meio de garantir que o que se imagina que acontece, realmente aconteça, envolvendo também o julgamento de valores [4]. Através da motivação de estudantes e usuários de forma geral, baseada na experiência de primeira pessoa vivenciada pelos mesmos, apontadas por pesquisadores como uma das principais vantagens da utilização de técnicas de RV [5] para fins educacionais. Um aluno em sua residência não teria os recursos necessários para estudar manutenção de computadores como placa mãe, processadores, discos rígidos, memórias, placas de rede, vídeo entre outros inúmeros dispositivos relacionados, destacando-se então a motivação deste estudo. Neste caso, o jogo virtual permitirá que o aluno possa estudar, praticar e aperfeiçoar suas técnicas de manutenção corretiva e preventiva bem como o reconhecimento e manuseio destes dispositivos. O presente estudo apresenta como objetivo principal o desenvolvimento de um jogo através de objetos de aprendizagem utilizando Realidade Virtual para o ensino de manutenção de computadores para alunos de ensino técnico e superior tanto no ensino presencial quanto a distância. II. FUNDAMENTOS CORRELATOS O gênero de jogo escolhido foi o Serious Game, segundo [6] são jogos que têm como propósito o ensino ou treinamento, podendo incluir elementos lúdicos e de entretenimento. Muitos desses jogos são desenvolvidos em ambientes virtuais, criados a partir da Realidade Virtual.

Bookmarks Related papers MentionsView impact

XV Jornada de Matemática de Catalão, 2004

Resumo. Este trabalho tem como objetivo passar uma introdução sobre os sistemas de Marca D´Água D... more Resumo. Este trabalho tem como objetivo passar uma introdução sobre os sistemas de Marca D´Água Digital, quais as propriedades destes sistemas, onde estes sistemas são utilizados e com quais finalidades são aplicados, descrevemos também quais são os principais tipos de processamentos que são usados em dados marcados como forma de ataque. Fazemos uma comparação entre métodos O uso de dados digitais sofreu grande aumento nos últimos anos, o principal propulsor deste aumento foi o surgimento da internet, que nos trouxe muitas vantagens como conectar pessoas de todo o mundo e proporcionar a todos meios livres para publicação, distribuição, reprodução e manipulação de trabalhos digitais, permitindo que os autores publiquem seus trabalhos e se tornem conhecidos por estes. Porém este surgimento também nos gerou alguns problemas, onde um destes problemas é a proteção de direitos autorais, pois os autores obtiveram facilidade para publicar seus trabalhos, porém na internet não só a publicação é facilitada, mas a manipulação, a reprodução e a distribuição destes trabalhos também. Com isso os autores frequentemente se deparavam com cópias não autorizadas de seus trabalhos e não tinham como provar que era de sua autoria, pois este trabalho não tinha nenhum sinal que pudesse designar quem era o verdadeiro autor. Com o intuito de resolver estes problemas surgiram os sistemas de Marca D'Água Digital, que basicamente inserem um código identificador ao dado digital, este sinal deve permanecer no dado mesmo após algum processamento ser aplicado sobre o mesmo, mas posteriormente este código poderá ser extraído ou detectado, pelo proprietário do trabalho para que assim possa ser provado quem é o verdadeiro autor do trabalho (Martínez, e Viola, 2000 e Mohanty, 1999). Existem sistemas de Marca D'Água Visíveis que geralmente são usadas apenas como sinal de advertência e sistemas de Marca D'Água Invisíveis que são usadas principalmente para garantir direitos autorais ou autenticidade de dados digitais, suas utilidades são determinadas de acordo com suas propriedades (frágeis ou robustas). Neste trabalho estaremos descrevendo uma introdução a Marca D'Água Digital, o artigo está dividido nas seguintes seções: 1. Introdução, 2. Comparando Criptografia, Esteganografia e Marca D'Água Digital, 3. Classificação e Propriedades Básicas das Marcas D'Água Digitais, 4. Aplicações de Marca D'Água Digital, 5. Principais Métodos de Inserção de Marca D'Água, 6. Conclusão e 7. Bibliografia. Estaremos dando ênfase a sistemas de Marca D'Água Digital aplicadas a imagens digitais, por este motivo algumas vezes o termo imagem será utilizado quando nos referirmos a mídias digitais.

