prikaz prve stranice dokumenta Očitavanje rukom pisanih slova
No public access
undergraduate thesis
Očitavanje rukom pisanih slova
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. urn:nbn:hr:168:564532
Gulan, Filip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Gulan, F. (2016). Očitavanje rukom pisanih slova (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:564532

Gulan, Filip. "Očitavanje rukom pisanih slova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:564532

Gulan, Filip. "Očitavanje rukom pisanih slova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:564532

Gulan, F. (2016). 'Očitavanje rukom pisanih slova', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 24 August 2024, https://urn.nsk.hr/urn:nbn:hr:168:564532

Gulan F. Očitavanje rukom pisanih slova [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2016 [cited 2024 August 24] Available at: https://urn.nsk.hr/urn:nbn:hr:168:564532

F. Gulan, "Očitavanje rukom pisanih slova", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2016. Available at: https://urn.nsk.hr/urn:nbn:hr:168:564532

Metadata
TitleOčitavanje rukom pisanih slova
Title (english)Handwritten Letters Recognition
AuthorFilip Gulan
MentorMarko Čupić (mentor)
Committee memberMarko Čupić (predsjednik povjerenstva)
Committee memberSiniša Srbljić (član povjerenstva)
Committee memberAlan Jović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2016-07-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu prikazan je način rada i implementacija sustav za očitavanje rukom pisanih slova koji je projektiran tako da na svoj ulaz primi sliku slova, a na svom izlazu vrati prepoznato slovo. Primljena slika se obrađuje te se iz nje izdvaja kostur slova. Izvučeni kostur se zatim skalira na uniformne dimenzije i gradi se vektor značajki korištenjem dijagonalne i horizontalne projekcije te broja točaka presjecište i broja krajnjih točaka. Tako dobiveni vektor značajki se dovodi na ulaze neuronske mreže koja je učena algoritmom propagacije pogreške unatrag uz dodatak momenta inercije. Skup za učenje neuronske mreže se sastojao od 4480 velikih i malih tiskanih slova hrvatske i engleske abecede.
Abstract (english)
This thesis describes the algorithm and implementation details of system for handwritten letter recognition. On its input, it receives letter image, and returns recognized letter as output. First, the input image is preprocessed and letter skeleton is extracted. After that, letter skeleton is scaled to uniform dimension and feature vector is extracted using diagonal and horizontal projection and number of cross-points and end-points. Extracted feature vector is input for neural network which is trained using backpropagation algorithm with momentum. Training set is consisted of 4480 large and small handwritten letters of Croatian and English alphabet.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:564532
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 conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 09:06:05