Andere Kunden interessierten sich auch für
![An Efficient System for Partial Palm Print Recognition using Ridges]( "An Efficient System for Partial Palm Print Recognition using Ridges")
An Efficient System for Partial Palm Print Recognition using Ridges23,99 €![Dynamic Force Spectroscopy and Biomolecular Recognition]( "Dynamic Force Spectroscopy and Biomolecular Recognition")
Dynamic Force Spectroscopy and Biomolecular Recognition204,99 €![CNN Based Person Specific Face Recognition & Detection]( "CNN Based Person Specific Face Recognition & Detection")
CNN Based Person Specific Face Recognition & Detection27,99 €![Basics of Molecular Recognition]( "Basics of Molecular Recognition")
Basics of Molecular Recognition242,99 €![ReCognition- CO-ANDA 19 VACCINE, Part 2]( "ReCognition- CO-ANDA 19 VACCINE, Part 2")
ReCognition- CO-ANDA 19 VACCINE, Part 237,99 €![Optical Pattern Recognition]( "Optical Pattern Recognition")
Optical Pattern Recognition75,99 €![The HOS for Blind Identification and Equalization of Systems]( "The HOS for Blind Identification and Equalization of Systems")
The HOS for Blind Identification and Equalization of Systems23,99 €
Automation of the recognition process of Auger spectra has turned out to be quite a tedious task. Attempts by various researchers have been made, and there are even some data processing software which do that, but with many remaining problems and high uncertainty. Two elements of the measured spectra which greatly interfere with the automatic recognition process are background and noise. Background interferes in quantitative evaluation of characteristic peaks of elements, whereas some of the spikes coming out as a result of noise, in the automatic recognition process will be falsely accounted for as peaks. Thus for further data preparation, finding proper methods for background removal and noise reduction is a must. Even though the idea seems straight forward, this is not an easy task, because whenever the data is manipulated through background removal and noise reduction methods, the risk of altering the original data is always present. Our team is studying methods to accomplishthe data preparation for automatic recognition with minimal loss of the original data. We expect that through these methods the automatic spectra recognition will be greatly improved.