Organic Computing Methods for Face Recognition Methoden des Organic Computing zur Gesichtserkennung
نویسنده
چکیده
Automatic face recognition is a slowly maturing and economically highly important technology, which still falls short of the high expectations set on it. The variation in images taken from the same person makes face recognition systems difficult to design – it is impossible to explicitly code all variability. Successful systems have relied heavily on the principle of self-organizing many fragile cues to arrive at a robust decision and have been built by learning from biological systems. The paper describes the techniques of elastic bunch graph matching as a hierarchical integration of image pixels into Gabor responses, jets, graphs, and bunch graphs. Beside face recognition, these concepts are used for face classification learned from examples. It is attempted to develop them further to reach a complete parameterization of all faces. Methods for more general object recognition using the same Organic Computing principles are outlined and include the concept of end-stopped cells as corner detectors. Zusammenfassung Automatische Gesichtserkennung ist eine Technik von immensem wirtschaftlichen Interesse, die aber die hohen Erwartungen noch nicht erfüllen kann. Die Schwierigkeit besteht darin, dass die Variation der Bilder ein und derselben Person nicht explizit kodiert werden kann. Erfolgreiche Systeme sind auf dem Prinzip der Selbstorganisation vieler unzuverlässiger Hinweise zu einer robusten Entscheidung aufgebaut und sind von biologischen Systemen inspiriert. Die Arbeit beschreibt die Technik des Bündelgraphenmatching als hierarchische Integration von Pixeln zu Filterantworten, Jets, Graphen und Bündelgraphen. Außer der Personenerkennung werden diese Konzepte auch zur Klassifizierung von Gesichtseigenschaften verwendet, die vollkommen aus Beispielen gelernt ist. Sie sollen zu einer kompletten Parameterisierung aller Gesichter weiterentwickelt werden. Methoden zur allgemeinen Objekterkennung, die auf denselben Prinzipien des Organic Computing beruhen, werden angedeutet, z. B. das Konzept der End-stopped cells zur Eckendetektion.
منابع مشابه
Formale Eigenschaften des SILKE-Ansatzes zur Kontrolle selbstoptimierender Systeme
Im Rahmen des Organic Computing werden auch eingebettete Echtzeitsysteme immer öfter mit selbstoptimierenden Eigenschaften ausgestattet. Die selbsttätige Adaption des Systemverhaltens kann aber potentiell zu kritischen Systemzuständen führen. Für spezielle lernfähige Fuzzy-Systeme wurde der sogenannte SILKE-Ansatz entwickelt, um kontrollierend auf den Selbstoptimierungsprozess einzuwirken und i...
متن کاملPrediction of the pharmaceutical solubility in water and organic solvents via different soft computing models
Solubility data of solid in aqueous and different organic solvents are very important physicochemical properties considered in the design of the industrial processes and the theoretical studies. In this study, experimental solubility data of 666 pharmaceutical compounds in water and 712 pharmaceutical compounds in organic solvents were collected from different sources. Three different artificia...
متن کاملFace Recognition Based Rank Reduction SVD Approach
Standard face recognition algorithms that use standard feature extraction techniques always suffer from image performance degradation. Recently, singular value decomposition and low-rank matrix are applied in many applications,including pattern recognition and feature extraction. The main objective of this research is to design an efficient face recognition approach by combining many tech...
متن کاملOrganic Computing for face and object recognition
In this paper I describe how the various subsystems for a vision system capable of recognizing faces and objects have been developed using Organic Computing methodology, namely the reliance on “learning from nature” and “self-organization”. Then, extensions and refinements currently under development are discussed.
متن کاملImproving the Resilience of Military Hospitals Through Self-Adaptation of Hospital Systems Using Organic Computing
Background and Aim: Among the failures of a disaster, the disruption of the critical infrastructure of the community causes the most damage to society. Therefore, the ability of critical infrastructure such as hospitals to anticipate, absorb, adapt or rapidly recover from a devastating event is essential. The purpose of this study is to design a self-adaptive model for resilient hospital system...
متن کامل