National Technical University of Athens (NTUA)
Ποιοτική και ποσοτική ανάλυση ψηφιακών εικόνων δοντιών και τηλεματική/κινητή αξιοποίηση των αποτελεσμάτων της επεξεργασίας
Abstract
dc:descriptionThe objective of this thesis is the qualitative and quantitative analysis of Dental Digital Images and x-rays in particular and the telematics/mobile utilization of the results of the processing. The imaging modalities used in dentistry, the dental – radiographic acquisition techniques, and other techniques are presented in the thesis. Furthermore, due to the fact that images to be processed are of low resolution, image quality improvement and contrast enhancement techniques are also presented along with image registration and post processing telematics/mobile image utilization techniques.Initially, a new contrast enhancement algorithm that combines the Region Growing segmentation and the theory of Partitioned Iterated Function Systems (PIFS) is proposed. The image is initially partitioned, through the Region Growing method, into domain regions and range regions, and the PIFS enhancement algorithm is applied separately to each image segment. The defined PIFS of each section are modeled by a contractive transformation which consists of an affine spatial transform, as well as the linear transform of the gray-levels of the image segment pixels. The transformation of the gray-levels is determined by two parameters which adjust the brightness and the contrast of the transformed image segment. After the PIFS algorithm is applied to each extracted image segment, a lowpass version of the original image is created. The contrast-enhanced image is obtained by suitably combining the original image with its lowpass version. Next, the methodology used for the automatics registration of 3-D datasets is presented based on pairs of relevant points. The problem is reduced in complexity by registering only specific (characteristic) image data points instead of the whole image dataset. This reduction in the complexity of the problem allows for the calculation of the optimal registration in a direct manner without the need of optimization techniques. The characteristic image points are determined in an automatic way only in the reference image and are subsequently paired with the relevant points in the image under registration. The transformation parameters are calculated directly from the pairs of points with a least squared estimation. Next, the transformation is applied in the image under registration and the measure of match between the two images is determined. This procedure can be repeated until the required measure of match is achieved. This procedure is applied to the dental images. Finally, we propose an integrated mobile system with the use of smartphones in order to take advantage of the results of the image processing performed. Images are captured from the user himself, who has the ability to process those images, improve their contrast and request for a match. The images per se as well as the results of the processing can be transmitted to a central server, as well as can be transmitted to a specialized dentist who can have a view of the evolution of the dental disease.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2014
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Koutsouri, Tzortzia
- Κουτσούρη, Τζόρτζια
Subjects
dc:subject × 12- Ψηφιακές εικόνες δοντιών
- Ψηφιακή επεξεργασία εικόνων
- Βελτίωση της αντίθεσης
- Τηλεματική
- Dental digital images
- Digital image processing
- Contrast enhancement
- Telematics
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/42283