User-driven quality of experience modelling for mobile video optimisation

The increasing demand for mobile video has attracted much attention from both industry and researchers. To satisfy users and to facilitate the usage of mobile video, providing optimal quality to the users is necessary. As a result, quality of experience (QoE) becomes an important focus in measuring the overall quality perceived by the end-users, from the aspects of both objective system performance and subjective experience. However, due to the complexity of user experience and diversity of resources (such as videos, networks and mobile devices), it is still challenging to develop QoE models for mobile video that can represent how user-perceived value varies with changing conditions. Previous QoE modelling research has two main limitations: aspects influencing QoE are insufficiently considered; and acceptability as the user value is seldom studied. Focusing on the QoE modelling issues, two aims are defined in this thesis: (i) investigating the key influencing factors of mobile video QoE; and (ii) establishing QoE prediction models based on the relationships between user acceptability and the influencing factors, in order to help provide optimal mobile video quality. To achieve the first goal, a comprehensive user study was conducted. It investigated the main impacts on user acceptance: video encoding parameters such as quantization parameter, spatial resolution, frame rate, and encoding bitrate; video content type; mobile device display resolution; and user profiles including gender, preference for video content, and prior viewing experience. Results from both quantitative and qualitative analysis revealed the significance of these factors, as well as how and why they influenced user acceptance of mobile video quality. Based on the results of the user study, statistical techniques were used to generate a set of QoE models that predict the subjective acceptability of mobile video quality by using a group of the measurable influencing factors, including encoding parameters and bitrate, content type, and mobile device display resolution. Applying the proposed QoE models into a mobile video delivery system, optimal decisions can be made for determining proper video coding parameters and for delivering most suitable quality to users. This would lead to consistent user experience on different mobile video content and efficient resource allocation. The findings in this research enhance the understanding of user experience in the field of mobile video, which will benefit mobile video design and research. This thesis presents a way of modelling QoE by emphasising user acceptability of mobile video quality, which provides a strong connection between technical parameters and user-desired quality. Managing QoE based on acceptability promises the potential for adapting to the resource limitations and achieving an optimal QoE in the provision of mobile video content.

Robust image hash functions using higher order spectra

Robust hashing is an emerging field that can be used to hash certain data types in applications unsuitable for traditional cryptographic hashing methods. Traditional hashing functions have been used extensively for data/message integrity, data/message authentication, efficient file identification and password verification. These applications are possible because the hashing process is compressive, allowing for efficient comparisons in the hash domain but non-invertible meaning hashes can be used without revealing the original data. These techniques were developed with deterministic (non-changing) inputs such as files and passwords. For such data types a 1-bit or one character change can be significant, as a result the hashing process is sensitive to any change in the input. Unfortunately, there are certain applications where input data are not perfectly deterministic and minor changes cannot be avoided. Digital images and biometric features are two types of data where such changes exist but do not alter the meaning or appearance of the input. For such data types cryptographic hash functions cannot be usefully applied. In light of this, robust hashing has been developed as an alternative to cryptographic hashing and is designed to be robust to minor changes in the input. Although similar in name, robust hashing is fundamentally different from cryptographic hashing. Current robust hashing techniques are not based on cryptographic methods, but instead on pattern recognition techniques. Modern robust hashing algorithms consist of feature extraction followed by a randomization stage that introduces non-invertibility and compression, followed by quantization and binary encoding to produce a binary hash output. In order to preserve robustness of the extracted features, most randomization methods are linear and this is detrimental to the security aspects required of hash functions. Furthermore, the quantization and encoding stages used to binarize real-valued features requires the learning of appropriate quantization thresholds. How these thresholds are learnt has an important effect on hashing accuracy and the mere presence of such thresholds are a source of information leakage that can reduce hashing security. This dissertation outlines a systematic investigation of the quantization and encoding stages of robust hash functions. While existing literature has focused on the importance of quantization scheme, this research is the first to emphasise the importance of the quantizer training on both hashing accuracy and hashing security. The quantizer training process is presented in a statistical framework which allows a theoretical analysis of the effects of quantizer training on hashing performance. This is experimentally verified using a number of baseline robust image hashing algorithms over a large database of real world images. This dissertation also proposes a new randomization method for robust image hashing based on Higher Order Spectra (HOS) and Radon projections. The method is non-linear and this is an essential requirement for non-invertibility. The method is also designed to produce features more suited for quantization and encoding. The system can operate without the need for quantizer training, is more easily encoded and displays improved hashing performance when compared to existing robust image hashing algorithms. The dissertation also shows how the HOS method can be adapted to work with biometric features obtained from 2D and 3D face images.

Reply by authors to J.C. Wilcox

This is a reply to "Comment on 'Online Estimation of Allan Variance Parameters' " by James C.Wilcox published in JOURNAL OF GUIDANCE, CONTROL, AND DYNAMICS Vol. 24, No. 3, May–June 2001. OUR statement “Modern gyros provide angular rate measurements directly, and hence, angular quantization is meaningless” made in the original paper should first be read with the accompanying sentences in the paragraph. The meaning of the sentence would perhaps have been clearer if written". . .

A flexible hierarchical approach for facial age estimation based on multiple features

Age estimation from facial images is increasingly receiving attention to solve age-based access control, age-adaptive targeted marketing, amongst other applications. Since even humans can be induced in error due to the complex biological processes involved, finding a robust method remains a research challenge today. In this paper, we propose a new framework for the integration of Active Appearance Models (AAM), Local Binary Patterns (LBP), Gabor wavelets (GW) and Local Phase Quantization (LPQ) in order to obtain a highly discriminative feature representation which is able to model shape, appearance, wrinkles and skin spots. In addition, this paper proposes a novel flexible hierarchical age estimation approach consisting of a multi-class Support Vector Machine (SVM) to classify a subject into an age group followed by a Support Vector Regression (SVR) to estimate a specific age. The errors that may happen in the classification step, caused by the hard boundaries between age classes, are compensated in the specific age estimation by a flexible overlapping of the age ranges. The performance of the proposed approach was evaluated on FG-NET Aging and MORPH Album 2 datasets and a mean absolute error (MAE) of 4.50 and 5.86 years was achieved respectively. The robustness of the proposed approach was also evaluated on a merge of both datasets and a MAE of 5.20 years was achieved. Furthermore, we have also compared the age estimation made by humans with the proposed approach and it has shown that the machine outperforms humans. The proposed approach is competitive with current state-of-the-art and it provides an additional robustness to blur, lighting and expression variance brought about by the local phase features.

Class-specific sparse codes for representing activities

In this paper we investigate the effectiveness of class specific sparse codes in the context of discriminative action classification. The bag-of-words representation is widely used in activity recognition to encode features, and although it yields state-of-the art performance with several feature descriptors it still suffers from large quantization errors and reduces the overall performance. Recently proposed sparse representation methods have been shown to effectively represent features as a linear combination of an over complete dictionary by minimizing the reconstruction error. In contrast to most of the sparse representation methods which focus on Sparse-Reconstruction based Classification (SRC), this paper focuses on a discriminative classification using a SVM by constructing class-specific sparse codes for motion and appearance separately. Experimental results demonstrates that separate motion and appearance specific sparse coefficients provide the most effective and discriminative representation for each class compared to a single class-specific sparse coefficients.