Raspoznavanje gesti ruku konvolucijskim modelima

master's thesis

• Title (english): Recognition of hand gestures with convolutional models
• Author: Filip Bronić
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Vladimir Čeperić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Raspoznavanje gesti ruku je neriješen problem računalnog vida s mnogim zanimljivim primjenama. U posljednje vrijeme, najbolji rezultati u tom području postižu se dubokim konvolucijskim modelima. U ovom radu se za raspoznavanje gesti ruku iz RGB videosnimki koriste 3D konvolucijske neuronske mreže koje su se pokazale uspješnima u tom području: arhitekture SlowFast i MobileNetV2. Koristeći navedene modele implementiran je sustav za dinamičko prepoznavanje gesti u stvarnom vremenu. Modeli su... More trenirani i evaluirani na podskupu Jester skupa podataka. Prezentirani su rezultati modela i predloženi pravci za daljnji rad. Less

Abstract (english)

Hand gesture recognition is a challenging computer vision problem with many practical uses. Recently, best results have been achieved by deep convolutional models. In this work, for hand gesture recognition in RGB videos 3D convolutional neural networks are used that have achieved great results in the field, architectures SlowFast and MobileNetV2. Using aforementioned architectures a real-time dynamic hand gesture recognition system is implemented. Models are trained and evaluated on a... More subset of the Jester dataset. Model results are presented and potential directions for future work are suggested. Less

• Keywords: računalni vid; strojno učenje; raspoznavanje gesti; konvolucijske neuronske mreže; duboko učenje
• Keywords (english): computer vision; machine learning; hand gesture recognition; convolutional neural networks; deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:490254
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 11:54:14