Volker Lohweg

Algorithms for hardware-based pattern recognition

Nonlinear spatial transforms and fuzzy pattern classification with unimodal potential functions are established in signal processing. They have proved to be excellent tools in feature extraction and classification. In this paper, we will present a hardware-accelerated image processing and classification system which is implemented on one field-programmable gate array (FPGA). Nonlinear discrete circular transforms generate a feature vector. The features are analyzed by a fuzzy classifier. This principle can be used for feature extraction, pattern recognition, and classification tasks. Implementation in radix-2 structures is possible, allowing fast calculations with a computational complexity of up to. Furthermore, the pattern separability properties of these transforms are better than those achieved with the well-known method based on the power spectrum of the Fourier Transform, or on several other transforms. Using different signal flow structures, the transforms can be adapted to different image and signal processing applications.

Banknote authentication with mobile devices

Maintaining confidence in security documents, especially banknotes, is and remains a major concern for the central banks in order to maintain the stability of the economy around the world. In this paper we describe an image processing and pattern recognition approach which is based on the Sound-of-Intaglio principle for the usage in smart devices such as smartphones. Today, in many world regions smartphones are in use. These devices become more and more computing units, equipped with resource-limited, but effective CPUs, cameras with illumination, and flexible operating systems. Hence, it is obvious to apply smartphones for banknote authentication, especially for visually impaired persons. Our approach shows that those devices are capable of processing data under the constraints of image quality and processing power. Strictly a mobile device as such is not an industrial product for harsh environments, but it is possible to use mobile devices for banknote authentication. The concept is based on a new strategy for constructing adaptive Wavelets for the analysis of different print patterns on a banknote. Furthermore, a banknote specific feature vector is generated which describes an authentic banknote effectively under various illumination conditions. A multi-stage Lineardiscriminant- analysis classifier generates stable and reliable output.

Sensor fusion by two-layer conflict solving

Many of the existing fusion approaches based on Dempster-Shafer Theory (DST) tend to be unreliable in various scenarios. Therefore, this topic is still in discussion. In this work a Two-Layer Conflict Solving (TLCS) data fusion scheme is proposed which is based on Dempster-Shafer Theory and on Fuzzy-Pattern-Classification (FPC) concepts. The aim is to provide an approach to data fusion which provides a stable conflict scenario handling. Furthermore, the scheme can easily be extended to fuzzy classification and is applicable to sensor fusion applications. Therefore, the suggested approach will contribute as a novel fuzzy fusion method.

Machine conditioning by importance controlled information fusion

Sensor and information fusion is recently a major topic which becomes important in machine diagnosis and conditioning for complex production machines and process engineering. It is a known fact that distributed automation systems have a major impact on signal processing and pattern recognition for machine diagnosis. Therefore, it is necessary to research and develop smart diagnosis methods which are applicable for distributed systems like resource-limited cyber-physical systems. In this paper we propose an new approach for sensor and information fusion based on Evidence Theory and socio-psychological decision-making. We show that context based condition monitoring is instantiated even in conflict situations, oc-curing in real life scenarios permanently. A simple but effective importance measure is proposed which controls the significance of conditioning propositions in a system.

An extended perspective on evidential aggregation rules in machine condition monitoring

In this paper we propose a novel, extended perspective on evidential aggregation rules in machine condition monitoring. First, aspects regarding the interconnections between Dempster-Shafer, Fuzzy Set, and Possibility Theory are shown. Subsequently, a novel approach for direct determination of basic probability assignments using Fuzzy membership functions is proposed. Finally, it is applied to a pipe extrusion lines condition monitoring system, considering and reducing pairwise conflicts.

