Sustav za raspoznavanje rukom pisanih znakova

undergraduate thesis

• Title (english): System for handwritten character recognition
• Author: Domagoj Boroš
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rad prikazuje primjenu umjetnih neuronskih mreža u sustavima za raspoznavanje rukom pisanih znakova. Za primjer konkretnog sustava koristi se sustav za raspoznavanje rukom pisanih znamenki. Kroz teoretski i praktični prikaz rad prikazuje način rada, dobre strane, probleme i nedostatke takvih sustava. Rad prikazuje primjenu umjetnih neuronskih mreža i konvolucijskih neuronskih mreža te ističe njihovu razliku. Uz rad je objašnjeno kako koristiti radne okvire koji su korišteni u prikazanim primjerima. U sklopu rada sakupljen je popis rukom pisanih matičnih brojeva od strane studenata Fakulteta elektrotehnike i računarstva na kolegiju Skriptni jezici. Nad tim popisom napravljena su testiranja naučene mreže te su prikazani i objašnjeni rezultati.

Abstract (english)

The thesis presents the application of artificial neural networks in systems for recognizing handwritten characters. As a particular system a system for recognizing handwritten digits is used. Through theoretical and practical presentation the thesis shows the strengths, problems and shortcomings of such systems. The thesis presents the application of artificial neural networks and the convolutional neural networks and emphasizes the difference. The usage of the used frameworks in the examples is explained. As a part of this thesis a list of handwritten student identification numbers was collected from the students of the Faculty of Electrical Engineering and Computing in the class of Scripting languages. A trained network was tested on this list. Results where presented and explained.

• Keywords: Umjetna neuronska mreža; Konvolucijska neuronska mreža; Sustav; Sustav za raspoznavanje rukom pisanih znakova; Sustav za raspoznavanje rukom pisanih znamenki; Rukom pisani znakovi; Rukom pisane znamenke; Lenet; Lenet-5; Raspoznavanje uzoraka
• Keywords (english): Artificial neural network; Convolutional neural network; Image recognition; Handwritten sign recognition; Handwritten digit recognition; Handwritten sign; Handwritten digit; Handwritten; Lenet; Lenet-5
• Language: croatian
• URN:NBN: urn:nbn:hr:168:481397
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 07:58:03