Loading...
11 results
Search Results
Now showing 1 - 10 of 11
- Audiovisual Quality of Live Music Streaming over Mobile Networks using MPEG-DASHPublication . Rodrigues, Rafael; Pocta, Peter; Melvin, Hugh; Bernardo, Marco V.; Pereira, Manuela; Pinheiro, Antonio M. G.The MPEG-DASH protocol has been rapidly adopted by most major network content providers and enables clients to make informed decisions in the context of HTTP streaming, based on network and device conditions using the available media representations. A review of the literature on adaptive streaming over mobile shows that most emphasis has been on adapting the video quality whereas this work examines the trade-off between video and audio quality. In particular, subjective tests were undertaken for live music streaming over emulated mobile networks with MPEG-DASH. A group of audio/video sequences was designed to emulate varying bandwidth arising from network congestion, with varying trade-off between audio and video bit rates. Absolute Category Rating was used to evaluate the relative impact of both audio and video quality in the overall Quality of Experience (QoE). One key finding from the statistical analysis of Mean Opinion Scores (MOS) results using Analysis of Variance indicates that providing reduced audio quality has a much lower impact on QoE than reducing video quality at similar total bandwidth situations. This paper also describes an objective model for audiovisual quality estimation that combines the outcomes from audio and video metrics into a joint parametric model. The correlation between predicted and subjective MOS was computed using several outcomes (Pearson and Spearman correlation coefficients, Root Mean Square Error (RMSE) and epsilon-insensitive RMSE). The obtained results indicate that the proposed approach is a viable solution for objective audiovisual quality assessment in the context of live music streaming over mobile network.
- A Quality of Recognition Case Study: Texture-based Segmentation and MRI Quality AssessmentPublication . Rodrigues, Rafael; Pinheiro, Antonio M. G.Muscle texture may be used as a descriptive feature for the segmentation of skeletal muscle in Magnetic Resonance Images (MRI). However, MRI acquisition is not always ideal and the texture richness might become compromised. Moreover, the research for the development of texture quality metrics, and particularly no-reference metrics, to be applied to the specific context of MRI is still in a very early stage. In this paper, a case study is established from a texture-based segmentation approach for skeletal muscle, which was tested in a thigh Dixon MRI database. Upon the obtained performance measures, the relation between objective image quality and the texture MRI richness is explored, considering a set of state-of-the-art no-reference image quality metrics. A discussion on the effectiveness of existing quality assessment methods in measuring MRI texture quality is carried out, based on Pearson and Spearman correlation outcomes.
- Severity classification in cases of Collagen VI-related myopathy with Convolutional Neural Networks and handcrafted texture featuresPublication . Rodrigues, Rafael; Quijano-Roy, Susana; Carlier, Robert-Yves; Pinheiro, Antonio M. G.Magnetic Resonance Imaging (MRI) is a non-invasive tool for the clinical assessment of low-prevalence neuromuscular disorders. Automated diagnosis methods might reduce the need for biopsies and provide valuable information on disease follow-up. In this paper, three methods are proposed to classify target muscles in Collagen VI-related myopathy cases, based on their degree of involvement, notably a Convolutional Neural Network, a Fully Connected Network to classify texture features, and a hybrid method combining the two feature sets. The proposed methods were evaluated on axial T1-weighted Turbo Spin-Echo MRI from 26 subjects, including Ullrich Congenital Muscular Dystrophy and Bethlem Myopathy patients at different evolution stages. The hybrid model achieved the best cross-validation results, with a global accuracy of 93.8%, and F-scores of 0.99, 0.82, and 0.95, for healthy, mild and moderate/severe cases, respectively.
- Severity classification in cases of Collagen VI-related myopathy with Convolutional Neural Networks and handcrafted texture featuresPublication . Rodrigues, Rafael; Quijano-Roy, Susana; Carlier, Robert-Yves; Pinheiro, Antonio M. G.Magnetic Resonance Imaging (MRI) is a non-invasive tool for the clinical assessment of low-prevalence neuromuscular disorders. Automated diagnosis methods might reduce the need for biopsies and provide valuable information on disease follow-up. In this paper, three methods are proposed to classify target muscles in Collagen VI-related myopathy cases, based on their degree of involvement, notably a Convolutional Neural Network, a Fully Connected Network to classify texture features, and a hybrid method combining the two feature sets. The proposed methods were evaluated on axial T1-weighted Turbo Spin-Echo MRI from 26 subjects, including Ullrich Congenital Muscular Dystrophy and Bethlem Myopathy patients at different evolution stages. The hybrid model achieved the best cross-validation results, with a global accuracy of 93.8%, and F-scores of 0.99, 0.82, and 0.95, for healthy, mild and moderate/severe cases, respectively.
