Automatic brightness control in near-infrared spectrum using approximate face region detection

doctoral thesis

• Title (croatian): Automatsko upravljanje svjetlinom u bliskom infracrvenom području s aproksimativnom detekcijom regije lica
• Author: Jurica Vugrin
• Mentor: Sven Lončarić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Davor Petrinović (član povjerenstva)
• Committee member: Edouard Ivanjko (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronic Systems and Information Processing); Zagreb
• Defense date and country: 2023-09-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing

Abstract

The face analysis field is a well-established research area in computer vision and image processing. A very important requirement for face analysis algorithms to work properly is to have a high-quality input face image regardless of various illumination conditions. For that reason, near-infrared images are used instead of visible spectrum images. To obtain a high-quality near-infrared face image, the fast automatic brightness control with approximate face region detection is introduced which properly adjusts the brightness of the approximate face region of the image. A novel algorithm for approximate face region detection based on a spatio-temporal sampled skin detection is implemented together with the split-range feedback controller and the face absence handle included. The proposed algorithm is accurate, fast and suitable for real-time embedded system implementation.

Abstract (croatian)

Područje analize lica je čvrsto utemeljena grana istraživanja u računalnom vidu i obrade slika. Vrlo važan zahtjev algoritama za uspješnu analizu lica je ulazna slika lica visoke kvalitete neovisno o različitim uvjetima osvjetljenja. Iz tog se razloga koriste slike u bliskom infracrvenom području umjesto slika u vidljivom spektru. Kako bi se dobile visokokvalitetne slike u infracrvenom području, predstavljeno je brzo automatsko upravljanje svjetlinom aproksimativne regije lica na slici. Implementiran je novi algoritam za aproksimativnu detekciju regije lica temeljen na vremensko-prostornoj detekciji pomoću uzorkovane segmentacije kože zajedno podijeljenom regulacijom uz mogućnost rada bez prisustva lica. Predloženi algoritam je precizan, brz i pogodan za izvedbu u stvarnom vremenu na ugradbenim računalnim sustavima.

• Keywords: near-infrared images; automatic brightness control; face region detection; split range feedback control; skin detection; embedded systems; real-time image processing
• Keywords (croatian): slike u bliskom infracrvenom području; automatsko upravljanje svjetlinom; detekcija regije lica; upravljanje razdvojenog područja; detekcija kože; ugradbeni računalni sustavi; obrada slike u stvarnom vremenu
• Language: english
• URN:NBN: urn:nbn:hr:168:316231
• Promotion: 2024
• Study programme: Title: Doctoral study programme "Electrical Engineering and Computing"; Study programme type: university; Study level: postgraduate; Academic / professional title: doktor/doktorica znanosti, po-dručje tehničkih znanosti (doktor/doktorica znanosti, po-dručje tehničkih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Repository: FER Repository
• Created on: 2024-04-03 11:12:59