diplomsko delo
Žiga Drab (Author), Luka Čehovin (Mentor)

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.

Keywords

ujemanje predlog;identifikacija;OCR;razpoznava;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [Ž. Drab]
UDC: 004.93(043.2)
COBISS: 122855171 Link will open in a new window
Views: 33
Downloads: 12
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Attendance logging using computer vision
Secondary 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.
Secondary keywords: computer vision;template matching;identifcation;OCR;recognition;web application;computer science;diploma;Računalniški vid;Beleženje podatkov;Spletne aplikacije;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 51 str.
ID: 16439172