- Segmentação de massas em ultrasons peitorais usando técnicas de multiresoluçãoPublication . Rodrigues, Jorge Rafael Mendes; Pinheiro, António Manuel GonçalvesA imagem de ultrasons é uma ferramenta de diagnóstico importante e cada vez mais aplicada na deteção do cancro da mama. No entanto, este tipo de exame é, intrinsecamente, degradado por ruído e pelo baixo contraste, resultando em di culdades na deteção de massas ou nódulos e, acima de tudo, na avaliação do seu tamanho e forma. Neste sentido, as técnicas de diagnóstico assistido por computador surgem como um factor de suporte importante para a análise deste tipo de imagem. No presente trabalho, uma abordagem bifaseada para um método de segmentação de ultrasons mamários, totalmente automático, é apresentada. A primeira etapa procura realizar uma segmentação inicial da imagem, que permita a localização primária da Região de Interesse (ROI). A segunda parte foca-se na área de nida na etapa anterior, tendo como objectivo a melhoria da resolução espacial da segmentação. Na primeira etapa de segmentação, diversas técnicas de classi cação binária são aplicadas para realizar a segmentação da imagem, utilizando características multiresolução para o descriptor de pixel - ltragem FIR passa-banda e difusão não linear e curvatura scale-space de alta escala. Estas técnicas de processamento de imagem são aplicadas para a redução da in uência dos componentes de ruído inerentes aos ultrasons e, simultaneamente, recolher informação estrutural e estatística adequada para a segmentação das massas. Os dados são classi cados usando Support Vector Machines e Análise Discriminante. Na segunda fase, as máscaras obtidas a partir da segmentação inicial são dilatadas, produzindo uma área restrita que contém a ROI. Considerando apenas os pixéis pertencentes a esta região, uma nova segmentação é executada, através do algoritmo AdaBoost, usando a difusão não linear e curvaturas de menor escala. Um algoritmo de contornos activos é, também, aplicado para melhorar os resultados da segmentação, sendo as máscaras da segmentação inicial utilizadas como contornos iniciais. Os resultados nais con rmam a metodologia proposta como sendo uma solução promissora para a segmentação de massas em imagens de ultrasons da mama, revelando, em termos globais, bons resultados de acurácia - 97,58% (AdaBoost) e 97,70% (Contornos Activos) -, sensibilidade - 76,46% (AdaBoost) e 75,40% (Contornos Activos) - e de precisão - 87,26% (AdaBoost) e 87,51% (Contornos Activos).
- Texture Analysis of T1-weighted Turbo Spin-Echo MRI for the Diagnosis and Follow-up of Collagen VI-related MyopathyPublication . Rodrigues, Rafael; Gómez-García de La Banda, Marta; Tordjman, Mickael; Gómez-Andrés, David; Quijano-Roy, Susana; Carlier, Robert-Yves; Pinheiro, Antonio M. G.Muscle texture analysis in Magnetic Resonance Imaging (MRI) has revealed a good correlation with typical histological changes resulting from neuromuscular disorders. In this research, we assess the effectiveness of several features in describing intramuscular texture alterations in cases of Collagen VI-related myopathy. A T1-weighted Turbo Spin-Echo MRI dataset was used (Nsubj = 26), consisting of thigh scans from subjects diagnosed with Ullrich Congenital Muscular Dystrophy or Bethlem Myopathy, with different severity levels, as well as healthy subjects. A total of 355 texture features were studied, including attributes derived from the Gray-Level Co-occurrence Matrix, the Run-Length Matrix, Wavelet and Gabor filters. The extracted features were ranked using the Support Vector Machine Recursive Feature Elimination (SVM-RFE) algorithm with Correlation Bias Reduction, prior to cross-validated classification with a Gaussian kernel SVM.
