prikaz prve stranice dokumenta Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica
  Download
PDF 10.17 MB
doctoral thesis
Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica
2017. urn:nbn:hr:200:158468
Zorić, Bruno
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

Cite this document

Zorić, B. (2017). Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica (Doctoral 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:200:158468

Zorić, Bruno. "Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica." Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:158468

Zorić, Bruno. "Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica." Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:158468

Zorić, B. (2017). 'Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica', Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 24 March 2025, https://urn.nsk.hr/urn:nbn:hr:200:158468

Zorić B. Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica [Doctoral thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2017 [cited 2025 March 24] Available at: https://urn.nsk.hr/urn:nbn:hr:200:158468

B. Zorić, "Unaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica", Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:200:158468

Please login to the repository to save this object to your list.
Metadata
TitleUnaprijeđeni postupci za raspoznavanje razina boli na temelju slika lica
Title (english)Enhanced pain level recognition methods based on facial images
AuthorBruno Zorić
MentorGoran Martinović (mentor)
Committee memberŽeljko Hocenski (predsjednik 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 country2017-11-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Universal decimal classification
(UDC)		621.3 - Electrical engineering
Abstract
U ovoj disertaciji razmatran je problem raspoznavanja razina boli na osnovu slike lica. Rijec je o složenom problemu iz domene raspoznavanja uzoraka, a za cije se rješavanje uobicajeno rabe postupci strojnog ucenja namijenjeni nadziranoj klasifikaciji. S obzirom da se klasifikacijska procedura provodi u nekoliko koraka, u sklopu ove disertacije predložene su ideje koje je moguce ugraditi u pojedine korake te tako pospješiti razinu raspoznavanja boli. Predstavljeni su tako postupak izdvajanja znacajki zasnovan na shearlet transformaciji, metoda odabira znacajki pracenjem njihova pojedinacnog doprinosa te unaprijeeni algoritam za oblikovanje klasifikacijskog modela radijalne neuronske mreže, zasnovan na algoritmu umjetne kolonije pcela. Svaki od prijedloga eksperimentalno je vrednovan na podacima dostupnim iz klinickog okruženja, a njegovo ponašanje je usporeeno s drugim pristupima dostupnima u literaturi. Rezultati analize sugeriraju da postupak izdvajanja znacajki dovodi do boljeg raspoznavanja razina boli prilikom uporabe razlicitih klasifikatora, a cini to uz relativno nizak broj znacajki. Nadalje, metoda odabira znacajki omogucuje pronalazak podskupova znacajki niže dimenzionalnosti uz održavanje kvalitete raspoznavanja ili njenog uvecavanja. Konacno, unaprijeeni algoritam za oblikovanje radijalnih neuronskih mreža uspijeva pronaci mreže koje prema svojim performansama nadilaze one oblikovane konkurentskim algoritmima iz literature.
Abstract (english)
In this doctoral dissertation the problem of pain level recognition based on facial images is considered. As it represents a complex problem from the domain of pattern recognition, various machine learning approaches are commonly utilised in an attempt to solve it. Considering the fact that the classification procedure involves several steps, as a part of this dissertation several ideas are proposed that can be implemented in individual steps, thusly improving the pain level recognition. A feature extraction procedure which is based on the shearlet transform, a method for feature selection through individual contribution tracking and an algorithm for radial basis network classification model design that is based on the artificial bee colony algorithm are presented and implemented. Each of these proposals has been experimentally evaluated on data coming from a clinical environment, and its behaviour compared with alternative approaches employed in the literature for the same tasks. The results of the conducted analysis suggest that the feature extraction procedure leads to better pain level recognition using several classifiers, while achieving the aforementioned using a comparingly lower number of features. Further more, the method for feature selection provides feature subsets that are comparingly of lower dimensionality while maintaining or improving the classification quality. Finally, the enhanced algorithm proposed for the radial basis network design outputs networks that give favourable results regarding classification performance when compared with the networks designed by other algorithms utilised in the experimental analysis.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:158468
Promotion2017-11-19
Study programmeTitle: Postgraduate doctoral study programme; specializations in: branch Power Engineering and Communications, branch Informatics
Course: branch Informatics
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika (doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2017-11-20 12:09:22