Facial expression recognition phd thesis

Facial expression recognition phd thesis

Facial Analysis Models for Face and Facial Expression Recognition Munasinghe Kankanamge Sarasi Madushika BSc. Eng (Hons, 1st Class) PhD Thesis Submitted in Ful lment Aug 17,  · Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the blogger.com by: 4 14 rows · An atypical recognition of facial expressions of emotion is thought to be part of the

Development of Facial Expression Recognition System Using Machine Learning Techniques - ethesis

Zhang, Ligang Towards spontaneous facial expression recognition in real-world video. PhD thesis, Queensland University of Technology. Facial expression is an important channel of human social communication.

Facial expression recognition FER aims to perceive and understand emotional states of humans based facial expression recognition phd thesis information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information.

Facial expression recognition phd thesis variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies.

Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions.

The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets.

It comprises of contributions towards three main objectives: 1 Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions.

A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework facial expression recognition phd thesis evaluated for both discrete and dimensional expression recognition on spontaneous data.

A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames.

The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases, facial expression recognition phd thesis. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions.

Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, facial expression recognition phd thesis, as well as posed versus spontaneous emotion discrimination.

These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications. Citation counts are sourced monthly from Scopus and Web of Science® citation databases. These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different.

Some works are not in either database and no count is displayed. Scopus includes citations from articles published in onwards, and Web of Science® generally from onwards. The count includes downloads for all files if a work has more than one. Export: EndNote Dublin Core BibTeX. Repository Staff Only: item control page. QUT Home Contact. Home Browse About. Description Facial expression is an important channel of human social communication. Notify us of incorrect data How to use citation counts More information.

Full-text downloads: since deposited on 17 Aug More statistics Export: EndNote Dublin Core BibTeX Repository Staff Only: item control page. Home Browse research About. CRICOS No. Ligang Zhang Thesis PDF 4MB. facial expression recognition, texture, geometry, feature fusion, posed, spontaneous, discrete, dimensional, feature selection, active shape model, adaboost, minimal redundancy maximal relevance criterion, facial expression recognition phd thesis, support vector machine.

Train your own Neural Network for Facial expression recognition - TensorFlow, CNN, Keras, tutorial

, time: 35:11

Towards spontaneous facial expression recognition in real-world video | QUT ePrints

14 rows · An atypical recognition of facial expressions of emotion is thought to be part of the Facial Analysis Models for Face and Facial Expression Recognition Munasinghe Kankanamge Sarasi Madushika BSc. Eng (Hons, 1st Class) PhD Thesis Submitted in Ful lment Title of Thesis: FACIAL AND EXPRESSION RECOGNITION FOR THE BLIND USING COMPUTER VISION Authors: Douglas Astler, Harrison Chau, Kailin Hsu, Alvin Hua, Andrew Kannan, Lydia Lei, Melissa Nathanson, Esmaeel Paryavi, Michelle Rosen, Hayato Unno, Carol Wang, Khadija Zaidi, and Xuemin Zhang. Directed by: Professors Rama Chellappa and Cha-Min Tang