- A Two-Step Segmentation Method for Breast Ultrasound Masses Based on Multi-resolution AnalysisPublication . Rodrigues, Rafael; Braz, Rui; Pereira, Manuela; Moutinho, José; Pinheiro, Antonio M. G.Breast ultrasound images have several attractive properties that make them an interesting tool in breast cancer detection. However, their intrinsic high noise rate and low contrast turn mass detection and segmentation into a challenging task. In this article, a fully automated two-stage breast mass segmentation approach is proposed. In the initial stage, ultrasound images are segmented using support vector machine or discriminant analysis pixel classification with a multiresolution pixel descriptor. The features are extracted using non-linear diffusion, bandpass filtering and scale-variant mean curvature measures. A set of heuristic rules complement the initial segmentation stage, selecting the region of interest in a fully automated manner. In the second segmentation stage, refined segmentation of the area retrieved in the first stage is attempted, using two different techniques. The AdaBoost algorithm uses a descriptor based on scale-variant curvature measures and non-linear diffusion of the original image at lower scales, to improve the spatial accuracy of the ROI. Active contours use the segmentation results from the first stage as initial contours. Results for both proposed segmentation paths were promising, with normalized Dice similarity coefficients of 0.824 for AdaBoost and 0.813 for active contours. Recall rates were 79.6% for AdaBoost and 77.8% for active contours, whereas the precision rate was 89.3% for both methods.
- Quality Evaluation of Machine Learning-based Point Cloud Coding SolutionsPublication . Prazeres, João; Rodrigues, Rafael; Pereira, Manuela; Pinheiro, Antonio M. G.In this paper, a quality evaluation of three point cloud coding solutions based on machine learning technology is presented, notably, ADLPCC, PCC_GEO_CNN, and PCGC, as well as LUT_SR, which uses multi-resolution Look-Up Tables. Moreover, the MPEG G-PCC was used as an anchor. A set of six point clouds, representing both landscapes and objects were coded using the five encoders at different bit rates, and a subjective test, where the distorted and reference point clouds were rotated in a video sequence side by side, is carried out to assess their performance. Furthermore, the performance of point cloud objective quality metrics that usually provide a good representation of the coded content is analyzed against the subjective evaluation results. The obtained results suggest that some of these metrics fail to provide a good representation of the perceived quality, and thus are not suitable to evaluate some distortions created by machine learning-based solutions. A comparison between the analyzed metrics and the type of represented scene or codec is also presented.
- MPEG DASH - some QoE-based insights into the tradeoff between audio and video for live music concert streaming under congested network conditionsPublication . Rodrigues, Rafael; Pocta, Peter; Melvin, Hugh; Pereira, Manuela; Pinheiro, Antonio M. G.The rapid adoption of MPEG-DASH is testament to its core design principles that enable the client to make the informed decision relating to media encoding representations, based on network conditions, device type and preferences. Typically, the focus has mostly been on the different video quality representations rather than audio. However, for device types with small screens, the relative bandwidth budget difference allocated to the two streams may not be that large. This is especially the case if high quality audio is used, and in this scenario, we argue that increased focus should be given to the bit rate representations for audio. Arising from this, we have designed and implemented a subjective experiment to evaluate and analyses the possible effect of using different audio quality levels. In particular, we investigate the possibility of providing reduced audio quality so as to free up bandwidth for video under certain conditions. Thus, the experiment was implemented for live music concert scenarios transmitted over mobile networks, and we suggest that the results will be of significant interest to DASH content creators when considering bandwidth tradeoff between audio and video.
- On the Subjective Assessment of the Perceived Quality of Medical Images and VideosPublication . Lévêque, Lucie; Liu, Hantao; Baraković, Sabina; Barakovic Husic, Jasmina; Martini, Maria G; Outtas, Meriem; Zhang, Lu; Kumcu, Asli; Platisa, Ljiljana; Rodrigues, Rafael; Pinheiro, Antonio M. G.; Skodras, AthanassiosMedical professionals are viewing an increasing number of images and videos in their clinical routine. However, various types of distortions can affect medical imaging data, and therefore impact the viewers’ experienced quality and their clinical practice. Thus it is necessary to quantify this impact and understand how the viewers, i.e., medical experts, perceive the quality of (distorted) images and videos. In this paper, we present an up-to-date review of the methodologies used in the literature for the subjective quality assessment of medical images and videos and discuss their merits and drawbacks depending on the use case.