Nikoo Arjang
Analysis of Topological Distribution of Skin Lesions.
Rel. Marco Piras, Guido Pagana. Politecnico di Torino, Master of science program in Ict For Smart Societies, 2024
|
Preview |
PDF (Tesi_di_laurea)
- Thesis
Licence: Creative Commons Attribution Non-commercial No Derivatives. Download (2MB) | Preview |
Abstract
In this thesis, we explore the application of edge detection and border detection algorithms in MATLAB for the purpose of skin lesion detection, focusing on melanoma. Specifically, we utilize the Canny and Sobel algorithms to identify and delineate the edges and borders of lesions in dermoscopic images. To assess the similarity of images and effectively detect lesions, we employ Normalized Cross-Correlation (NCC) and Mean Squared Error (MSE) methods. These techniques allow for the comparison of suspected melanoma regions against known samples, facilitating accurate diagnosis. Additionally, we investigate the use of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm for object detection within the images.
However, the results from DBSCAN were not satisfactory for our specific application, highlighting the challenges in clustering-based approaches for skin lesion detection
Relators
Academic year
Publication type
Number of Pages
Course of studies
Classe di laurea
URI
![]() |
Modify record (reserved for operators) |
