The explosion of Deep Learning (DL) added a boost to the already rapidly developing field of Computer Vision to such a point that vision-based tasks are now parts of our everyday lives. Applications such as image classification, photo stylization, or face recognition are nowadays pervasive, as evidenced by the advent of modern systems trivially integrated into mobile applications. In this thesis, we investigated and enhanced the visual counting task, which automatically estimates the number of objects in still images or video frames. Recently, due to the growing interest in it, several Convolutional Neural Network (CNN)-based solutions have been suggested by the scientific community. These artificial neural networks, inspired by the organization of the animal visual cortex, provide a way to automatically learn effective representations from raw visual data and can be successfully employed to address typical challenges characterizing this task, ...

It takes more time to think of a silent scene, action or event than finding one that emanates sound. Not only speaking or playing music but almost everything that happens is accompanied with or results in one or more sounds mixed together. This makes acoustic event detection (AED) one of the most researched topics in audio signal processing nowadays and it will probably not see a decline anywhere in the near future. This is due to the thirst for understanding and digitally abstracting more and more events in life via the enormous amount of recorded audio through thousands of applications in our daily routine. But it is also a result of two intrinsic properties of audio: it doesn’t need a direct sight to be perceived and is less intrusive to record when compared to image or video. Many applications such ...

Gliomas represent about 80% of all malignant primary brain tumors. Despite recent advancements in glioma research, patient outcome remains poor. The 5 year survival rate of the most common and most malignant subtype, i.e. glioblastoma, is about 5%. Magnetic resonance imaging (MRI) has become the imaging modality of choice in the management of brain tumor patients. Conventional MRI (cMRI) provides excellent soft tissue contrast without exposing the patient to potentially harmful ionizing radiation. Over the past decade, advanced MRI modalities, such as perfusion-weighted imaging (PWI), diffusion-weighted imaging (DWI) and magnetic resonance spectroscopic imaging (MRSI) have gained interest in the clinical field, and their added value regarding brain tumor diagnosis, treatment planning and follow-up has been recognized. Tumor segmentation involves the imaging-based delineation of a tumor and its subcompartments. In gliomas, segmentation plays an important role in treatment planning as well ...

The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this thesis, we address the challenges of knowledge transfer through embedding spaces that capture and store hierarchical knowledge. In the first part of the thesis, we focus on the problem of cross-domain knowledge transfer. We first address zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We train two coupled dictionaries which align visual and semantic domains via an intermediate embedding space. We then extend this idea by training deep networks that ...

Recent advances in many fields ranging from engineering to natural science, require increasingly complicated optimization tasks in the experiment design, for which the target objectives are generally in the form of black-box functions that are expensive to evaluate. In a common formulation of this problem, a designer is expected to solve the black-box optimization tasks via sequentially attempting candidate solutions and receiving feedback from the system. This thesis considers Bayesian optimization (BO) as the black-box optimization framework, and investigates the enhancements on BO from the aspects of efficiency, adaptation and reliability. Generally, BO consists of a surrogate model for providing probabilistic inference and an acquisition function which leverages the probabilistic inference for selecting the next candidate solution. Gaussian process (GP) is a prominent non-parametric surrogate model, and the quality of its inference is a critical factor on the optimality performance ...

Distributed signal or information processing using Internet of Things (IoT), facilitates real-time monitoring of signals, for example, environmental pollutants, health indicators, and electric energy consumption in a smart city. Despite the promising capabilities of IoTs, these distributed deployments often face the challenge of data privacy and communication rate constraints. In traditional machine learning, training data is moved to a data center, which requires massive data movement from distributed IoT devices to a third-party location, thus raising concerns over privacy and inefficient use of communication resources. Moreover, the growing network size, model size, and data volume combined lead to unusual complexity in the design of optimization algorithms beyond the compute capability of a single device. This necessitates novel system architectures to ensure stable and secure operations of such networks. Federated learning (FL) architecture, a novel distributed learning paradigm introduced by McMahan ...

Voice biometric systems use automatic speaker verification (ASV) technology for user authentication. Even if it is among the most convenient means of biometric authentication, the robustness and security of ASV in the face of spoofing attacks (or presentation attacks) is of growing concern and is now well acknowledged by the research community. A spoofing attack involves illegitimate access to personal data of a targeted user. Replay is among the simplest attacks to mount - yet difficult to detect reliably and is the focus of this thesis. This research focuses on the analysis and design of existing and novel countermeasures for replay attack detection in ASV, organised in two major parts. The first part of the thesis investigates existing methods for spoofing detection from several perspectives. I first study the generalisability of hand-crafted features for replay detection that show promising results ...

This thesis presents novel exemplar-based texture synthesis methods for image prediction (i.e., predictive coding) and image inpainting problems. The main contributions of this study can also be seen as extensions to simple template matching, however the texture synthesis problem here is well-formulated in an optimization framework with different constraints. The image prediction problem has first been put into sparse representations framework by approximating the template with a sparsity constraint. The proposed sparse prediction method with locally and adaptive dictionaries has been shown to give better performance when compared to static waveform (such as DCT) dictionaries, and also to the template matching method. The image prediction problem has later been placed into an online dictionary learning framework by adapting conventional dictionary learning approaches for image prediction. The experimental observations show a better performance when compared to H.264/AVC intra and sparse prediction. ...

