Growth in storage capacity has led to large digital video repositories and complicated the discovery of specific information without the laborious manual annotation of data. The research focuses on creating a retrieval system that is ultimately independent of manual work. To retrieve relevant content, the semantic gap between the searcher's information need and the content data has to be overcome using content-based technology. Semantic gap constitutes of two distinct elements: the ambiguity of the true information need and the equivocalness of digital video data. The research problem of this thesis is: what computational content-based models for retrieval increase the effectiveness of the semantic retrieval of digital video? The hypothesis is that semantic search performance can be improved using pattern recognition, data abstraction and clustering techniques jointly with human interaction through manually created queries and visual browsing. The results of this ...

The main research area of this Ph.D. thesis is video sequence processing and analysis for description and indexing of visual content. Its objective is to contribute in the development of a computational system with the capabilities of object-based segmentation of audiovisual material, automatic content description, summarization for preview and browsing, as well as content-based retrieval. The thesis consists of four parts. The first introduces video sequence analysis, segmentation and object extraction based on color, motion, and depth field. A fusion technique is proposed that combines individual cue segmentations and allows for reliable identification of semantic objects. The second part refers to automatic description and annotation of the visual content by means of feature vectors, summarization, implemented by optimal selection of a limited set of key frames and shots, and content-based search and retrieval. In the third part, the problem of ...

Advances in compression techniques, decreasing cost of storage, and high-speed transmission have facilitated the way videos are created, stored and distributed. As a consequence, videos are now being used in many applications areas. The increase in the amount of video data deployed and used in today's applications reveals not only the importance as multimedia data type, but also led to the requirement of efficient management of video data. This management paved the way for new research areas, such as indexing and retrieval of video with respect to their spatio-temporal, visual and semantic contents. This thesis presents work towards a unified framework for semi-automated video indexing and interactive retrieval. To create an efficient index, a set of representative key frames are selected which capture and encapsulate the entire video content. This is achieved by, firstly, segmenting the video into its constituent ...

Accounting for uncertainty in three-dimensional (3D) shapes is important in a large number of scientific and engineering areas, such as biometrics, biomedical imaging, and data mining. It is well known that 3D polar shaped objects can be represented by Fourier descriptors such as spherical harmonics and double Fourier series. However, the statistics of these spectral shape models have not been widely explored. This thesis studies several areas involved in 3D shape modeling, including random field models for statistical shape modeling, optimal shape filtering, parametric active contours for object segmentation and surface reconstruction. It also investigates multi-modal image registration with respect to tumor activity quantification. Spherical harmonic expansions over the unit sphere not only provide a low dimensional polarimetric parameterization of stochastic shape, but also correspond to the Karhunen-Lo´eve (K-L) expansion of any isotropic random field on the unit sphere. Spherical ...

Visual information, in the form of digital images and videos, has become so omnipresent in computer databases and repositories, that it can no longer be considered a “second class citizen”, eclipsed by textual information. In that scenario, image classification has become a critical task. In particular, the pursuit of automatic identification of complex semantical concepts represented in images, such as scenes or objects, has motivated researchers in areas as diverse as Information Retrieval, Computer Vision, Image Processing and Artificial Intelligence. Nevertheless, in contrast to text documents, whose words carry semantic, images consist of pixels that have no semanticinformation by themselves, making the task very challenging. In this dissertation, we have addressed the problem of representing images based on their visual information. Our aim is content-based concept detection in images and videos, with a novel representation that enriches the Bag-of-Words model. ...

In this thesis, we examine the problem of algorithmic analysis of complex audio scenes with a special emphasis on natural audio scenes. One of the driving goals behind this work is to develop tools for monitoring the presence of animals in areas of interest based on their vocalisations. This task, which often occurs in the evaluation of nature conservation measures, leads to a number of subproblems in audio scene analysis. In order to develop and evaluate pattern recognition algorithms for animal sounds, a representative collection of such sounds is necessary. Building such a collection is beyond the scope of a single researcher and we therefore use data from the Animal Sound Archive of the Humboldt University of Berlin. Although a large portion of well annotated recordings from this archive has been available in digital form, little infrastructure for searching and ...

Content Based Image Retrieval (CBIR) has gained a lot of interest over the last two decades. The need to search and retrieve images from databases, based on information (“features”) extracted from the image itself, is becoming increasingly important. CBIR can be useful for handheld image recognition devices in which the image to be recognized is acquired with a camera, and thus there is no additional metadata associated to it. However, most CBIR systems require large computations, preventing their use in handheld devices. In this PhD work, we have developed low-complexity algorithms for content based image retrieval in handheld devices for camera acquired images. Two novel algorithms, ‘Color Density Circular Crop’ (CDCC) and ‘DCT-Phase Match’ (DCTPM), to perform image retrieval along with a two-stage image retrieval algorithm that combines CDCC and DCTPM, to achieve the low complexity required in handheld devices ...

