prikaz prve stranice dokumenta Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja
  Download
PDF 2.57 MB
undergraduate thesis
Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. urn:nbn:hr:200:422173
Takač, David
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Takač, D. (2019). Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:422173

Takač, David. "Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:422173

Takač, David. "Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:422173

Takač, D. (2019). 'Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 18 February 2025, https://urn.nsk.hr/urn:nbn:hr:200:422173

Takač D. Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2025 February 18] Available at: https://urn.nsk.hr/urn:nbn:hr:200:422173

D. Takač, "Raspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:422173

Metadata
TitleRaspoznavanje slova znakovnog jezika korištenjem postupaka strojnog učenja
Title (english)Character letters recognition by using machine learning methods
AuthorDavid Takač
MentorGoran Martinović (mentor)
MentorBruno Zorić (mentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberRobert Cupec (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2019-09-23, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Rad donosi teorijsku podlogu potrebnu za razumijevanje procesa implementacije modela strojnog učenja za raspoznavanje znakovnog jezika pomoću uslikane ruke. Daje se pregled cijelog postupka od predobrade slika i izlučivanja značajki do treniranja klasifikatora, vrednovanja i odabira optimalnih hiperparametara. Rješenje je implementirano pomoću Scikit-learn, Scikit-image i OpenCV Python biblioteka. Najbolji rezultati postignuti su šumom odluke i značajkama dobivenim algoritmom lokalnih binarnih uzoraka, ali i stroj s potpornim vektorima i k-najbližih susjeda postižu slične rezultate s takvim značajkama. Analizirane su i druge metode izdvajanja značajki kao Canny detekcija rubova i osnovna analiza komponenti sa spomenutim klasifikatorima, iako su dale lošije rezultate.
Abstract (english)
This work presents the theoretical background necessary for understanding the implementation of a sign language classifier. An overview of the entire process is given; from image preprocessing and feature extraction to classifier training and cross-validation for fine tuning the machine learning model. The experimental portion was implemented using Python libraries such as Scikit-learn, Scikit-image and OpenCV. The best results were achieved using a random forest classifier with features extracted using the local binary patterns algorithm, although support vector machine and K-nearest neighbor classifiers achieved similar results with such features. Other feature extraction algorithms such as Canny edge detection and principal component analysis were implemented with those classifiers as well, although with poorer results.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:422173
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-11-05 14:17:55