Refine
Year of publication
- 2013 (87) (remove)
Document Type
- Bachelor Thesis (31)
- Doctoral Thesis (23)
- Part of Periodical (13)
- Master's Thesis (12)
- Diploma Thesis (3)
- Study Thesis (3)
- Conference Proceedings (1)
- Habilitation (1)
Has Fulltext
- yes (87) (remove)
Keywords
- Pflanzenschutzmittel (3)
- Information Retrieval (2)
- Routing (2)
- Vorlesungsverzeichnis (2)
- ABox (1)
- Abduktion <Logik> (1)
- Aggregation (1)
- Agrochemikalien (1)
- Arbeitsbelastungen (1)
- Arbeitszufriedenheit (1)
- Bach (1)
- Bewertung (1)
- Biogeografie (1)
- Biomonitoring (1)
- Boden (1)
- Bodenchemie (1)
- Bodenökologie (1)
- Burn-out-Syndrom (1)
- Burnout (1)
- C++ (1)
- CIDR (1)
- Calculus (1)
- Cations (1)
- Chironomus riparius (1)
- Computational Toxicology (1)
- Compute Shader (1)
- Computergraphik (1)
- Computermodell (1)
- Computervisualistik (1)
- Cooperative Learning; Teaching Methods (1)
- Crayfish (1)
- Crayfish plague (1)
- Deduktion (1)
- Defi-Now! (1)
- Defibrillator (1)
- Differentia Scanning Calorimetry (1)
- Differential scanning calorimetry (1)
- Digitale Bibliothek (1)
- Distance Vector Routing (1)
- Distanz Vektor Routing (1)
- Distribution <Linguistik> (1)
- E-KRHyper (1)
- E-KRHyper theorem prover (1)
- Edelkrebs (1)
- Elektronische Bibliothek (1)
- Emergenz (1)
- Endokrine Regulation (1)
- Englisch (1)
- Enterprise 2.0 (1)
- Entwicklung (1)
- Environmental Risk Assessment (1)
- Erste Hilfe (1)
- Fabric Simulation (1)
- First aid (1)
- Fledermäuse (1)
- Flugbegleiter (1)
- Fluss (1)
- Fragebeantwortung (1)
- GIRT (1)
- Game Design (1)
- Gefrierpunktserniedrigung (1)
- Genetic diversity (1)
- Genetische Variabilität (1)
- Gewässer (1)
- Glasumwandlung (1)
- Glasübergang (1)
- Graphik (1)
- Grundwasser (1)
- Grundwasserfauna (1)
- Grundwasserökologie (1)
- Hyaluronan (1)
- Hyaluronsäure (1)
- Hydratation (1)
- Hydration (1)
- Individualisierung von Lernwegen (1)
- Individualized Learning (1)
- Individuelle Förderung (1)
- Informatik (1)
- Information (1)
- Information Flow Ontology (1)
- Information Visualization (1)
- Informationsverarbeitung (1)
- Informationsverlinkung (1)
- Informationsvisualisierung (1)
- Informetrie (1)
- Integrated Model (1)
- Interactive Visualizations (1)
- Interaktive Visualisierungen (1)
- Internetregulierung (1)
- Kation-Brücken (1)
- Kationen (1)
- Kognitive Linguistik (1)
- Kontiguität (1)
- Konturfindung (1)
- Konzept (1)
- Kookkurrenz (1)
- Kooperatives Lernen (1)
- Krebspest (1)
- Landwirtschaft (1)
- Lendenwirbelsäule (1)
- Limnologie (1)
- Limology (1)
- Line Space (1)
- Linespace (1)
- Linked Data Modeling (1)
- Linking of Information (1)
- Literaturrecherche (1)
- Logischer Schluss (1)
- Lookup-Algorithmen (1)
- MKS-Simulation (1)
- Magnetis (1)
- Mesofauna (1)
- Methode (1)
- Mikroorganismus (1)
- Mitarbeiterzufriedenheit (1)
- Mixture Toxicity (1)
- Museums visitors (1)
- Museumsbesucher (1)
- N-Body Simulation (1)
- N-Körper Simulation (1)
- NMR-Spektroskopie (1)
- Non-freezing water (1)
- Nuclear Magnetic R (1)
- OWL (1)
- Online-Kommunikation (1)
- Ontologie (1)
- OpenGL (1)
- OpenGL Shading Language (1)
- Operationsplanung (1)
- Organische Bodensubstanz (1)
- Pestizid (1)
- Pestizide (1)
- Phylogeographie (1)
- Plasticization; Glass transition (1)
- Plastifizieren (1)
- Plastifizierung (1)
- Politik (1)
- Polysaccharide (1)
- Polysaccharides (1)
- Power Law (1)
- Predictive Model (1)
- Programmierung (1)
- Prädikatenlogik (1)
- Präposition (1)
- RDF (1)
- Rechnernetz (1)
- Risikoabschätzung (1)
- Risikoanalyse (1)
- Risikomanagement (1)
- Route Aggregation (1)
- Routen-Aggregation (1)
- Router (1)
- Routing- und Forwarding Tabellen (1)
- Schlussfolgern (1)
- Schreibprozess (1)
- Semantic Web (1)
- Simulation (1)
- Situationales Interesse (1)
- Smartphone Applikation (1)
- Softwareergonomie (1)
- Spiel (1)
- Steuerung (1)
- Stoffsimulation (1)
- Streams (1)
- Stress (1)
- Stygofauna (1)
- Stygoregion (1)
- Suchmaschine (1)
- Supernetting (1)
- Support System (1)
- Säugetiere (1)
- Süßwasserhaushalt (1)
- TBox (1)
- Text Analysis (1)
- Text Mining (1)
- Textlinguistik (1)
- Theorem prover (1)
- Theorembeweiser (1)
- Torf (1)
- Umweltchemikalie (1)
- Umwelttoxikologie (1)
- Umweltwissenschaften (1)
- Unterrichtsmethoden (1)
- Usability (1)
- Videospiel (1)
