Mouth Features Extraction for Emotion Analysis

Robert, Staniucha; Wojciechowski, Adam

doi:10.1007/978-3-319-48429-7_21

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first one, the signal features extraction, producing the most valuable data that can be further processed in the second stage. This stage can be carried out by methods such as common spatial pattern (CSP), extreme energy ratio (ERR), autoregressive (AR) parameters, wavelet packet transform (WPT) (Sun and Zhou, 2014)(Lipiński, 2011), principal component analysis (PCA) (Agarwal et al , 2015)(Staniucha and Wojciechowski, 2016) or hidden Markov model (HMM) (Nasehi and Pourghassem, 2013). Methods of this stage are subject to further improvement but, in our work, we do not focus on this area; thus, we interpret raw signal, appropriately divided into time windows, without additional preprocessing.…”

Section: Related Workmentioning

confidence: 99%

LSTM multichannel neural networks in mental task classification

Opałka

Szajerman

Wojciechowski

2019

COMPEL

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this paper is to apply recurrent neural networks (RNNs) and more specifically long-short term memory (LSTM)-based ones for mental task classification in terms of BCI systems. The authors have introduced novel LSTM-based multichannel architecture model which proved to be highly promising in other fields, yet was not used for mental tasks classification. Design/methodology/approach Validity of the multichannel LSTM-based solution was confronted with the results achieved by a non-multichannel state-of-the-art solutions on a well-recognized data set. Findings The results demonstrated evident advantage of the introduced method. The best of the provided variants outperformed most of the RNNs approaches and was comparable with the best state-of-the-art methods. Practical implications The approach presented in the manuscript enables more detailed investigation of the electroencephalography analysis methods, invaluable for BCI mental tasks classification. Originality/value The new approach to mental task classification, exploiting LSTM-based RNNs with multichannel architecture, operating on spatial features retrieving filters, has been adapted to mental tasks with noticeable results. To the best of the authors’ knowledge, such an approach was not present in the literature before.

show abstract

Section: Related Workmentioning

confidence: 99%

LSTM multichannel neural networks in mental task classification

Opałka

Szajerman

Wojciechowski

2019

COMPEL

Self Cite

View full text Add to dashboard Cite

show abstract

“…[18] and constrained local neural fields (CLNF) [24], claim to obtain higher precision of landmark detection, especially in strictly constrained, restricted environment (inconvenient light, partial face occlusion). Highly efficient local analysis may also base on gradient templates [29]. Face feature points, retrieved within face analysis, can be subsequently structured in a face or head reference model.…”

Section: Head Pose Estimation Methodsmentioning

confidence: 99%

“…It might be exploited in sociological children behaviour monitoring [4], [5], distant computer interface control [6], [31], crowdsourcing systems [7], [8] or in cognitive computation researches [9], [29]. Though very intuitively and naturally accomplished by humans, the problem of head pose estimation is still a challenging problem for current computer systems.…”

Section: Introductionmentioning

confidence: 99%

Robust face model based approach to head pose estimation

Fornalczyk

Wojciechowski

2017

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Abstract-Head pose estimation from camera images is a computational problem that may influence many sociological, cognitive, interaction and marketing researches. It is especially crucial in the process of visual gaze estimation which accuracy depends not only on eye region analysis, but head inferring as well. Presented method exploits a 3d head model for a user head pose estimation as it outperforms, in the context of performance, popular appearance based approaches and assures efficient face head pose analysis. The novelty of the presented approach lies in a default head model refinement according to the selected facial features localisation. The new method not only achieves very high precision (about 4• ), but iteratively improves the reference head model. The results of the head pose inferring experiments were verified with professional Vicon motion tracking system and head model refinement accuracy was verified with high precision Artec structural light scanner.

show abstract

Modeling Human Pupil Dilation to Decouple the Pupillary Light Reflex

Napieralski

Rynkiewicz

2019

Open Physics

View full text Add to dashboard Cite

The aim of this paper is to present methods to calculate pupil size based on various parameters, such as: luminance, age, corneal flux density or monocular/binocular effect. These models allow to distinguish pupil dilation caused by the influence of light and other factors such as psychological state of participants.The developed methods were presented based on empirical data. Various researchers estimate their equations based on oculographic data obtained in the course of experiments. The presented plots are based on those equations. Different approaches can be compared to show the difference between particular models.The methods presented in this paper enable a more detailed investigation of the influence of various parameters on the pupil. It can be used to better estimate the influence of light on pupil size. The main changes occurring in pupil size, i.e. contractions and dilation, are caused by light. Other criteria such emotional arousal, cognitive processes or even memory operations can also alter the pupil, among which the decoupling of light is important. The presented approach is distinct from other similar studies because it decouples the pupillary light reflex.

show abstract

Mouth Features Extraction for Emotion Analysis

Cited by 4 publications

References 25 publications

LSTM multichannel neural networks in mental task classification

LSTM multichannel neural networks in mental task classification

Robust face model based approach to head pose estimation

Modeling Human Pupil Dilation to Decouple the Pupillary Light Reflex

Contact Info

Product

Resources

About