prikaz prve stranice dokumenta Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža
Access restricted to students and staff of home institution
undergraduate thesis
Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. urn:nbn:hr:179:235487
Klein, Luka
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Klein, L. (2021). Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:235487

Klein, Luka. "Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:235487

Klein, Luka. "Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:235487

Klein, L. (2021). 'Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:235487

Klein L. Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:179:235487

L. Klein, "Prepoznavanje captcha znakova korištenjem povratnih neuronskih mreža", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:235487

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje captcha znakova korištenjem povratnih neuronskih mreža
Title (english)Recognition of captcha characters using recurrent neural networks
AuthorLuka Klein
MentorMatko Šarić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom završnom radu objašnjeni su temelji rada konvolucijskih i povratnih neuronskih mreža. Objašnjen je način prepoznavanja teksta u slikama korištenjem jednostavne troslojne neuronske mreže primjenom procesa segmentacije i prepoznavanja teksta. Na primjeru su praktično primijenjene CNN i RNN arhitekture u svrhu prepoznavanja CAPTCHA znakova iz skupa od 1040 jedinstvenih slika. Prosječna uspješnost aplikacije je nešto viša od 75%.
Abstract (english)
In this bachleor's thesis the basics of the operation of convolutional and recurrent neural networks are explained. The way of text recognition in images is explained using a simple three-layer neural network with the process of segmentation and text recognition. In the example, CNN and RNN architectures were practically applied for the purpose of recognizing CAPTCHA characters from a set of 1040 unique images. The average success rate of the application is slightly higher than 75%.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:235487
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
RepositoryRepository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Created on2021-12-06 14:15:04