- Visualisierung (1)
- Vocabulary Mapping (1)
- Wachstumsregler (1)
- Web 2.0 (1)
- Web Analytics (1)
- Wikipedia (1)
- Wirbellose (1)
- Wissensbasis (1)
- World Wide Web (1)
- Zuckmücken (1)
- agent-based simulation (1)
- agriculture (1)
- aquatic ecotoxicology (1)
- automated theorem prover (1)
- bats (1)
- biogeography (1)
- biomonitoring (1)
- burnout (1)
- by-stander effect (1)
- cation bridges (1)
- co-occurrence (1)
- cognitive linguistic approach (1)
- concept (1)
- conflicting information (1)
- contiguity (1)
- development (1)
- digital library (1)
- ecological risk management (1)
- ecosystem functions (1)
- emergence (1)
- endocrine disrupting chemicals (1)
- endokrine Regulation (1)
- english prepositions (1)
- flight attendant (1)
- freshwater ecosystem (1)
- game (1)
- governance (1)
- groundwater ecology (1)
- groundwater fauna (1)
- iSearch (1)
- information flow regulation (1)
- information processing (1)
- interaktiv (1)
- invertebrates (1)
- knowledge base (1)
- kollaboratives Schreiben (1)
- konfligierende Information (1)
- kooperatives Schreiben (1)
- landscape (1)
- life cycle test (1)
- mammals (1)
- metasearch engine (1)
- microorganisms (1)
- minimum self-contained graphs (1)
- modelling (1)
- nicht gefrierbares Wasser (1)
- norm (1)
- ontology (1)
- peat (1)
- pesticide (1)
- pesticides (1)
- plant protection products (1)
- policy modelling (1)
- probabilistic (1)
- question answering (1)
- risk assessment (1)
- search engine (1)
- situational interest (1)
- smartphone app (1)
- soil (1)
- soil organic matter (1)
- stygofauna (1)
- teaching (1)
- usability study (1)
- video game (1)
- workload (1)
- Ökologie (1)
- Ökosystem (1)
- Ökotoxologie (1)
Institute
- Fachbereich 4 (50)
- Fachbereich 7 (9)
- Zentrale Einrichtungen (8)
- Fachbereich 8 (4)
- Institut für Computervisualistik (4)
- Institut für Informatik (4)
- Institute for Web Science and Technologies (2)
- Fachbereich 5 (1)
- Institut für Germanistik (1)
- Institut für Integrierte Naturwissenschaften, Abt. Biologie (1)
English prepositions take only a small proportion of the language but play a substantial role. Although prepositions are of course also frequently used in English textbooks for secondary school, students fail to incidentally acquire them and often show low achievements in using prepositions correctly. The strategy commonly employed by language instructors is teaching the multiple senses of prepositions by rote which fails to help the students to draw links between the different meanings in usage. New findings in Cognitive Linguistics (CL) suggest a different approach to teaching prepositions and thus might have a strong impact on the methodologies of foreign language teaching and learning on the aspects of meaningful learning. Based on the Theory of Domains (Langacker, 1987), the notions of image schemas (Johnson, 1987) as well as the Conceptual Metaphor Theory (Lakoff & Johnson, 1980), the present study developed a CL-inspired approach to teaching prepositions, which was compared to the traditional teaching method by an empirical study conducted in a German school setting. Referring to the participants from the higher track and the medium track, who are at different proficiency levels, the results indicate that the CL-inspired teaching approach improved students" performance significantly more than the traditional approach in all the cases for the higher track and in some cases for the medium track. Thus, these findings open up a new perspective of the CL-inspired meaningful learning approach on language teaching. In addition, the CL-inspired approach demonstrates the unification of the integrated model of text and picture comprehension (the ITPC model) in integrating the new knowledge with related prior knowledge in the cognitive structure. According to the learning procedure of the ITPC model, the image schema as visual image is first perceived through the sensory register, then is processed in the working memory by conceptual metaphor, and finally it is integrated with cognitive schemata in the long term memory. Moreover, deep-seated factors, such as transfer of mother tongue, the difficulty of teaching materials, and the influence of prior knowledge, have strong effects on the acquisition of English prepositions.
