Operacije nad sivom slikom temeljene na neizrazitoj logici i neuro-neizrazitim sustavima te primjena na rješavanje Captcha-testova

master's thesis

• Title (english): Fuzy Logic and Neuro-Fuzzy Based Operations on Grayscale Images with Application on Captcha
• Author: Janko Kovačević
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Marin Golub (član povjerenstva)
• Committee member: Jan Šnajder (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Postoji niz različitih operacija koje je moguće raditi nad slikama s 256 nijansi sive boje (engl. grayscale images) a koje uključuju poboljšanje kontrasta, detekciju rubova i slično.
U okviru ovog diplomskog rada implementirane su operacije poboljšanja kontrasta, uklanjanja zrnatog šuma te detekcije rubova temeljeći se neizrazitoj logici te neuro-neizrazitim sustavima. Razrađuje se model adaptivnog neuro-neizrazitog sustava (ANFIS) te algoritmi pomoću kojih model može učiti iz podataka. Razvijeni postupci primjenjeni su na rješavanje odabrane vrste Captcha-testova.

Abstract (english)

There are many different operations which could manipulate gray-scale images. They include contrast enhancement, edge detection and similar algorithms. In this thesis contrast enhancement, clutter removal and edge detection algorithms are analyzed and implemented. Adaptive neuro-fuzzy system (ANFIS) is described as well as algorithms which can be used for its machine learning. Described algorithms are used to solve one type of test CAPTCHA.

• Keywords: Neizrazita logika; Neuro-neizraziti sustavi; ANFIS; Povećanje kontrasta; Uklanjanje šuma; Detekcija rubova; Rješavanje testa Captcha
• Keywords (english): Fuzzy Logic; Neuro-Fuzzy system; ANFIS; Contrast enhancement; Image clutter removal; Image edge detection; test Captcha
• Language: croatian
• URN:NBN: urn:nbn:hr:168:923109
• 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 21:50:07