prikaz prve stranice dokumenta Automatska segmentacija računa pomoću dubokog učenja
No public access
undergraduate thesis
Automatska segmentacija računa pomoću dubokog učenja
2018. urn:nbn:hr:168:001729
Mesar, Antun
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Mesar, A. (2018). Automatska segmentacija računa pomoću dubokog učenja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:001729

Mesar, Antun. "Automatska segmentacija računa pomoću dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:001729

Mesar, Antun. "Automatska segmentacija računa pomoću dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:001729

Mesar, A. (2018). 'Automatska segmentacija računa pomoću dubokog učenja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 10 September 2024, https://urn.nsk.hr/urn:nbn:hr:168:001729

Mesar A. Automatska segmentacija računa pomoću dubokog učenja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 September 10] Available at: https://urn.nsk.hr/urn:nbn:hr:168:001729

A. Mesar, "Automatska segmentacija računa pomoću dubokog učenja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:001729

Please login to the repository to save this object to your list.
Metadata
TitleAutomatska segmentacija računa pomoću dubokog učenja
Title (english)Automatic Segmentation of Receipts Using Deep Learning
AuthorAntun Mesar
MentorMarko Subašić (mentor)
Committee memberMarko Subašić (predsjednik povjerenstva)
Committee memberDavor Petrinović (član povjerenstva)
Committee memberNikola Banić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu smo definirali osnove dubokog učenja i računalnog vida. Primjenili smo znanje na zadatak segmentiranja računa. Za izvedbu smo računalno generirali veliku količinu umjetnih računa. Nad njima smo trenirali neuronsku mrežu za prepoznavanje i klasificiranje podataka sa slike. Koristili smo već gotovu mrežu dostupnu preko tensorflow object detection API-a. Evaluaciju smo provodili putem tensoboarda. Na kraju smo isprobali model na stvarnom računu.
Abstract (english)
In this work we defined the basics of deep learning and computer vision.We used that knowlage on our task of segmenting recepies. We implemented a recepie generator , because we needed a large database. We trained a localization and clasification neural network on the database. For the network we used a predefined network by Google's tensorflow object detection API. The evaluation aspect was done by tensorboard. Finally we tested our model on a real world recepie.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:001729
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 on2019-03-13 22:58:07