Shape description is a crucial step in many computer vision applications. This thesis is an attempt to introduce various representations of two and three dimensional shape information. These representations are aimed to be in homogeneous parametric forms in 2D or 3D space, such that subspace-based feature extraction techniques are applicable on them. We tackle three di erent applications: (i) Person recognition with hand biometry, (ii) Person recognition with three-dimensional face biometry, (iii) Indexing and retrieval of generic three-dimensional models. For each application, we propose various combinations of shape representation schemes and subspace-based feature extraction methods. We consider subspaces with fixed bases such as cosines, complex exponentials and tailored subspaces such as Principal Component Analysis, Independent Component Analysis and Nonnegative Matrix Factorization. Most of the descriptors we propose are dependent on the pose of the object. In this thesis we give ...

Retrieval of images that lack a (suitable) annotations cannot be achieved through (traditional) Information Retrieval (IR) techniques. Access through such collections can be achieved through the application of computer vision techniques on the IR problem, which is baptized Content-Based Image Retrieval (CBIR). In contrast with most purely technological approaches, the thesis Human-Centered Content-Based Image Retrieval approaches the problem from a human/user centered perspective. Psychophysical experiments were conducted in which people were asked to categorize colors. The data gathered from these experiments was fed to a Fast Exact Euclidean Distance (FEED) transform (Schouten & Van den Broek, 2004), which enabled the segmentation of color space based on human perception (Van den Broek et al., 2008). This unique color space segementation was exploited for texture analysis and image segmentation, and subsequently for full-featured CBIR. In addition, a unique CBIR-benchmark was developed (Van ...

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 ...

Music was the first mass-market industry to be completely restructured by digital technology, and today we can have access to thousands of tracks stored locally on our smartphone and millions of tracks through cloud-based music services. Given the vast quantity of music at our fingertips, we now require novel ways of describing, indexing, searching and interacting with musical content. In this thesis we focus on a technology that opens the door to a wide range of such applications: automatically estimating the pitch sequence of the melody directly from the audio signal of a polyphonic music recording, also referred to as melody extraction. Whilst identifying the pitch of the melody is something human listeners can do quite well, doing this automatically is highly challenging. We present a novel method for melody extraction based on the tracking and characterisation of the pitch ...

The present doctoral thesis aims towards the development of new long-term, multi-channel, audio-visual processing techniques for the analysis of bioacoustics phenomena. The effort is focused on the study of the physiology of the gastrointestinal system, aiming at the support of medical research for the discovery of gastrointestinal motility patterns and the diagnosis of functional disorders. The term "processing" in this case is quite broad, incorporating the procedures of signal processing, content description, manipulation and analysis, that are applied to all the recorded bioacoustics signals, the auxiliary audio-visual surveillance information (for the monitoring of experiments and the subjects' status), and the extracted audio-video sequences describing the abdominal sound-field alterations. The thesis outline is as follows. The main objective of the thesis, which is the technological support of medical research, is presented in the first chapter. A quick problem definition is initially ...

Many scientific and engineering problems require us to process measurements and data in order to extract information. Since we base decisions on information, it is important to design accurate and efficient processing algorithms. This is often done by modeling the signal of interest and the noise in the problem. One type of modeling is Compressed Sensing, where the signal has a sparse or low-rank representation. In this thesis we study different approaches to designing algorithms for sparse and low-rank problems. Greedy methods are fast methods for sparse problems which iteratively detects and estimates the non-zero components. By modeling the detection problem as an array processing problem and a Bayesian filtering problem, we improve the detection accuracy. Bayesian methods approximate the sparsity by probability distributions which are iteratively modified. We show one approach to making the Bayesian method the Relevance Vector ...

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 ...

An adaptive edge-enhanced correlation based robust and real-time visual tracking framework, and two machine vision systems based on the framework are proposed. The visual tracking algorithm can track any object of interest in a video acquired from a stationary or moving camera. It can handle the real-world problems, such as noise, clutter, occlusion, uneven illumination, varying appearance, orientation, scale, and velocity of the maneuvering object, and object fading and obscuration in low contrast video at various zoom levels. The proposed machine vision systems are an active camera tracking system and a vision based system for a UGV (unmanned ground vehicle) to handle a road intersection. The core of the proposed visual tracking framework is an Edge Enhanced Back-propagation neural-network Controlled Fast Normalized Correlation (EE-BCFNC), which makes the object localization stage efficient and robust to noise, object fading, obscuration, and uneven ...