Bookmarks Related papers MentionsView impact

Bookmarks Related papers MentionsView impact

Workshop do Programa de Pós-graduação em Informática, 2012

As the most of the waste generated on the big cities are recyclable, it is necessary to establish... more As the most of the waste generated on the big cities are recyclable, it is necessary to establish a selective collection manner for correctly classifying them. The different kinds of bins available for recycling may confuse a not well-disciplined user who do not know where (in which trash) should discard his waste. This paper proposes a novel system, named IRSOM, to assist the common users on this task. It is based on Self-Organizing Maps (SOM) with Content-based Image Retrieval (CBIR) for automated sorting of waste from selective collection. Our system aims to assist the user by recognizing the waste to be dropped indicating the proper bin with acceptable precision, thus becoming a smart tool for helping social problems and environmental education else well.

Bookmarks Related papers MentionsView impact

IEEE Transactions on Multimedia, 2016

Understanding the perceptual impact of compression artifacts in video is one of the keys for desi... more Understanding the perceptual impact of compression artifacts in video is one of the keys for designing better coding schemes and appropriate visual quality control chains. Although compression and transmission artifacts, such as block-iness, blurriness and packet-loss, appear simultaneously in digital videos, traditionally they have been studied in isolation. In this paper, we report the results of three subjective quality assessment experiments aimed at studying perceptual characteristics of a set of artifacts common in digital videos. With this goal, first we study the annoyance of each of three artifacts (blockiness, blurriness and packet-loss) in isolation and then in combination. Based on the subjective evaluations, we design several models of the annoyance caused by the joint presence of these three artifacts on digital video. Index Terms-Video quality assessment, compression artifacts, subjective quality, human visual system modeling.

Bookmarks Related papers MentionsView impact

Journal of Electronic Imaging, 2018

Objective Video Quality Metrics are designed to be as reliable as the subjective quality assessme... more Objective Video Quality Metrics are designed to be as reliable as the subjective quality assessments on which they are calibrated and validated. However, existing standard methodologies for subjective video quality assessment provide low reliable results for some conditions. In this study, we investigate whether an extension of the Quality Ruler experimental methodology, originally defined for images and shown to be more reliable than, e.g., standard Single Stimulus methods, can be adapted to reliably assess the quality of videos. The Video Quality Ruler methodology allows subjects to assess video quality using a set of reference anchor images (the ruler), spanning a wide range of quality altogether, but closely spaced in function of quality one from the other. Subjects are asked to compare the quality of the displayed test video with the quality of these anchor images, displayed on a tablet, and indicate which of the reference images matches in quality the test video. As a result, the video quality assessment task is reduced to a set of visual comparisons between video and reference image quality. In this paper, we describe how to adapt the original Quality Ruler methodology to video quality assessment, and we compare the proposed methodology with two other, widely used experimental methodologies: the Single Stimulus (SS) and the Double Stimulus (DS) method. Our results show that VQR is a reliable method to assess video quality according to a multitude of criteria.

Bookmarks Related papers MentionsView impact

The application of computer games in education has evolved significantly in recent times, conside... more The application of computer games in education has evolved significantly in recent times, considering its appeal to the student and the capacity of higher concentration during its execution, resulting in a more consistent learning. The main objective of this project is to develop a game that applies Virtual Reality to the teaching of Computer Maintenance, by creating a learning object that promotes student interaction with the developed 3D environment where the student (user) will handle a hardware device. This action can be performed using the mouse or the joystick from a Playstation – this part of the prototype has already been developed. The game will return to the user on the proper handling due to static electricity and the correct connection to the motherboard, interspersed with the "Virtual Quiz", a virtual questionnaire, sequence of questions concerning the situations experienced by the student with the learning object, in a game in which the teacher himself can supply the quiz. It can become a strong ally to the Computer Maintenance teacher and can be used both in the classroom and in distance education. The game genre chosen was the Serious Game and the directives considered for the project were based on flow.

