António M. G. Pinheiro

Factors Influencing Quality of Experience

In this chapter different factors that may influence Quality of Experience (QoE) in the context of media consumption, networked services, and other electronic communication services and applications, are discussed. QoE can be subject to a range of complex and strongly interrelated factors, falling into three categories: human, system and context influence factors (IFs). With respect to Human IFs, we discuss variant and stable factors that may potentially bear an influence on QoE, either for low-level (bottom-up) or higher-level (top-down) cognitive processing. System IFs are classified into four distinct categories, namely content-, media-, network- and device-related IFs. Finally, the broad category of possible Context IFs is decomposed into factors linked to the physical, temporal, social, economic, task and technical information context. The overview given here illustrates the complexity of QoE and the broad range of aspects that potentially have a major influence on it.

HDR image compression: A new challenge for objective quality metrics

High Dynamic Range (HDR) imaging is able to capture a wide range of luminance values, closer to what the human visual system can perceive. It is believed by many that HDR is a technology that will revolutionize TV and cinema industry similar to how color television did. However, the complexity of HDR requires reinvention of the whole chain from capture to display. In this paper, HDR images compressed with the upcoming JPEG XT HDR image coding standard are used to investigate the correlation between thirteen well known full-reference metrics and perceived quality of HDR content. The metrics are benchmarked using ground truth subjective scores collected during quality evaluations performed on a Dolby Pulsar HDR monitor. Results demonstrate that objective quality assessment of HDR image compression is challenging. Most of the tested metrics, with exceptions of HDR-VDP-2 and FSIM computed for luma component, poorly predict human perception of visual quality.

Performance evaluation of the emerging JPEG XT image compression standard

The upcoming JPEG XT is under development for High Dynamic Range (HDR) image compression. This standard encodes a Low Dynamic Range (LDR) version of the HDR image generated by a Tone-Mapping Operator (TMO) using the conventional JPEG coding as a base layer and encodes the extra HDR information in a residual layer. This paper studies the performance of the three profiles of JPEG XT (referred to as profiles A, B and C) using a test set of six HDR images. Four TMO techniques were used for the base layer image generation to assess the influence of the TMOs on the performance of JPEG XT profiles. Then, the HDR images were coded with different quality levels for the base layer and for the residual layer. The performance of each profile was evaluated using Signal to Noise Ratio (SNR), Feature SIMilarity Index (FSIM), Root Mean Square Error (RMSE), and CIEDE2000 color difference objective metrics. The evaluation results demonstrate that profiles A and B lead to similar saturation of quality at the higher bit rates, while profile C exhibits no saturation. Profiles B and C appear to be more dependent on TMOs used for the base layer compared to profile A.

Piecewise Approximation of Contours Through Scale-Space Selection of Dominant Points

This paper describes a method of approximating a shape contour with a polygon. The polygon vertices are extracted from the curvature extremes, through a scale-space description of the contour, via linear diffusion. These vertices are located on the contour points where the sharper changes of the contour directions occur. Using a proper strategy, a set of extremes that result in a given approximation level is chosen. By adding new vertices, the approximation level can be improved, and a scalable representation of the contour is identified. This method results in an approximation that discriminates local from global geometric features and provides a good visual representation of the original contour. This polygonal approximation method is used for scalable encoding of the shape contours. In this regard, an encoding technique suitable for scalable polygonal approximation has been developed. We show that encoding the approximated polygons result in a good relation between the distortion and the bitrate. Finally, we show that in addition to coding this method can be efficiently used for shape comparison and shape retrieval.

