Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/B15CF960-F240-4C09-8603-615FBFF91ECD | ||
| Year | 2020 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Iliana Zacharopoulou, "Hyperspectral dermoscope for the diagnostic and aesthetic analysis of the skin ", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2020 https://doi.org/10.26233/heallink.tuc.85671 | ||
| Appears in Collections |
Hyperspectral Imaging is a powerful analytical tool that enables the acquisition of a series of images in narrow spectral bands. This technique makes it possible to combine both spatial and spectral information about the scene under investigation. Therefore, it is widely used for non-destructive and non-invasive analysis in various fields, ranging from food quality assessment to biomedical applications. The study of aging and the effects that causes on the human's skin texture has been for years investigated from both medical science and the cosmetic industry. For years, experts have relied on the evaluation of the human's skin texture with "naked eye" which has effects on the objective diagnosis and appropriate treatment. Until today, several imaging devices have been developed to contribute as additional tools for better and more objective diagnosis, but with several disadvantages that still affect it. The aim of this study is to develop an imaging system that will not only capture appearance of skin texture but also quantify it. Several approaches have been reported in the literature using image processing methods to analyze and quantify the texture of the skin, but restrict the analysis only in specific skin texture characteristics that are affected during the aging process. This study proposes a new method that is proving to be more effective and provides a quantitative assessment of skin texture characteristics, compared to the most widely used methods for this purpose, such as GLCM matrix, histogram and image processing in the frequency domain. Finally, using an innovative hyper-spectral dermoscope and a hyper-spectral imaging system, it is possible to collect images of the skin surface in narrow spectral bands extended beyond the visible spectrum perceived by the human eye. By using the appropriate image processing method and the appropriate spectral image band, more accurate and objective measurements can be extracted that will contribute to the objective diagnosis of specialists and the selection of more effective treatments.
Copyright © DIAS 2013
