Automatic image annotation is the process of automatically producing words to de- scribe the content for a given image. It provides us with a natural means of semantic indexing for content based image retrieval. In this thesis, two novel automatic image annotation systems targeting di&amp / #64256 / erent types of annotated data are proposed. The &amp / #64257 / rst system, called Supervised Ensemble of Visual Descriptors (SEVD), is trained on a set of annotated images with prede&amp / #64257 / ned class labels. Then, the system auto- matically annotates an unknown sample depending on the classi&amp / #64257 / cation results. The second system, called Unsupervised Ensemble of Visual Descriptors (UEVD), assumes no class labels. Therefore, the annotation of an unknown sample is accomplished by unsupervised learning based on the visual similarity of images. The available auto- matic annotation systems in the literature mostly use a single set of features to train a single learning architecture. On the other hand, the proposed annotation systems utilize a novel model of image representation in which an image is represented with a variety of feature sets, spanning an almost complete visual information comprising color, shape, and texture characteristics. In both systems, a separate learning entity is trained for each feature set and these entities are gathered under an ensemble learning approach. Empirical results show that both SEVD and UEVD outperform some of the state-of-the-art automatic image annotation systems in equivalent experimental setups.

In pattern recognition, &ldquo / bias-variance&rdquo / trade-off is a challenging issue that the scientists has been working to get better generalization performances over the last decades. Among many learning methods, two-layered homogeneous stacked generalization has been reported to be successful in the literature, in different problem domains such as object recognition and image annotation. The aim of this work is two-folded. First, the problems of stacked generalization are attacked by a proposed novel architecture. Then, a set of success criteria for stacked generalization is studied. A serious drawback of stacked generalization architecture is the sensitivity to curse of dimensionality problem. In order to solve this problem, a new architecture named &ldquo / unanimous decision&rdquo / is designed. The performance of this architecture is shown to be comparably similar to two layered homogeneous stacked generalization architecture in low number of classes while it performs better than stacked generalization architecture in higher number of classes. Additionally, a new success criterion for two layered homogeneous stacked generalization architecture is proposed based on the individual properties of the used descriptors and it is verified in synthetic datasets.

The aim of this thesis is the development of an infrastructure which is used for semantic retrieval of multimedia contents. Motivated by the needs of semantic search and retrieval of multimedia contents, operating directly on the MPEG-7 based annotations can be thought as a reasonable way for meeting these needs as MPEG-7 is a common standard providing a wide multimedia content description schema. However, it is clear that the MPEG-7 formalism is deficient about the semantics and reasoning support. From this perspective, additionally, we need to represent MPEG-7 descriptions in a new formalism in order to fill the gap about semantics and reasoning. Then, the semantic web and multimedia technologies intercept at this point of multimedia semantics. In this thesis, OWL Web Ontology Language, which is based on description logic has been utilized to model a connection between the ontology semantics and video metadata. Modeling the domain of the videos using ontologies and the MPEG-7 descriptions, and reasoning on the videos by the help of the logical formalism of these ontologies are the main objectives of the thesis.

Automatic image annotation is the process of assigning keywords to digital images depending on the content information. In one sense, it is a mapping from the visual content information to the semantic context information. In this thesis, we propose a novel approach for automatic image annotation problem, where the annotation is formulated as a multivariate mapping from a set of independent descriptor spaces, representing a whole image, to a set of words, representing class labels. For this purpose, a hierarchical annotation architecture, named as HANOLISTIC (Hierarchical Image Annotation System Using Holistic Approach), is dened with two layers. At the rst layer, called level-0 annotator, each annotator is fed by a set of distinct descriptor, extracted from the whole image. This enables us to represent the image at each annotator by a dierent visual property of a descriptor. Since, we use the whole image, the problematic segmentation process is avoided. Training of each annotator is accomplished by a supervised learning paradigm, where each word is represented by a class label. Note that, this approach is slightly dierent then the classical training approaches, where each data has a unique label. In the proposed system, since each image has one or more annotating words, we assume that an image belongs to more than one class. The output of the level-0 annotators indicate the membership values of the words in the vocabulary, to belong an image. These membership values from each annotator is, then, aggregated at the second layer by using various rules, to obtain meta-layer annotator. The rules, employed in this study, involves summation and/or weighted summation of the output of layer-0 annotators. Finally, a set of words from the vocabulary is selected based on the ranking of the output of meta-layer. The hierarchical annotation system proposed in this thesis outperforms state of the art annotation systems based on segmental and holistic approaches. The proposed system is examined in-depth and compared to the other systems in the literature by means of using several performance criteria.

In this thesis, a system, called Ontology-Based Spatio-Temporal Video Management System (OntoVMS) is developed in order to supply a framework which can be used for semantic data modeling and querying in video files. OntoVMS supports semantic data modeling which can be divided into concept modeling, spatio-temporal relation and trajectory data modeling. The system uses Rhizomik MPEG-7 Ontology as the core ontology. Moreover ontology expression capability is extended by automatically attaching domain ontologies. OntoVMS supports querying of all spatial relations such as directional relations (north, south ...), mixed directional relations (northeast, southwest ...), distance relations (near, far), positional relations (above, below ...) and topological relations (inside, touch ...) / temporal relations such as starts, equal, precedes / and trajectories of objects of interest. In order to enhance querying capability, compound queries are added to the framework so that the user can combine simple queries by using &quot / (&quot / , &quot / )&quot / , &quot / AND&quot / and &quot / OR&quot / operators. Finally, the use of the system is demonstrated with a semi-automatic face annotation tool.