Image Descriptors Based on the Edge Orientation

Edges are one of the most important image visual features. They are highly related with shapes and can also be representative of the image textures. Edge orientation histograms are usually very reliable descriptors suitable for image analysis, search and retrieval. In this work two methods to compute edge based orientation descriptors are reported: the Edge Pixel Orientations Histogram and the Angular Orientation Partition Edge Descriptor.Edges are detected with Canny algorithm. The resulting edge pixels are separated into No gradient orientation intervals.For the first descriptor, edges detected without and with hysteresis, result in a histogram of gradient orientations. The two edge images are divided into NxN sub-images, resulting in a 2 No N N bins histogram.In the second descriptor, after an angular division of the image, edges are described by their angular orientations. Considering Na angular divisions, and No angular orientations, a descriptor with No Na bins results.Because of the angular geometry, this descriptor is resilient to rotation and by shifting the center of the angular division it is also possible to add translation resilience.Two examples of automatic image semantic annotation using this description method is reported using a database with 738 keyframes and the JPSearch database with 971 high resolution images (3888x2592).The K Nearest Neighbor is used as classifier and the Manhattan distance is used for image similarity computation. The two descriptors annotation performance are compared between them, with the MPEG-7 Edge Histogram Descriptor and with the SIFT descriptor.

Comparative analysis of autofocus functions in digital in-line phase-shifting holography

Numerical reconstruction of digital holograms relies on a precise knowledge of the original object position. However, there are a number of relevant applications where this parameter is not known in advance and an efficient autofocusing method is required. This paper addresses the problem of finding optimal focusing methods for use in reconstruction of digital holograms of macroscopic amplitude and phase objects, using digital in-line phase-shifting holography in transmission mode. Fifteen autofocus measures, including spatial-, spectral-, and sparsity-based methods, were evaluated for both synthetic and experimental holograms. The Fresnel transform and the angular spectrum reconstruction methods were compared. Evaluation criteria included unimodality, accuracy, resolution, and computational cost. Autofocusing under angular spectrum propagation tends to perform better with respect to accuracy and unimodality criteria. Phase objects are, generally, more difficult to focus than amplitude objects. The normalized variance, the standard correlation, and the Tenenbaum gradient are the most reliable spatial-based metrics, combining computational efficiency with good accuracy and resolution. A good trade-off between focus performance and computational cost was found for the Fresnelet sparsity method.

A Two-Step Segmentation Method for Breast Ultrasound Masses Based on Multi-resolution Analysis.

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.

Optic Disc Localization in Retinal Images Based on Cumulative Sum Fields

This paper describes an automatic method for the optic disc localization in retinal images, which is effective and reliable with multiple datasets. Particularly, the described method reveals very effective dealing with retinal images with large pathological signs. The algorithm begins with a new vessel enhancement method based on a modified corner detector. Subsequently, a weighted version of the vessel enhancement is combined with morphological operators, to detect the four main vessels orientations {0°, 45°, 90°, 135°}. These four image functions have all the necessary information to determine an initial optic disc localization, resulting in two images that are respectively divided along the vertical or horizontal orientations with different division sizes. Each division is averaged creating a 2-D step function, and a cumulative sum of the different sizes step functions is calculated in the vertical and horizontal orientations, resulting in an initial optic disc position. The final optic disc localization is determined by a vessel convergence algorithm using its two most relevant features; high vasculature convergence and high intensity values. The proposed method was evaluated in eight publicly available datasets, including the STARE and DRIVE datasets. The optic disc was localized correctly in 1752 out of the 1767 retinal images (99.15%) with an average computation time of 18.34 s.

Annotation of medical images using the SURF descriptor

This paper describes a method for medical images annotation based on the SURF descriptor and the SVM classifier. For the features extraction a Fast-Hessian detector was used. The feature matching was performed with a SVM with a quadratic kernel. The testing of the developed system was performed using a subset of the IRMA radiographic images. The results provided with the SURF descriptor are compared with the ones obtained using the SIFT descriptor with SVM classification. Applying the SURF descriptor resulted in improved classification of lung images with an accuracy over 96%. The research shows that the SURF is a potentially strong tool to be applied in the field of medical image annotation. Together with the SVM classification it may construct an efficient system for automatic medical image retrieval and annotation.

Shape matching using a curvature based polygonal approximation in scale-space

The emerging MPEG-7 standard demands shape description and shape retrieval techniques. Polygonal approximations of the shape contours give attractive solutions in this domain, because of the description simplicity. This paper introduces a shape matching technique based on the turning function comparison of the shape contour polygonal approximations.