Loading...
16 results
Search Results
Now showing 1 - 10 of 16
- 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.
- Application of texture analysis to muscle MRI: 1-What kind of information should be expected from texture analysis?Publication . Certaines, Jacques De; Larcher, Thibaut; Duda, Dorota; Azzabou, Noura; Eliat, Pierre-Antoine; Escudero, Luis M.; Pinheiro, Antonio M. G.; Yang, Guanyu; Coatrieux, Jean-Louis; Snezkho, Eduard; Shukelovich, Alexey; Pereira, Manuela; Lerski, RichardSeveral previous clinical or preclinical studies using computerized texture analysis of MR Images have demonstrated much more clinical discrimination than visual image analysis by the radiologist. In muscular dystrophy, a discriminating power has been already demonstrated with various methods of texture analysis of magnetic resonance images (MRI-TA). Unfortunately, a scale gap exists between the spatial resolutions of histological and MR images making a direct correlation impossible. Furthermore, the effect of the various histological modifications on the gray level of each pixel is complex and cannot be easily analyzed. Consequently, clinicians will not accept the use of MRI-TA in routine practice if TA remains a “black box” without clinical correspondence at a tissue level. A goal therefore of the multicenter European COST action MYO-MRI is to optimize MRI-TA methods in muscular dystrophy and to elucidate the histological meaning of MRI textures.
- Quality comparison of the HEVC and VP9 encoders performancePublication . Fernandes, Pedro; Bernardo, Marco; Pinheiro, Antonio M. G.; Fiadeiro, Paulo; Pereira, ManuelaThis paper reports a comparison between two recent video codecs, namely the HEVC and the VP9, using High Definition Video Sequences encoded with different bit rates. A subjective test for the evaluation of the provided Quality of Experience is reported. The video sequences were shown to a panel of subjects on a High Definition LED display and the subjective tests were performed using a Single Stimulus Methodology. The results shown that the HEVC encoder provides a better visual quality on low bit rates than the VP9. Similar performance was obtained for visually lossless conditions, although the HEVC requires lower bit rates to reach that level. Moreover, the correlation of the subjective evaluation and three tested objective metrics (PSNR, SSIM, and FSIM) revealed a good representation of the subjective results, particularly the SSIM and the FSIM metrics.
- 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.
- 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.
- Motion estimation with chessboard pattern prediction strategyPublication . Amirpour, Hadi; Ghanbari, Mohammad; Pinheiro, Antonio M. G.; Pereira, ManuelaDue to high correlations among the adjacent blocks, several algorithms utilize movement information of spatially and temporally correlated neighboring blocks to adapt their search patterns to that information. In this paper, this information is used to define a dynamic search pattern. Each frame is divided into two sets, black and white blocks, like a chessboard pattern and a different search pattern, is defined for each set. The advantage of this definition is that the number of spatially neighboring blocks is increased for each current block and it leads to a better prediction for each block. Simulation results show that the proposed algorithm is closer to the Full-Search algorithm in terms of quality metrics such as PSNR than the other state-of-the-art algorithms while at the same time the average number of search points is less.
- 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.
- Assessment of speckle denoising filters for digital holography using subjective and objective evaluation modelsPublication . Fonseca, Elsa; Fiadeiro, Paulo; Bernardo, Marco V.; Pinheiro, Antonio M. G.; Pereira, ManuelaDigital holography is an emerging imaging technique for displaying and sensing three dimensional objects. The perceived image quality of a hologram is frequently corrupted by speckle noise due to coherent illumination. Although several speckle noise reduction methods have been developed so far, there are scarce quality assessment studies to address their performance and they typically focus solely on objective metrics. However, these metrics do not reflect the visual quality perceived by a human observer. In this work, the performance of four speckle reduction algorithms, namely the nonlocal means, the Lee, the Frost and the block matching 3D filters, with varying parameterizations, were subjectively evaluated. The results were ranked with respect to the perceived image quality to obtain the mean opinion scores using pairwise comparison. The correlation between the subjective results and twenty different no-reference objective quality metrics was evaluated. The experiment indicates that block matching 3D and Lee are the preferred filters, depending on hologram characteristics. The best performing objective metrics were identified for each filter.