Back to search

Institutional Repository of Vilnius University

Detection of Scribbles Elements by Image Recognition /

Abstract

dc:description

The goal is to find or create a method suitable for scribble recognition. Four overall machine learning methods were tested: • K Nearest Neighbour using DTW distance measure • Support Vector Machines • Random Forest • Convolutional Neural Networks KNN DTW is proven to be unsuitable due to the nature of vectorised drawing data and the arbitrary class distinctions imposed by R. Kellogg, who naturally approached the problem of classification from a children’s psychological development perspective. Support vector machine and Random Forest methods perform admirably despite minimal feature engineering, with Random Forest proving superior, reaching competitive accuracy and classification speed. Finally, convolutional neural networks are shown to handle scribbles as time-series-like data well, except for significant overfitting, which was solved by taking advantage of data augmentation. Most of R. Kellogg’s classes are easy to augment, bringing the dataset from 7037 scribble instances to 148,029. The best accuracy of this classifier is approximately 98%.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Vaitkevičius, Lukas,
Contributors dc:contributor
  • Dervinis, Donatas

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Vaitkevičius, Lukas,. Detection of Scribbles Elements by Image Recognition /. Institutional Repository of Vilnius University, 2019. https://repository.vu.lt/VU:ELABAETD37989217&prefLang=en_US