Automatsko raspoznavanje oblika lica

undergraduate thesis

• Title (english): Automatic Face Shape Recognition
• Author: Jakov Raguž
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Demijan Grgić (član povjerenstva)
• Committee member: Ivana Slošić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Automatsko raspoznavanje oblika lica iz slike u ovome radu temeljeno je na tri koraka: detekcija lica i njegovih karakterističnih točaka, segmentacija lica iz slike te u konačnici detekcija oblika iz prethodno pripremljenih predložaka. Za detekciju lica korištene su javno dostupne biblioteke Dlib i OpenCV. Segmentacija lica iz zadane slike provedena je u dva dijela: preko karakterističnih točaka lica te uspoređujući BGR vrijednosti boje lica. Klasifikacija oblika temeljila se na preklapanju segmentirane slike s predlošcima te računanje broja preklopljenih piksela. Na temelju toga lice se svrstava u jedan od četiri osnovna oblika: srcoliki, ovalni, okrugli ili četvrtasti. Raspravljeni su glavni problemi prilikom implementacije kao i moguća poboljšanja.

Abstract (english)

Automatic face shape recognition from the image in discussed in this paper is based on three steps: detection of the face and its characteristic points, segmentation of the face from the image and finally detection of the shape from the previously prepared templates. Publicly available Dlib and OpenCV libraries were used for face detection. Facial segmentation from a given image was performed in two parts: over characteristic facial points and comparing BGR values of facial color. The classification of shapes was based on overlapping a segmented image with templates and calculating the number of overlapping pixels. Based on this, the face is classified into one of four basic shapes: heart, oval, round, or square. The main problems during implementation as well as possible improvements were also discussed.

• Keywords: OpenCV; Dlib; detekcija lica; detekcija karakterističnih točaka lica; segmentacija lica; oblik lica; BGR vrijednosti
• Keywords (english): OpenCV; Dlib; face detection; face feature detection; face segmentation; face shape; BGR values
• Language: croatian
• URN:NBN: urn:nbn:hr:168:046674
• 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: 2023-01-14 09:48:14