Self-adaptive models for laser monitor image processing

The paper is devoted to processing the images of specific type. In particular, we present a work in progress of how the image quality can be improved when such images are obtained using a laser monitor. This monitor represents a novel technology that allows to see (observe) some objects or processes...

Full description

Saved in:
Bibliographic Details
Published in:2016 17th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM) pp. 300 - 303
Main Authors: Zaytsev, Alexandre, Trigub, Maxim, Kushik, Natalia, Yevtushenko, Nina, Evtushenko, Tatiana
Format: Conference Proceeding
Language:English
Published: IEEE 01-06-2016
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The paper is devoted to processing the images of specific type. In particular, we present a work in progress of how the image quality can be improved when such images are obtained using a laser monitor. This monitor represents a novel technology that allows to see (observe) some objects or processes that cannot be distinguished with human being eyes, for example, human beings cannot see through flames without special equipment. A laser monitor provides these abilities but the corresponding images are captured by high speed cameras and still need to be improved. Such improvement cannot be performed with the use of `classical' methods and software tools. The reason is that by default almost all of them perform the de-noising under the assumption of well studied noises, such as white Gaussian noise. However, this is not the case for the images obtained from the laser monitor as it is demonstrated in this paper by our experimental results. As an alternative solution, we propose to address the self adaptive models for efficient improvement of the images of this proper kind. The paper contains the discussion about the types of self adaptive models that can be taken into consideration for this purpose.
ISSN:2325-419X
DOI:10.1109/EDM.2016.7538745