In dieser Arbeit wurde der Einfluss von nicht wässrigen Mahlflüssigkeiten auf Metall-Keramik-Pulvermischungen im Nassmahlprozess untersucht. Es wurden Al- und Cr-Al₂O₃-Pulvermischungen ausgewählt, um den Einfluss der Mahlflüssigkeiten auf die Mahlung von Metall-Keramik-Pulvermischungen mit einer duktilen (Aluminium) und einer spröden (Chrom) Metallkomponente zu untersuchen.
Assessment of bat activity in agricultural environments and the evaluation of the risk of pesticides
(2013)
Although agriculture dominates with around 50% area much of Europe- landscape, there is virtually no information on how bats use this farmed environment for foraging. Consequently, little is known about effective conservation measures to compensate potential negative effects of agrarian management practice on the food availability for bats in this habitat. Moreover, there are currently no specific regulatory requirements to include bats in European Union risk assessments for the registration of pesticides since no information about pesticide exposure on this mammal group is available. To evaluate the potential pesticide exposure of bats via ingestion of contaminated insects, information about bat presence and activity in agricultural habitats is required. In order to examine bat activity on a landscape scale it was necessary to establish a suitable survey method. Contrary to capture methods, telemetry, and direct observations, acoustic surveys of bat activity are a logistically feasible and cost-effective way of obtaining bat activity data. However, concerns regarding the methodological designs of many acoustic surveys are expressed in the scientific literature. The reasons are the failing of addressing temporal and spatial variation in bat activity patterns and the limitations of the suitability of the used acoustic detector systems. By comparing different methods and detector systems it was found that the set up of several stationary calibrated detector systems which automatically trigger the ultrasonic recording has the highest potential to produce reliable, unbiased and comparable data sets on the relative activity of bats.
By using the proposed survey method, bat diversity and activity was recorded in different crops and semi-natural habitats in southern Rhineland-Palatinate. Simultaneously, the availability of aerial prey insects was studied by using light and sticky traps. In more than 500 sampling nights about 110,000 call sequences were acoustically recorded and almost 120,000 nocturnal insects were sampled. A total of 14 bat species were recorded, among them the locally rare and critically endangered northern bat (Eptesicus nilssonii) and the barbastelle (Barbastella barbastellum), all of them also occurring over agricultural fields. The agricultural landscape of southern Palatinate is dominated by vineyards, a habitat that was shown to be of low quality for most bat species because of the demonstrated low availability of small aerial insects. By surveying bat activity and food availably in a pair-wise design on several rain water retention ponds and neighbouring vineyards it was demonstrated that aquatic insect emergence in artificial wetlands can provide an important resource subsidy for bats. The creation of artificial wetlands would be a possibility to create important foraging habitats for bats and mitigate negative effects of management practice in the agricultural landscape.