Automatic ear recognition systems have seen increased interest over recent years due to multiple desirable characteristics. Ear images used in such systems can typically be extracted from profile head shots or video footage. The acquisition procedure is contactless and non-intrusive, and it also does not depend on the cooperation of the subjects. In this regard, ear recognition technology shares similarities with other image-based biometric modalities. Another appealing property of ear biometrics is its distinctiveness. Recent studies even empirically validated existing conjectures that certain features of the ear are distinct for identical twins. This fact has significant implications for security-related applications and puts ear images on a par with epigenetic biometric modalities, such as the iris. Ear images can also supplement other biometric modalities in automatic recognition systems and provide identity cues when other information is unreliable or even unavailable. In ...

The large number of practical applications involving digital images has motivated a significant interest towards restoration solutions that improve the visual quality of the data under the presence of various acquisition and compression artifacts. Digital images are the results of an acquisition process based on the measurement of a physical quantity of interest incident upon an imaging sensor over a specified period of time. The quantity of interest depends on the targeted imaging application. Common imaging sensors measure the number of photons impinging over a dense grid of photodetectors in order to produce an image similar to what is perceived by the human visual system. Different applications focus on the part of the electromagnetic spectrum not visible by the human visual system, and thus require different sensing technologies to form the image. In all cases, even with the advance of ...

As biometrics gains popularity and proliferates into the daily life, there is an increased concern over the loss of privacy and potential misuse of biometric data held in central repositories. The major concerns are about i) the use of biometrics to track people, ii) non-revocability of biometrics (eg. if a fingerprint is compromised it can not be canceled or reissued), and iii) disclosure of sensitive information such as race, gender and health problems which may be revealed by biometric traits. The straightforward suggestion of keeping the biometric data in a user owned token (eg. smart cards) does not completely solve the problem, since malicious users can claim that their token is broken to avoid biometric verification altogether. Put together, these concerns brought the need for privacy preserving biometric authentication methods in the recent years. In this dissertation, we survey existing ...

The use of biometrics looks promising as it is already being applied in electronic passports, ePassports, on a global scale. Because the biometric data has to be stored as a reference template on either a central or personal storage device, its wide-spread use introduces new security and privacy risks such as (i) identity fraud, (ii) cross-matching, (iii) irrevocability and (iv) leaking sensitive medical information. Mitigating these risks is essential to obtain the acceptance from the subjects of the biometric systems and therefore facilitating the successful implementation on a large-scale basis. A solution to mitigate these risks is to use template protection techniques. The required protection properties of the stored reference template according to ISO guidelines are (i) irreversibility, (ii) renewability and (iii) unlinkability. A known template protection scheme is the helper data system (HDS). The fundamental principle of the HDS ...

The localization and tracking of sound sources using microphone arrays is a problem that, even if it has attracted attention from the signal processing research community for decades, remains open. In recent years, deep learning models have surpassed the state-of-the-art that had been established by classic signal processing techniques, but these models still struggle with handling rooms with strong reverberations or tracking multiple sources that dynamically appear and disappear, especially when we cannot apply any criteria to classify or order them. In this thesis, we follow the ideas of the Geometric Deep Learning framework to propose new models and techniques that mean an advance of the state-of-the-art in the aforementioned scenarios. As the input of our models, we use acoustic power maps computed using the SRP-PHAT algorithm, a classic signal processing technique that allows us to estimate the acoustic energy ...

Copy Number Alterations (CNA)s are hallmarks of cancer, which are gains or losses in copies of Deoxyribonucleic Acid (DNA) sections. Nowadays, CNAs are routinely measured by different techniques for diagnostic and prognostic purposes. The array-Comparative Genomic Hybridization (aCGH), Array-Single Nucleotide Polymorphism (aSNP) and Next Generation Sequencing (NGS) are examples of technologies that enable cost-efficient high resolution detection of CNAs. Intensive noise as well as technical and biological biases inherent to modern technologies of CNAs probing often cause inconsistency between the estimates provided by different methods. Efficient and accurate detection of the breakpoint positions in heterogeneous cancer samples measured under such conditions is a challenging practical and methodological problem. Despite the necessity of accurate CNA estimates, there is no much information regarding the estimation errors. Based on studies of the confidence limits for noisy stepwise signals, an efficient algorithm has been ...

Single-channel source separation for radio-frequency (RF) systems is a challenging problem relevant to key applications, including wireless communications, radar, and spectrum monitoring. This thesis addresses the challenge by focusing on data-driven approaches for source separation, leveraging datasets of sample realizations when source models are not explicitly provided. To this end, deep learning techniques are employed as function approximations for source separation, with models trained using available data. Two problem abstractions are studied as benchmarks for our proposed deep-learning approaches. Through a simplified problem involving Orthogonal Frequency Division Multiplexing (OFDM), we reveal the limitations of existing deep learning solutions and suggest modifications that account for the signal modality for improved performance. Further, we study the impact of time shifts on the formulation of an optimal estimator for cyclostationary Gaussian time series, serving as a performance lower bound for evaluating data-driven methods. ...