izpis_h1_title_alt

Beleženje prisotnosti s pomočjo računalniškega vida
ID DRAB, ŽIGA (Author), ID Čehovin Zajc, Luka (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (16,70 MB)
MD5: C8C96EC2D83E886B5894547BAFE23C0F

Abstract
Preverjanje prisotnosti poteka na obveznih vajah ali predavanjih ter pri opravljanju kolokvijev in izpitov. Sam proces se skoraj vedno nagiba v eno izmed dveh skrajnosti; velikokrat je preveč natančen in predolg, na primer ko profesor obhodi celotno predavalnico in označi vsakega posebej, ali pa je premalo natančen, nezaupljiv in krajši, na primer ko se študenti podpišejo na list papirja, ki kroži okoli po predavalnici. V okviru diplomske naloge smo razvili sistem za beleženje prisotnosti s pomočjo računalniškega vida, ki vsebuje najboljše lastnosti obeh ekstremov. Študentje se, ob zahtevi profesorja, sprehodijo do naprave in pokažejo študentsko izkaznico. Sistem s tehnikami OCR razpozna vpisne številke in jih posreduje spletnemu strežniku, ki jih shrani v podatkovno bazo. Profesorjem je na voljo spletna aplikacija, kjer lahko napravo za določen termin rezervirajo. Po končanem preverjanju lahko dostopijo do evidence ter jo po potrebi tudi izvozijo. Tak način identifikacije je hitrejši in enostavnejši, a kljub temu izjemno zanesljiv.

Language:Slovenian
Keywords:računalniški vid, ujemanje predlog, identifikacija, OCR, razpoznava, spletna aplikacija
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Year:2022
PID:20.500.12556/RUL-140180 This link opens in a new window
COBISS.SI-ID:122855171 This link opens in a new window
Publication date in RUL:12.09.2022
Views:988
Downloads:91
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Attendance logging using computer vision
Abstract:
Attendance is checked in obligatory auditory exercises or lectures and in colloquia and examinations. The process itself almost always tends to one of two extremes: it is often too detailed and too long, e.g. when the professor goes around the whole lecture hall and ticks each one individually, or it is too imprecise, not reliable enough and too short, e.g. when students sign a piece of paper that is passed around the lecture hall. We implemented an attendance system, that contains the best features of both extremes. Students, when asked by the professor, walk by the device and show their student IDs. The system recognises the registration numbers with ORC techniques and sends them to the server, which stores them in a database. Professors have an access to a web application where they can book the device for a specific term. Once the verification is complete, they can access and, if necessary, export the records. This way of identification is faster and simpler, but still extremely reliable.

Keywords:computer vision, template matching, identification, OCR, recognition, web application

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back