Naslov
Melanoma and Skin Lesion Detection Using OpenCV and Machine Learning Algorithms

Autori
Banfić, Nenad

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
11.07

Godina
2017

Stranica
49

Mentor
Milašinović, Boris

Ključne riječi
melanoma ; skin lesion ; benign ; malignant ; colour ; structure ; asymmetry ; border ; texture ; OpenCV ; Android ; server ; machine learning ; model ; images ; image processing

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA