Super-resolution (SR) is a filtering technique that combines a sequence of under-sampled and degraded low-resolution images to produce an image at a higher resolution. The reconstruction takes advantage of the additional spatio-temporal data available in the sequence of images portraying the same scene. The fundamental problem addressed in super-resolution is a typical example of an inverse problem, wherein multiple low-resolution (LR)images are used to solve for the original high-resolution (HR) image. Super-resolution has already proved useful in many practical cases where multiple frames of the same scene can be obtained, including medical applications, satellite imaging and astronomical observatories. The application of super resolution filtering in consumer cameras and mobile devices shall be possible in the future, especially that the computational and memory resources in these devices are increasing all the time. For that goal, several research problems need to be ...

Air pollution remains a major global challenge, particularly in urban areas where high pollutant concentrations negatively impact public health and contribute to climate change. Among the various pollutants, biogenic volatile organic compounds (BVOCs) play a critical role in atmospheric chemistry, influencing the formation of secondary organic aerosols and ground-level ozone, affecting air quality and climate dynamics. Accurately estimating BVOC emissions at high spatial resolution is challenging due to the limitations of satellite observations and computational models. Additionally, forecasting nitrogen dioxide (NO2) concentrations in urban environments is vital for effective air quality management, yet existing models often struggle to capture complex spatiotemporal dependencies. The thesis aims to address these challenges by proposing novel deep learning (DL) frameworks to tackle two key tasks: (i) improving the spatial resolution of BVOC emission maps through super-resolution (SR) techniques and (ii) developing a robust model ...

Recently, significant advances in the field of automated face recognition have been achieved using computer vision, machine learning, and deep learning methodologies. However, despite claims of super-human performance of face recognition algorithms on select key benchmark tasks, there remain several open problems that preclude the general replacement of human face recognition work with automated systems. State-of-the-art automated face recognition systems based on deep learning methods are able to achieve high accuracy when the face images they are tasked with recognizing subjects from are of sufficiently high quality. However, low image resolution remains one of the principal obstacles to face recognition systems, and their performance in the low-resolution regime is decidedly below human capabilities. In this PhD thesis, we present a systematic study of modern automated face recognition systems in the presence of image degradation in various forms. Based on our ...

This thesis concerns the use of spatial and tonal adaptivity in improving the resolution of aliased image sequences under scene or camera motion. Each of the five content chapters focuses on a different subtopic of super-resolution: image registration (chapter 2), image fusion (chapter 3 and 4), super-resolution restoration (chapter 5), and super-resolution synthesis (chapter 6). Chapter 2 derives the Cramer-Rao lower bound of image registration and shows that iterative gradient-based estimators achieve this performance limit. Chapter 3 presents an algorithm for image fusion of irregularly sampled and uncertain data using robust normalized convolution. The size and shape of the fusion kernel is adapted to local curvilinear structures in the image. Each data sample is assigned an intensity-related certainty value to limit the influence of outliers. Chapter 4 presents two fast implementations of the signal-adaptive bilateral filter. The xy-separable implementation filters ...

In scalable image/video coding, high resolution content is encoded to the highest visual quality and the bit-streams are adapted to cater various communication channels, display devices and usage requirements. These content adaptations, which include quality, resolution and frame rate scaling may also affect the content protection data, such as, watermarks and are considered as a potential watermark attack. In this thesis, research on robust watermarking techniques for scalable coded image and video, are proposed and the improvements in robustness against various content adaptation attacks, such as, JPEG 2000 for image and Motion JPEG 2000, MC-EZBC and H.264/SVC for video, are reported. The spread spectrum domain, particularly wavelet-based image watermarking schemes often provides better robustness to compression attacks due to its multi-resolution decomposition and hence chosen for this work. A comprehensive and comparative analysis of the available wavelet-based watermarking schemes,is performed ...

The work presented in this thesis covers topics that extend the scalability functionalities in video coding and improve the compression performance. Two main novel approaches are presented, each targeting a different part of the scalable video coding (SVC) architecture: motion adaptive wavelet transform based on the wavelet transform in lifting implementation, and a design of a flexible framework for generalised spatio-temporal decomposition. Motion adaptive wavelet transform is based on the newly introduced concept of connectivity-map. The connectivity-map describes the underlying irregular structure of regularly sampled data. To enable a scalable representation of the connectivity-map, the corresponding analysis and synthesis operations have been derived. These are then employed to define a joint wavelet connectivity-map decomposition that serves as an adaptive alternative to the conventional wavelet decomposition. To demonstrate its applicability, the presented decomposition scheme is used in the proposed SVC framework, ...

Ill-posed inverse problems appear in many signal and image processing applications, such as deblurring, super-resolution and compressed sensing. The common approach to address them is to design a specific algorithm, or recently, a specific deep neural network, for each problem. Both signal processing and machine learning tactics have drawbacks: traditional reconstruction strategies exhibit limited performance for complex signals, such as natural images, due to the hardness of their mathematical modeling; while modern works that circumvent signal modeling by training deep convolutional neural networks (CNNs) suffer from a huge performance drop when the observation model used in training is inexact. In this work, we develop and analyze reconstruction algorithms that are not restricted to a specific signal model and are able to handle different observation models. Our main contributions include: (a) We generalize the popular sparsity-based CoSaMP algorithm to any signal ...

