Mapiranje karakterističnih točaka ljudskog lica koristeći strojno učenje te Blender programsku podršku

undergraduate thesis

• Title (english): Mapping of characteristic points of the human face using machine learning and Blender software
• Author: Petra Gregov
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2022-09-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Tema ovog rada je istražiti metode umjetne inteligencije za detekciju i mapiranje karakterističnih crta ljudskog lica te implementirati iste u python-u i Blender-u radi animacije 3D modela. Najefikasnija takva metoda su konvolucijske neuronske mreže koje precizno razlučuju obrasce na datim slikama. U prvom dijelu rada se razradio njihov princip rada te prikladne python biblioteke. Dok se u drugom dijelu rada opisao proces dodavanja i namještanja 3D modela, te način animiranja istih unutar Blender grafičkog softvera. Animiranje se izvelo u python kodu pomoću OpenPose biblioteke.

Abstract (english)

The topic of this paper is to investigate artificial intelligence methods for the detection and mapping of characteristic features of the human face and their implementation in Python and Blender for the animation of 3D models. The most efficient such a method are convolutional neural networks that accurately distinguish patterns in given images. Their working principle and suitable python libraries are explained in the first part of the work. While the second part of the paper shows how to add and adjust 3D models and how to achieve their animation within the Blender graphics software. The animation was performed in python code using the OpenPose library.

• Keywords: Python; Blender; 3D model; karakteristične crte lica; OpenPose; CNN
• Keywords (english): Python; Blender; 3D model; characteristic facial features; OpenPose; CNN
• Language: croatian
• URN:NBN: urn:nbn:hr:235:038887
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-09-27 16:20:01