Bookmarks Related papers MentionsView impact

As the most of the waste generated on the big cities are recyclable, it is necessary to establish... more As the most of the waste generated on the big cities are recyclable, it is necessary to establish a selective collection manner for correctly classifying them. The different kinds of bins available for recycling may confuse a not well-disciplined user who do not know where (in which trash) should discard his waste. This paper proposes a novel system, named IRSOM, to assist the common users on this task. It is based on Self- Organizing Maps (SOM) with Content-based Image Retrieval (CBIR) for automated sorting of waste from selective collection. Our system aims to assist the user by recognizing the waste to be dropped indicating the proper bin with acceptable precision, thus becoming a smart tool for helping social problems and environmental education else well.

Bookmarks Related papers MentionsView impact

The main causes for the reducing of visual quality in digital imaging systems are the unwanted pr... more The main causes for the reducing of visual quality in digital imaging systems are the unwanted presence of degradations introduced during processing and transmission steps. However, measuring the quality of a video implies in a direct or indirect comparison between test video and reference video. In most applications, psycho-physical experiments with human subjects are the most reliable means of determining the quality of a video. Although more reliable, these methods are time consuming and difficult to incorporate into an automated quality control service. As an alternative, objective metrics, i.e. algorithms, are generally used to estimate video quality quality automatically. To develop an objective metric, it is important understand how the perceptual characteristics of a set of artifacts are related to their physical strengths and to the perceived annoyance. Then, to study the characteristics of different types of artifacts commonly found in compressed videos (i.e. blockiness, blurriness, and packet-loss) we performed six psychophysical experiments to independently measure the strength and overall annoyance of these artifact signals when presented alone or in combination. We analyzed the data from these experiments and proposed several models for the overall annoyance based on combinations of the perceptual strengths of the individual artifact signals and their interactions. Inspired by experimental results, we proposed a no-reference video quality metric based in several features extracted from the videos (e.g. DCT information, cross-correlation of sub-sampled images, average absolute differences between block image pixels, intensity variation between neighbouring pixels, and visual attention). A non-linear regression model using a support vector (SVR) technique is used to combine all features to obtain an overall quality estimate. Our metric performed better than the tested artifact metrics and for some full-reference metrics.

Bookmarks Related papers MentionsView impact

Dissertation, 2006

With the augment of criminal activities as bank robbery, kidnapping, etc., the needs of identifyi... more With the augment of criminal activities as bank robbery, kidnapping, etc., the needs of identifying a person in a safe manner became indispensable. Several algorithms have been proposed with the aim of resolving some of the challenges found in the retrieval systems as pose, illumination, age and facial expression effects. A very well diffused method in face recognition is the PCA - Principal Component Analysis, proposed by Turk and Pentland in 1991. The PCA method has as the main goal to seek the principal components of faces distribution, which means, the eigenvectors of the covariance matrix of the face set, where each eigenvector represents the variation among the faces (auto faces) that can be seen as a feature set. This work dedicates to the performance of the PCA method in face retrieval, taking into consideration the use of different poses, facial expression and illumination effects. The PCA is also evaluated when the query face has some of its features modified (i.e. noise, occlusion, cutting, etc). An analysis is done taking into consideration how these modified features could change the retrieval results, besides the illumination and poses influence. The performance of PCA method is also evaluated considering which ones and the quantity of eigenvalues to be selected by the algorithm, with the aim of reaching good retrieval results. With the aim of verifying the illumination problem, a smooth filter is used in a set of faces and then the PCA method is applied in this set of images considering only those images pieces that have texture and noise presence, derived of the difference between the original and the smoothed image. The main goal is to improve the face retrieval under several illumination conditions.

Bookmarks Related papers MentionsView impact