In this thesis a natural language query interface is developed for semantic and spatio-temporal querying of MPEG-7 based domain ontologies. The underlying ontology is created by attaching domain ontologies to the core Rhizomik MPEG-7 ontology. The user can pose concept, complex concept (objects connected with an &ldquo / AND&rdquo / or &ldquo / OR&rdquo / connector), spatial (left, right . . . ), temporal (before, after, at least 10 minutes before, 5 minutes after . . . ), object trajectory and directional trajectory (east, west, southeast . . . , left, right, upwards . . . ) queries to the system. Furthermore, the system handles the negative meaning in the user input. When the user enters a natural language (NL) input, it is parsed with the link parser. According to query type, the objects, attributes, spatial relation, temporal relation, trajectory relation, time filter and time information are extracted from the parser output by using predefined rules. After the information extraction, SPARQL queries are generated, and executed against the ontology by using an RDF API. Results are retrieved and they are used to calculate spatial, temporal, and trajectory relations between objects. The results satisfying the required relations are displayed in a tabular format and user can navigate through the multimedia content.

Syntheses of biodegradable PLLA homopolymers and PLLA-mPEG diblock copolymers for the formation of thermo-sensitive gels were performed. The sol-gel transition temperature of the matrix was adjusted by altering the length of each PEG and LA component. PLLA-mPEG biocompatible copolymers, having appropriate length of each block component, showed sols at around 42-45 oC, suitable for the injection, then a gel with subsequent rapid cooling to body temperature. Topotecan and camptothecin were selected as anti-cancer drugs. Both drugs can easily hydrolyze at physiological conditions (pH=7.4). This causes the loss of its activity, and it turns into inactive toxic carboxylate form from active lactone state. To keep those anti cancer drugs in the lactone form, they were efficiently loaded into PLLA-mPEG gels in different loading ratios. Their stability in gel was fully examined with HPLC and fluorescence spectroscopy. It was found that both drugs were highly stable and in active form in the prepared gels (&gt / 95 %). Then, both release profile of drugs at different loading ratios showed prolonged release over weeks. Mechanistic studies on the stabilization of CPT anti cancer drug with PLLA-mPEG gels were carried out using ATR-FTIR, confocal and optic microscopes. The cytotoxic efficacy of TPT in the PLLA-mPEG platform (PLLA-mPEG-TPT) was evaluated on LLC-1 and 4T1 cancer cell lines by MTT assay. In vivo, the administration of PLLA-mPEG-TPT to the mice bearing breast tumours established with 4T1 cells resulted in a significant reduction in tumour size and better survival percentages. Additionally, stabilization of CPT and TPT with gels may find another application on solid tumors in brain via local injection. A novel conducting polymer was successfully synthesized via electropolymerization of 1-(1H-pyrrol-1-yl)-2,5-di(thiophen-2-yl)-1H-pyrrole. The electrochemical and electro-optical properties of the corresponding polymer, which was the first example of polymer containing 1,1&rsquo / -bipyrrole units, were elaborated using electroanalytical and spectroscopic techniques. Cyclic voltammograms and electrooptical studies showed that the polymer has a stable and well-defined reversible redox process as well as electrochromic behavior. The processable polymer film also possessed a yellowish orange light emitter property.

Semantic annotation of video content is necessary for indexing and retrieval tasks of video management systems. Currently, it is not possible to extract all high-level semantic information from video data automatically. Video annotation tools assist users to generate annotations to represent video data. Generated annotations can also be used for testing and evaluation of content based retrieval systems. In this study, a semi-automatic semantic video annotation tool is presented. Generated annotations are in MPEG-7 metadata format to ensure interoperability. With the help of image processing and pattern recognition solutions, annotation process is partly automated and annotation time is reduced. Annotations can be done for spatio-temporal decompositions of video data. Extraction of low-level visual descriptions are included to obtain complete descriptions.

Continuous progress in multimedia research in recent years have led to proliferation of their applications in everyday life. The ever-growing demand in high performance multimedia applications creates the need for new and efficient storage and retrieval techniques. There exist numerous studies in the literature attempting to describe the content of these multimedia documents. Moving Picture Experts Group&rsquo / s XML based MPEG-7 is one of these studies that makes it possible to describe multimedia content in terms of both low and high level properties. MPEG-7 DDL allows defining new types using already defined types. Within the past ten years, it became a widely accepted standard in multimedia applications. In this thesis, an XML database application is developed to manage MPEG-7 descriptions, utilizing eXist XML DB as the database management system and a JAVA application as the frontend. MPEG-7 Description Schemes are extended by introducing fuzzy semantic types, such as FuzzyObject and FuzzyEvent, using the MPEG-7 DDL. From this point of view, the application of fuzzy XML methods in MPEG-7 standard is a novel approach.

No description available.