High compression ratio, scalability and reliability are the main issues for transmitting multimedia content over best effort networks. Scalable image and video coding meets the user requirements by truncating the scalable bitstream at different quality, resolution and frame rate. However, the performance of scalable coding deteriorates rapidly over packet networks if the base layer packets are lost during transmission. Multiple description coding (MDC) has emerged as an effective source coding technique for robust image and video transmission over lossy networks. In this research problem of incorporating scalability in MDC for robust image and video transmission over best effort network is addressed. The first contribution of this thesis is to propose a strategy for generating more than two descriptions using multiple description scalar quantizer (MDSQ) with an objective to jointly decoded any number of descriptions in balanced and unbalanced manner. The ...

Speech Enhancement (SE) is a vital technology for online human communication. Applications of Deep Neural Network (DNN) technologies in concert with traditional signal processing approaches to the task have revolutionised both the research and implementation of SE in recent years. However, the training objective of these Neural Network Speech Enhancement (NNSE) systems generally do not consider the psychoacoustic processing which occurs in the human auditory system. As a result, enhanced audio can often contain auditory artefacts which degrade the perceptual quality or intelligibility of the speech. To overcome this, systems which directly incorporate psychoacoustically motivated measures into the training objectives of NNSE systems have been proposed. A key development in speech audio processing in recent years is the emergence of Self Supervised Speech Representation (SSSR) models. These are powerful foundational DNN models which can be utilised for a number of ...

Scalable representation of a source (e.g., image/video/3D mesh) enables decoding of the encoded bit-stream on a variety of end-user terminals with varying display, storage and processing capabilities. Furthermore, it allows for source communication via channels with different transmission bandwidths, as the source rate can be easily adapted to match the available channel bandwidth. From a different perspective, error-resilience against channel losses is also very important when transmitting scalable source streams over lossy transmission channels. Driven by the aforementioned requirements of scalable representation and error-resilience, this dissertation focuses on the analysis and design of scalable single and multiple description scalar quantizers. In the first part of this dissertation, we consider the design of scalable wavelet-based semi-regular 3D mesh compression systems. In this context, our design methodology thoroughly analyzes different modules of the mesh coding system in order to single-out appropriate design ...

This thesis discusses approaches and techniques to convert Sparsely-Sampled Light Fields (SSLFs) into Densely-Sampled Light Fields (DSLFs), which can be used for visualization on 3DTV and Virtual Reality (VR) devices. Exemplarily, a movable 1D large-scale light field acquisition system for capturing SSLFs in real-world environments is evaluated. This system consists of 24 sparsely placed RGB cameras and two Kinect V2 sensors. The real-world SSLF data captured with this setup can be leveraged to reconstruct real-world DSLFs. To this end, three challenging problems require to be solved for this system: (i) how to estimate the rigid transformation from the coordinate system of a Kinect V2 to the coordinate system of an RGB camera; (ii) how to register the two Kinect V2 sensors with a large displacement; (iii) how to reconstruct a DSLF from a SSLF with moderate and large disparity ranges. ...

The generation and manipulation of digital images is made simple by widely available digital cameras and image processing software. As a consequence, we can no longer take the authenticity of a digital image for granted. This thesis investigates the problem of protecting the trustworthiness of digital images. Image authentication aims to verify the authenticity of a digital image. General solution of image authentication is based on digital signature or watermarking. A lot of studies have been conducted for image authentication, but thus far there has been no solution that could be robust enough to transmission errors during images transmission over lossy channels. On the other hand, digital image forensics is an emerging topic for passively assessing image authenticity, which works in the absence of any digital watermark or signature. This thesis focuses on how to assess the authenticity images when ...

Meningioma subtypes classification is a real world problem from the domain of histological image analysis that requires new methods for its resolution. Computerised histopathology presents a whole new set of problems and introduces new challenges in image classification. High intra-class variation and low inter-class differences in textures is often an issue in histological image analysis problems such as Meningioma subtypes classification. In this thesis, we present an adaptive wavelets based technique that adapts to the variation in the texture of meningioma samples and provides high classification accuracy results. The technique provides a mechanism for attaining an image representation consisting of various spatial frequency resolutions that represent the image and are referred to as subbands. Each subband provides different information pertaining the texture in the image sample. Our novel method, the Adaptive Discriminant Wavelet Packet Transform (ADWPT), provides a means for ...

The recent progress in artificial neural networks (rebranded as “deep learning”) has significantly boosted the state-of-the-art in numerous domains of computer vision offering an opportunity to approach the problems which were hardly solvable with conventional machine learning. Thus, in the frame of this PhD study, we explore how deep learning techniques can help in the analysis of one the most basic and essential semantic traits revealed by a human face, namely, gender and age. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes. Convolutional Neural Network (CNN) has currently become a standard model for image-based object recognition in general, and therefore, is a natural choice for addressing the first of these two problems. However, our preliminary studies have shown that the ...

Hyperspectral (HS) imaging, which consists of acquiring a same scene in several hundreds of contiguous spectral bands (a three dimensional data cube), has opened a new range of relevant applications, such as target detection [MS02], classification [C.-03] and spectral unmixing [BDPD+12]. However, while HS sensors provide abundant spectral information, their spatial resolution is generally more limited. Thus, fusing the HS image with other highly resolved images of the same scene, such as multispectral (MS) or panchromatic (PAN) images is an interesting problem. The problem of fusing a high spectral and low spatial resolution image with an auxiliary image of higher spatial but lower spectral resolution, also known as multi-resolution image fusion, has been explored for many years [AMV+11]. From an application point of view, this problem is also important as motivated by recent national programs, e.g., the Japanese next-generation space-borne ...