« August 2005 | Main | November 2005 »
Recherche und Poster zum Thema "Autonome Staubsauger Produkte 09/2005"
Praktikumsarbeit (Gymnasium) von Maximilian Orlowski und Jan Fedor Rohr
Download: A1-Poster
Categories: AMS-Projekte, RobotBuildingLab
Computer vision is a computer science field belonging to artificial intelligence. The purpose of this branch is allowing computers to understand the physical world by visual media means. This document proposes an artificial neural network based face detection system. It detects frontal faces in RGB images and is relatively light invariant.
Problem description and definition are enounced in the first sections; then the neural network training process is discussed and the whole process is proposed; finally, practical results and conclusions are discussed. Process has three stages: 1) Image preprocessing, 2) Neural network classifying, 3) Face number reduction. Skin color detection and Principal Component Analysis are used in preprocessing stage; back propagation neural network is used for classifying and a simple clustering algorithm is used on the reduction stage.
Abgabe: 12.09.2005
Betreuer: Dipl.-Inform. Ingo Boersch
Downloads: Studienarbeit
Categories: Abschlussarbeiten, Maschinelles Lernen
| 14. Projektwoche Bertolt-Brecht-Gymnasium Brandenburg/Havel |
Categories: AKSEN, AMS-Projekte, RobotBuildingLab
Relating to this text
During the last years of my career, the main intention of my work has been to apply neural networks to several fields of my interest, mainly networking security and biomedicine. As Dr. Carmen Paz Suárez Araujo’s, from University of Las Palmas de Gran Canaria (Spain), and Prof. Ingo Boersch’s, from Fachhochschule Brandenburg (Germany), undergraduate student I have learned how important the neurocomputing is becoming in nowadays engineering tasks. Through this path, I have gathered a variety of ideas and problems which I would have appreciated to be written or explicitly available for my personal reading and further understanding.
The employment of a simulator to develop first stage analysis and to plan further work is a must in the engineering discipline. My aim in the development of this brief textbook has been to compose a little, but well condensed manual, where the reader can get the point of self organized networks, and moreover, of Kohonen Self Organized Maps, SOM. Using JNNS, the reader will be able to apply the theoretical issues of
Kohonen networks into practical and real development of ideas.
This brief textbook is oriented to those with little experience in self organization and Kohonen networks, but also to those interested in using and analyzing the deployment of solutions with the Java Neural Network Simulator, JNNS.
Abgabe: 07.09.2005
Betreuer: Dipl.-Inform. Ingo Boersch
Downloads: Studienarbeit Patternfiles.zip
Categories: Abschlussarbeiten, Maschinelles Lernen