Detekcija melanoma i lezija kože korištenjem OpenCV-a i algoritama strojnog učenja

master's thesis

• Title (english): Melanoma and Skin Lesion Detection Using OpenCV and Machine Learning Algorithms
• Author: Nenad Banfić
• Mentor: Boris Milašinović (mentor)
• Committee member: Boris Milašinović (predsjednik povjerenstva)
• Committee member: Nikica Hlupić (član povjerenstva)
• Committee member: Mirjana Domazet-Lošo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Zadatak ovog diplomskog rada je bio prikupiti slike dobroćudnih i zloćudnih lezija kože, a zatim proučiti programski okvir OpenCV te korištenjem različitih algoritama segmentacije i ekstrakcije značajki, naći način za izvući značajke poput boje, asimetrije, granice te strukture iz same slike. Također su razvijeni i testirani različiti nadzirani modeli strojnog učenja u cilju klasificiranja lezija u potencijalno opasne ili bezopasne. Razvijena je i mobilna aplikacija za platformu Android koja omogućuje fotografiranje lezija i prikazivanja rezultata analize korisniku. Razmotrena je varijanta obrade slike i klasifikacije na uređaju, kao i na poslužitelju.

Abstract (english)

The task of this master thesis was to collect images of both benign and malicious skin lesions, study the OpenCV application framework and find a way to extract features such as colours, asymmetry, borders, structures by using different segmentations and feature extraction algorithms. Afterwards, it was important to develop and test different supervised machine learning models in order to classify lesions into potentially dangerous or safe and develop an Android application that would enable a user to take a photo of a lesion and receive back the analysis result. Different variants of image processing were taken into the consideration, i.e. on a mobile device and on the server.

• Keywords: melanoma; lezija kože; dobroćudni; zloćudni; boja; struktura; asimetrija; granica; tekstura; OpenCV; Android; poslužitelj; strojno učenje; model; slike; obrada slike
• Keywords (english): melanoma; skin lesion; benign; malignant; colour; structure; asymmetry; border; texture; OpenCV; Android; server; machine learning; model; images; image processing
• Language: english
• URN:NBN: urn:nbn:hr:168:441657
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 18:48:52