In several other agricultural crops, however, high abundances of suitable prey insects and high bat activity levels, comparable or even higher than in the nearby forests and meadows known to be used as foraging habitats were demonstrated. Especially high bat activity levels were recorded over several fruit orchards and vegetable fields where insects were also present. Both crops are known for high pesticide inputs, and, therefore, a pesticide exposure through ingestion of contaminated insects can not be excluded. To follow the current risk assessment approach for birds and mammals pesticide residues were measured on bat-specific food items in an apple orchard following insecticide applications and bat activity was recorded in parallel. The highest residue values were measured on foliage-dwelling arthropods which may results in a reproductive risk for all bat species that, even to a small extent, include this prey group in their diet. The presence of bats in agricultural landscapes that form a majority of the land area in Europe but also on a global scale leads to exposure of bats by contaminated food and depletion of their food resources by pesticide use. So far conservation efforts for bats focussed on securing hibernation sites and the creation of artificial roost sites since especially the latter were thought to be limiting population growth. However the potential pesticide effects might be also crucial for the population persistence in agricultural landscapes of bats and need to be addressed adequately, especially in risk assessment procedures for the regulation of pesticides.
Agricultural pesticides, especially insecticides, are an integral part of modern farming. However, these may often leave their target ecosystems and cause adverse effects in non- target, especially freshwater ecosystems, leading to their deterioration. In this thesis, the focus will be on Insect Growth Regulators (IGRs) that can in many ways cause disruption of the endocrine system of invertebrates. Freshwater invertebrates play important ecological, economic and medical roles, and disruption of their endocrine systems may be crucial, considering the important role hormones play in the developmental and reproductive processes in organisms. Although Endocrine Disruption Chemicals (EDCs) can affect moulting, behaviour, morphology, sexual maturity, time to first brood, egg development time, brood size (fecundity), and sex determination in invertebrates, there is currently no agreement upon how to characterize and assess endocrine disruption (ED). Current traditional ecotoxicity tests for Ecological Risk Assessment (ERA) show limitations on generating data at the population level that may be relevant for the assessment of EDCs, which effects may be sublethal, latent and persist for several generations of species (transgenerational).
It is therefore the primary objective of this thesis to use a test method to investigate adverse effects of EDCs on endpoints concerning development and reproduction in freshwater invertebrates. The full life-cycle test over two generations that includes all sensitive life stages of C. riparius (a sexual reproductive organism) allows an assessment of its reproduction and should be suitable for the investigation of long-term toxicity of EDCs in freshwater invertebrates. C. riparius is appropriate for this purpose because of its short life cycle that enables the assessment of functional endpoints of the organism over several generations. Moreover, the chironomid life cycle consists of a complete metamorphosis controlled by a well-known endocrine mechanism and the endocrine system of insects has been most investigated in great detail among invertebrates. Hence, the full life-cycle test with C. riparius provides an approach to assess functional endpoints (e.g. reproduction, sex ratio) that are population-relevant as a useful amendment to the ERA of EDCs. In the laboratory, C. riparius was exposed to environmentally-relevant concentrations of the selected IGRs in either spiked water or spiked sediment scenario over two subsequent generations.
The results reported in this thesis revealed significant effects of the IGRs on the development and the reproduction of C. riparius with the second (F1) generation showing greater sensitivity. These findings indicated for the first time the suitability of multigenerational testing for various groups of EDCs and strongly suggested considering the full life-cycle of C. riparius as an appropriate test method for a better assessment of EDCs in the freshwater environment. In conclusion, this thesis helps to detect additional information that can be extrapolated at population level and, thus, might contribute to better protection of freshwater ecosystems against the risks of Endocrine Disrupting Chemicals (EDCs.) It may furthermore contribute to changes in the ERA process that are necessary for a real implementation of the new European chemical legislation, REACH (Registration, Evaluation Authorization and Restriction of Chemicals). Finally, significant interactions between temperature, chemical exposure and generation were reported for the first time and, may help predict impacts that may occur in the future, in the field, under predicted climate change scenarios.
A Kinect device has the ability to record color and depth images simultaneously. This thesis is an attempt to use the depth image to manipulate lighting information and material properties in the color image. The presented method of lighting and material manipulation needs a light simulation of the lighting conditions at the time of recording the image. It is used to transform information from a new light simulation directly back into the color image. Since the simulations are performed on a three-dimensional model, a way is searched to generate a model out of single depth image. At the same time the text will react to the problems of the depth data acquisition of the Kinect sensor. An editor is designed to make lighting and material manipulations possible. To generate a light simulation, some simple, real-time capable rendering methods and lighting modells are proposed. They are used to insert new illumination, shadows and reflections into the scene. Simple environments with well defined lighting conditions are manipulated in experiments to show boundaries and possibilities of the device and the techniques being used.