Information Fusion of Conflicting Input Data

Sensors, and also actuators or external sources such as databases, serve as data sources in order to realise condition monitoring of industrial applications or the acquisition of characteristic parameters like production speed or reject rate. Modern facilities create such a large amount of complex data that a machine operator is unable to comprehend and process the information contained in the data. Thus, information fusion mechanisms gain increasing importance. Besides the management of large amounts of data, further challenges towards the fusion algorithms arise from epistemic uncertainties (incomplete knowledge) in the input signals as well as conflicts between them. These aspects must be considered during information processing to obtain reliable results, which are in accordance with the real world. The analysis of the scientific state of the art shows that current solutions fulfil said requirements at most only partly. This article proposes the multilayered information fusion system MACRO (multilayer attribute-based conflict-reducing observation) employing the μBalTLCS (fuzzified balanced two-layer conflict solving) fusion algorithm to reduce the impact of conflicts on the fusion result. The performance of the contribution is shown by its evaluation in the scope of a machine condition monitoring application under laboratory conditions. Here, the MACRO system yields the best results compared to state-of-the-art fusion mechanisms. The utilised data is published and freely accessible.

Fuzzy-Pattern-Classifier Training with Small Data Sets

It is likely in real-world applications that only little data is available for training a knowledge-based system. We present a method for automatically training the knowledge-representing membership functions of a Fuzzy-Pattern-Classification system that works also when only little data is available and the universal set is described insufficiently. Actually, this paper presents how the Modified-Fuzzy-Pattern-Classifier’s membership functions are trained using probability distribution functions.

A Possibilistic Framework for Sensor Fusion with Monitoring of Sensor Reliability

Sensor and Information fusion is recently a major topic, not only in traffic management, military, avionics, robotics, image processing, and e. g. medical applications, but becomes more and more important in machine diagnosis and conditioning for complex production machines and process engineering. Several approaches for multi-sensor systems exist in the literature, cf. (Hall & Llinas, 2001); (Bosse et al., 2007). The diagnosis and flaw detection in machines and process plants is a complex task, which is dependent on many effects. In the past decades, autonomous and automatic systems have become ubiquitous in our daily life. As famous examples, one may cite advanced driver-assistance systems in vehicles, quality monitoring in production processes, or semi-autonomous unmanned aircraft systems in military forces. All these systems have the common feature that they (partially) capture the state of the environment and generate fused information based on the data gained. More technically, the analogous environment is captured applying several sources (sensors, experts, etc.). After obtaining these analogous signals and experts’ information, they are preprocessed and transformed into the digital domain, so that they can be processed on computers. In many cases the information captured from the environment may be imprecise, incomplete or inconsistent. Furthermore, signal sources may be not reliable. Therefore, it is necessary to extend known fusion concepts insofar that they are able to handle and to measure imprecision and reliability. In this chapter we will highlight, to our best knowledge, a new human-centric based fusion framework. Additionally, an application of the fusion method is shown for printing machines in the area of quality inspection and machine conditioning. The goal is the early recognition of errors in machines in order to avoid flaws by combining measuring data from several sensors with expert knowledge for the improvement of quality by

Feature Extraction Algorithm for Banknote Textures Based on Incomplete Shift Invariant Wavelet Packet Transform

Segmentation and feature extraction algorithms based on Wavelet Transform or Wavelet Packet Transform are established in pattern recognition. Especially in the field of texture analysis they are known to be practical. One difficulty of texture analysis was in the past the characterization of different printing processes. In this paper we present a new algorithmic concept to feature extraction of textures, printed by different printing techniques, without the necessity of a previous teaching phase. The typical characters of distinct printed textures are extracted by first order statistical moments of wavelet coefficients. The algorithm uses the 2D incomplete shift invariant Wavelet Packet Transform, resulting in a fast execution time of O(N log2 (N )). Since the incomplete shift invariant Wavelet Packet Transform was exclusively defined for 1D-signals, it has been modified in this research. The application describes the detection of different printed security textures.

Fast evidence-based information fusion

Information fusion systems are crucial for the success of the upcoming fourth industrial revolution. In this emerging field, cyber-physicals systems play a major role. These are physical processing systems equipped with sensory devices which interconnect over communication networks for distributed cognitive information processing applications. Cyber-physical systems are generally limited in computational resources. Due to this fact, signal processing algorithms cannot be implemented one-to-one. Instead, efforts must be spent in algorithm optimisation towards resource efficiency and reduced computational complexity. In this contribution, we present our optimisation approach by matrix decomposition of an evidence-based conflict-reducing fusion approach which after optimisation is applicable in resource-limited devices for cognitive signal processing. We evaluate the results by comparison with the algorithms original definition and show the improvements achieved.