Virtualne maske pokretane praćenjem lica

undergraduate thesis

• Title (english): Virtual masks driven by face tracking
• Author: Klaudija Palle
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Nenad Markuš (član povjerenstva)
• Committee member: Martina Manhart (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-09-21, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Računalni vid područje je računarstva koje teži tome da razvije algoritme koji računalima omogućuju procesuiranje slike na način sličan ljudima. U ovom radu računalni vid koristi se za iscrtavanje maske povrh ljudskog lica u video slici. Upotrebljava se biblioteka računalnog vida Visage|SDK koja omogućuje detekciju lica i njegovih karakterističnih točaka. Iz tih karakterističnih točaka stvara se mreža povezanih trokuta koji sačinjavaju lice. Odgovarajuće karakteristične točke lica (ujedno i točke mreže) potrebno je detektirati unutar videa, povrh kojeg se želi iscrtati maska, i slike maske. Pomoću tih točaka zatim se preslikava tekstura maske na odgovarajući trokut u video slici.

Abstract (english)

Computer vision is a field of computing whose purpose is inventing algorithms that enable computers to process images in a way similar to humans. In this paper computer vision is used for drawing masks over the human face in a video sequence. Visage|SDK, a library of computer vision, is used to detect faces and their feature points. From those feature points a triangle mesh is made that makes up the face. The facial feature points (the vertices of the mesh) have to be detected in the video, over which we want to draw the mask, as well as in the image of the mask. By using these points we can draw the texture from the mask over the corresponding triangle in the video frame.

• Keywords: Računalni vid; Visage|SDK; OpenGL; OpenCV; detekcija lica; karakteristične točke lica; mreža trokuta
• Keywords (english): Computer vision; Visage|SDK; OpenGL; OpenCV; face detection; facial feature points; triangle mesh
• Language: croatian
• URN:NBN: urn:nbn:hr:168:472604
• 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: 2018-02-06 11:03:31