This dissertation investigates the usage of theorem provers in automated question answering (QA). QA systems attempt to compute correct answers for questions phrased in a natural language. Commonly they utilize a multitude of methods from computational linguistics and knowledge representation to process the questions and to obtain the answers from extensive knowledge bases. These methods are often syntax-based, and they cannot derive implicit knowledge. Automated theorem provers (ATP) on the other hand can compute logical derivations with millions of inference steps. By integrating a prover into a QA system this reasoning strength could be harnessed to deduce new knowledge from the facts in the knowledge base and thereby improve the QA capabilities. This involves challenges in that the contrary approaches of QA and automated reasoning must be combined: QA methods normally aim for speed and robustness to obtain useful results even from incomplete of faulty data, whereas ATP systems employ logical calculi to derive unambiguous and rigorous proofs. The latter approach is difficult to reconcile with the quantity and the quality of the knowledge bases in QA. The dissertation describes modifications to ATP systems in order to overcome these obstacles. The central example is the theorem prover E-KRHyper which was developed by the author at the Universität Koblenz-Landau. As part of the research work for this dissertation E-KRHyper was embedded into a framework of components for natural language processing, information retrieval and knowledge representation, together forming the QA system LogAnswer.
Also presented are additional extensions to the prover implementation and the underlying calculi which go beyond enhancing the reasoning strength of QA systems by giving access to external knowledge sources like web services. These allow the prover to fill gaps in the knowledge during the derivation, or to use external ontologies in other ways, for example for abductive reasoning. While the modifications and extensions detailed in the dissertation are a direct result of adapting an ATP system to QA, some of them can be useful for automated reasoning in general. Evaluation results from experiments and competition participations demonstrate the effectiveness of the methods under discussion.
Augmented Reality (AR) is getting more and more popular. To augment information into the field of vision of the user using HMDs, e.g. front shields of a car, glasses, displays of a smartphone or tablets are the main use of AR technology. It is necessary to get the position and orientation (pose) of the camera in space to augment correctly.
Nowadays, this is solved with artificial markers. These known markers are placed in the room and the system is taught to this set up. The next step is to get rid of these artificial markers. If we are calculating the pose without such markers we are talking about marker-less tracking. Instead of artificial markers we will use natural objects in the real world as reference points to calculate the pose. Thus, this approach can be used flexibly and dynamically. We are no longer dependent on artificial markers but we need much more knowledge about the scenery to find the pose. This is compensated by technical actions and/or the user himself. However, both solutions are neither comfortable nor efficient for the usage of such a system. This is why marker-less 3D tracking is still a big field of research.
This sets the starting point for the bachelor thesis. In this thesis an approach is proposed that needs only a quantity of 2D Feature from a given camera image and a quantity of 3D Feature of an object to find the initial Pose. With this approach, we got rid of the technical and user assistance. 2D and 3D Features can be detected in any way you like.
The main idea of this approach is to build six correspondences between these quantities. With those we are able to estimate the pose. Each 3D Feature is mapped with the estimated pose onto image coordinates, whereby the estimated pose can be evaluated. Each distance is measured between the mapped 3D Feature and the associated 2D Feature. Each correspondency is evaluated and the results are summed up to evaluate the whole pose. The lower this summed up value is, the better the pose. It has been shown to have a correct pose with a value around ten pixels.
Due to lots of possibilities to build six correspondences between the quantities, it is necessary to optimize the building process. For the optimization we will use a genetic algorithm.
During the test case the system worked quite reliably. The hit rate was around 90% with a runtime of approximately twelve minutes. Without optimization it can take easily some years.
The goal of this Bachelor thesis was programming an existig six-legged robot, which should be able to explore any environment and create a map of it autonomous. A laser scanner is to be integrated for cognition of this environment. To build the map and locate the robot a suitable SLAM(Simultaneous Localization and Mapping) technique will be connected to the sensor data. The map is reported to be the robots base of path planning and obstancle avoiding, what will be developed in the scope of the bachelor thesis, too. Therefore both GMapping and Hector SLAM will be implemented and tested.
An exploration algorithm is described in this bachelor thesis for exploring the robots environment. The implementation on the robot takes place in the space of ROS(Robot Operating System) framework on a "Raspberry Pi" miniature PC.
