Neural network edge detection and skin lesions image segmentation methods: analysis and evaluation
Publication Date
2003
Creator
Abstract
Similar to a human observer, an automated image vision system is able to recognise most parts of an object if the system could accurately trace and reflect its true shape. This has prompted the development of the many diverse edge detection techniques. Neural networks have been successfully applied to pattern recognition tasks and edge detection. However, there is a great necessity to analyse neural network models so as to achieve close insight into their internal functionality. To this purpose, a new and general training set, consisting of a limited number of prototype edge patterns, is proposed to analyse the problem of neural network edge detection.
This thesis also proposes two approaches to the skin lesion image segmentation problem. The first is a mainly thresholding segmentation method where an optimal threshold is determined iteratively by an isodata algorithm. The second method proposed is based on neural network edge detection and a rational Gaussian curve that fits an approximate closed elastic curve between the recognized neural network edge patterns. A quantitative comparison of the techniques is enabled by the use of synthetic lesions to which Gaussian noise is added. The proposed techniques are also compared with an established automatic skin segmentation method. It is demonstrated that for lesions with a range of different border irregularity properties the thresholding segmentation method provides the best performance over a range of signal to noise ratios; the thresholding segmentation method is also demonstrated to have similar performance when tested on real skin lesions.
Item Type
ethesis
Thesis Type
PhD
Supervisors
Subjects (LC)
Associated Schools / Departments
Department of Electrical and Electronic Engineering (UK)
eprints ID
13681
UoN Repository URI
Except where otherwise noted, this item's license is described as
File(s)![Thumbnail Image]()
Name
405093.pdf
Type
Full-text
Size
17.53 MB
Format
Adobe PDF
Checksum ()