Bernd Kleinjohann

Real-Time Facial Expression Recognition Using a Fuzzy Emotion Model

This paper presents the fuzzy video based emotion recognition system VISBER, that allows to analyze facial expressions in video sequences. In order to process images in real-time a tracking mechanism is used for face localization. The fuzzy classification itself analyzes the deformation of a face separately in each image. In contrast to most existing approaches, also blended emotions with varying intensities as proposed by psychologists can be handled. For this purpose we propose a fuzzy emotion model which is generally applicable for also for other emotion recognition solutions. Furthermore, VISBER supports the automatic adaptation to the characteristics of individual human faces by a short training phase that can be done before the emotion recognition starts.

Marker-less vision based tracking for mobile augmented reality

In this paper an object recognition and tracking approach for the mobile, marker-less and PDA-based augmented reality system AR-PDA is described. For object recognition and localization 2D features are extracted from images and compared with a priori known 3D models. The system consists of a 2D graph matching, 3D hypothesis generation and validation and an additional texture based validation step.

Towards a complete design method for embedded systems using predicate/transition-nets

In this paper, we present a new approach to embedded system design based on modeling discrete and also continuous system parts with high level Petri—Nets. Our investigations concentrate on a complete design flow, analysis on high level Petri—Nets and their meaning for hardware/software partitioning of real-time embedded systems. The concepts for hybrid modeling of discrete and continuous systems are applied in an example in the domain of mechatronic systems.

Fuzzy emotion recognition in natural speech dialogue

This paper describes the realization of a natural speech dialogue for the robot head MEXI with focus on its emotion recognition. Specific for MEXI is that it can recognize emotions from natural speech and also produce natural speech output with emotional prosody. For recognizing emotions from the prosody of natural speech we use a fuzzy rule based approach. Since MEXI often communicates with well known persons but also with unknown humans, for instance at exhibitions, we realized a speaker-dependent mode as well as a speaker-independent mode in the prosody based emotion recognition. A key point of our approach is that it automatically selects the most significant features from a set of twenty analyzed features based on a training data base of speech samples. This is important according to our results, since the set of significant features differs considerably between the distinguished emotions. With our approach we reached average recognition rates of 84% in speaker-dependent mode and 60% in speaker-independent mode.

The SEA Language for System Engineering and Animation

This paper describes the hierarchical, graphical SEA Language. The SEA Language relies on extended Predicate Transition Nets that unambiguously define the semantics of graphical system specifications. These nets are also used as a basis for simulating/animating system specifications. The SEA Language allows to easily incorporate several user defined or standardized graphical symbols and their behaviour. Via this approach a unified semantic basis for different graphical specification formalisms/techniques can be provided. These techniques may be application independent like data flow graphs, statecharts or block diagrams for differential equations or application dependent like logical gates for hardware systems. Hence, engineers can specify system (parts) using the graphical symbols they are used to. Due to the underlying common semantics defined by extended Predicate Transition Nets, a heterogeneous system can be specified and simulated as a whole at very early stages of design before some system components are already constructed. This approach and its benefits will be explained using the well known elevator system as an example of a heterogeneous system.

Prosody based emotion recognition for MEXI

This paper describes the emotion recognition from natural speech as realized for the robot head MEXI. We use a fuzzy logic approach for analysis of prosody in natural speech. Since MEXI often communicates with well known persons but also with unknown humans, for instance at exhibitions, we realized a speaker dependent mode as well as a speaker independent mode in our prosody based emotion recognition. A key point of our approach is that it automatically selects the most significant features from a set of twenty analyzed features based on a training database of speech samples. This is important according to our results, since the set of significant features differs considerably between the distinguished emotions. With our approach we reach average recognition rates of 84% in speaker dependent mode and 60% in speaker independent mode.

Low Latency Color Segmentation on Embedded Real-Time Systems

This paper presents a color segmentation algorithm for embedded real-time systems with a special focus on latencies. The algorithm is part of a Hardware-Software-System that realizes fast reactions on visual stimuli in highly dynamic environments. There is furthermore the constraint to use low-cost hardware to build the system. Our system is implemented on a RoboCup middle size league prototype robot.

Feature based Face Localization and Recognition on Mobile Devices

Due to increasing miniaturization and decreasing prizes of cameras more and more mobile devices like PDAs or smartphones are equipped with a camera. Due to this fact, mobile face recognition will gain popularity in identifying persons e.g. in order to prevent unauthorized use or access to data and equipment. In this paper, the feature based face localization and recognition system FaceScry is presented. In spite of the limited resources available on mobile devices, FaceScry is able to localize an arbitrary number of faces with different sizes in images taken under varying illumination conditions in real-time. Also face recognition is size invariant due to the selected set of features, which mainly consists of angles and cross ratios. Since it stores reference face data for recognition as feature vectors and not as huge image data, FaceScry also allows for keeping a reasonable personal face data base for recognizing a set of persons on the smartphone

CV-SDF - a model for real-time computer vision applications

This paper presents a model for real-time computer vision applications based on the synchronous dataflow (SDF) methodology. To accomplish the needs of computer vision applications (mainly access to pixel neighborhood and access to previous video frames) a new buffer concept called Structured Buffers replaces the FIFO buffers used in the SDF model. The model minimizes the systems latency and memory consumption and allows an execution time analysis which is an essential prerequisite for real-time applications. Finally a line-based edge vectorization is presented as an example of the usage of the presented model.

Hybrid planning and hierarchical optimization of mechatronic systems

In the presented work, a hybrid planner is used to adjust the active suspension system of a novel railway vehicle to upcoming situations. The hybrid planner uses the results from a model based multi objective optimization as a basis for discrete planning in continuous domains. The optimization works on a hierarchically organized set of mechatronic function modules which are represented as a hierarchical model. A centralistic as well as a distributed optimization mode are presented along with a resulting Pareto set.