The conservation of groundwater ecosystems requires an assessment and evaluation scheme that shows the state of the ecosystem. Consequently, faunal and microbial criteria are required for groundwater monitoring, in addition to physico-chemical analyses. To proof the adequacy of the application of groundwater organisms for the biological assessment of groundwater quality, an extensive sampling collection of various groundwater systems was accomplished between 2002 and 2009 in Germany. Key aspects were the examination of the indicator potential of groundwater communities towards surface-groundwater interactions and anthropogenic impacts, as well as the analysis of stygofaunal distribution patterns, as a base and reference for a faunal assessment scheme of groundwater systems. The sampling design considered local, regional, and biogeographic conditions. To test the indicator potential of groundwater organisms on a local and regional scale, groundwater systems in Nordrhein-Westfalen (NRW) and Baden-Württemberg (BW) were examined. The faunal and microbial data from unconsolidated aquifers (Erftgebiet, NRW) show the sensitivity of groundwater organisms against land use effects, e.g. extensive agriculture. Data analyses revealed positive correlations of organic material (estimated amount of detritus, TOC) and nitrate with faunal abundance, species richness, diversity and the proportions of stygoxene species. Moreover, the bacterial abundance and diversity in the groundwater of the Erftgebiet was high compared to oligotrophic groundwater systems, indicating an effect of surface influence due to agricultural land use. The groundwater colonization in the Alb-Donau-Kreis (BW) was analyzed for regional effects (landscape, type of aquifer, hydrogeology) and local effects (comparing single wells). The results show that the fauna reflects the strength of the hydrological exchange on different spatial scales. Furthermore, the fauna reflects the interaction of regional and local conditions. Accordingly, the diversity and abundance of groundwater organisms was influenced by the high connectivity of the karst and unconsolidated alluvial aquifers, the type of land use, covering layers of soil, the age of groundwater, and the sampling depths. In general, faunal and microbial data of the Alb-Donau-Kreis are characteristic for oligotrophic, oligoalimonic groundwaters. The large scale analyses of stygofaunal distribution patterns revealed significant biogeographical differences of the communities. These community patterns of the groundwater fauna do not coincide with existing classification schemes defined for surface landscapes or freshwater systems. The largest differences between faunal surface and subsurface distribution patterns were found between the groundwater of northern and southern Germany and the foothills of the central mountain ranges - all of them regions shaped by the last ice ages.
In accordance with the faunal data assessed in groundwater, four different stygoregions were defined that are populated by distinct faunal assemblages. These are 1) the "Northern lowlands", 2) the "Central mountain ranges", 3) the "South-western mountain ranges", and 4) the "Southern mountain ranges and northern alps". The study corroborates that stygofaunal and microbial communities are an adequate tool for the qualitative assessment and monitoring of groundwater ecosystems. The best indicators to detect anthropogenic impacts on groundwater ecosystems are the faunal diversity, abundance, the proportions of stygobitic (obligate groundwater species) and stygoxene species (species not obligate for groundwater), and the bacterial abundance. The development of an ecologically based groundwater assessment and management, is crucial for the conservation of our groundwater ecosystems and thus, healthy drinking water. The defintion of "stygoregions" is an important base for the development of an assessment and reference scheme for groundwater ecosystems. The assessment of the ecological state of groundwater systems must be conducted on local scale, because the strength of the local hydrological influence determines the amount of food and oxygen as well as stygoxene animals within the aquifer, and thus shapes the local groundwater communities. Nevertheless, information of the biogeographic and regional conditions is needed as a reference for the type of species and abundances that potentially can occur in certain groundwater systems.
Autonomous systems such as robots already are part of our daily life. In contrast to these machines, humans an react appropriately to their counterparts. People can hear and interpret human speech, and interpret facial expressions of other people.
This thesis presents a system for automatic facial expression recognition with emotion mapping. The system is image-based and employs feature-based feature extraction. This thesis analyzes the common steps of an emotion recognition system and presents state-of-the-art methods. The approach presented is based on 2D features. These features are detected in the face. No neutral face is needed as reference. The system extracts two types of facial parameters. The first type consists of distances between the feature points. The second type comprises angles between lines connecting the feature points. Both types of parameters are implemented and tested. The parameters which provide the best results for expression recognition are used to compare the system with state-of-the-art approaches. A multiclass Support Vector Machine classifies the parameters.
The results are codes of Action Units of the Facial Action Coding System. These codes are mapped to a facial emotion. This thesis addresses the six basic emotions (happy, surprised, sad, fearful, angry, and disgusted) plus the neutral facial expression. The system presented is implemented in C++ and is provided with an interface to the Robot Operating System (ROS).