Automatska provjera diktata korištenjem Google ML Kita

undergraduate thesis

• Title (english): Automatic dictation check using Google ML Kit
• Author: Marta Dulibić
• Mentor: Boris Milašinović (mentor)
• Committee member: Boris Milašinović (predsjednik povjerenstva)
• Committee member: Danijel Mlinarić (član povjerenstva)
• Committee member: Juraj Dončević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sažetak
U ovom je radu opisana izrada i organizacija mobilne aplikacije My Spelling Buddy. Svrha aplikacije je da služi kao pomoćni alat pri vježbanju pisanja diktata te tako pomaže pri poboljšavanju pravopisnih i gramatičkih znanja korisnika. Sučelje aplikacije je jednostavno i intuitivno te je stoga pogodna za korištenje za sve dobne skupine.
Glavna funkcionalnost aplikacije je automatsko ispravljanje teksta diktata te prikaz napravljenih pogreški. Za ostvarivanje automatskog ispravljanja diktata i skeniranje QR koda korišten je Google ML Kit, mobilni SDK koji implementacijom algoritama iz strojnog i dubokog učenja rješava probleme vezane za vid i prirodni jezik.
Aplikacija je napisana za operacijski sustav Android te je korišten programski jezik Kotlin radi sažetosti koda i lake čitljivosti. Kao baza podataka, korišten je Firebase radi jednostavnosti implementacije i održavanja bez potrebe za pisanjem vlastitog backend servisa.

Abstract (english)

This paper describes the development and organization of the mobile application My Spelling Buddy. The purpose of the application is to serve as an assistant learning tool for practicing dictation writing and thus helps to improve the spelling and grammar knowledge of the users. The application interface is simple and intuitive and therefore convenient to use for all age groups.
The main functionality of the application is the automatic correction of dictation text and the display of made errors. The Google ML Kit, a mobile SDK that solves vision and natural language problems by implementing algorithms from machine and deep learning, was used to achieve automatic dictation correction and QR code scanning.
The application was built for the Android operating system and the Kotlin programming language was used because of its code conciseness and great readability. Firebase was used as the database because of its ease of implementation and maintenance without the need of writing your own back end service.

• Keywords: mobilna aplikacija; diktat; Android; Kotlin; Firebase; Google ML Kit; pravopis; automatsko prepoznavanje; gramatika; QR kod
• Keywords (english): mobile application; dictation; Android; Kotlin; Firebase; Google ML Kit; spelling; automatic recognition; grammar; QR code
• Language: croatian
• URN:NBN: urn:nbn:hr:168:410286
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 10:03:03