Impact of the face registration techniques on facial expressions recognition

Allaert, Benjamin; Mennesson, José; Bilasco, Ioan Marius; Djeraba, Chabane

doi:10.1016/j.image.2017.11.002

Cited by 20 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The important global head motions overcome the local motion characterizing facial expressions. Specific pre-processing steps as those illustrated in [47] are required in order to address challenges brought by large head movements.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Micro and Macro Facial Expression Recognition Using Advanced Local Motion Patterns

Allaert

Bilasco

Djeraba

2022

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

In this paper, we develop a new method that recognizes facial expressions, on the basis of an innovative Local Motion Patterns (LMP) feature. The LMP feature analyzes locally the motion distribution in order to separate consistent mouvement patterns from noise. Indeed, facial motion extracted from the face is generally noisy and without specific processing, it can hardly cope with expression recognition requirements especially for micro-expressions. Direction and magnitude statistical profiles are jointly analyzed in order to filter out noise. This work presents three main contributions. The first one is the analysis of the face skin temporal elasticity and face deformations during expression. The second one is a unified approach for both macro and micro expression recognition leading the way to supporting a wide range of expression intensities. The third one is the step forward towards in-the-wild expression recognition, dealing with challenges such as various intensity and various expression activation patterns, illumination variations and small head pose variations. Our method outperforms state-of-the-art methods for micro expression recognition and positions itself among top-ranked state-of-the-art methods for macro expression recognition.

show abstract

Section: Resultsmentioning

confidence: 99%

“…However, we believe that the registration based on facial components or shape are not adapted to dynamic approaches. Such registrations cause facial deformations and induce noisy motion [47]. We believe that suitable relationship between motion representation and registration is the key for expression recognition in presence of head movements.…”

Section: Resultsmentioning

confidence: 99%

Micro and Macro Facial Expression Recognition Using Advanced Local Motion Patterns

Allaert

Bilasco

Djeraba

2022

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

show abstract

“…Usually a distorted face is registered into a frontal view face before feature extraction. The amount of LD and HPV as well as the face registration techniques have an impact on facial expression recognition [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

Feature Selection on 2D and 3D Geometric Features to Improve Facial Expression Recognition

Perez-Gomez

Ríos-Figueroa

Rechy-Ramirez

et al. 2020

Sensors

View full text Add to dashboard Cite

An essential aspect in the interaction between people and computers is the recognition of facial expressions. A key issue in this process is to select relevant features to classify facial expressions accurately. This study examines the selection of optimal geometric features to classify six basic facial expressions: happiness, sadness, surprise, fear, anger, and disgust. Inspired by the Facial Action Coding System (FACS) and the Moving Picture Experts Group 4th standard (MPEG-4), an initial set of 89 features was proposed. These features are normalized distances and angles in 2D and 3D computed from 22 facial landmarks. To select a minimum set of features with the maximum classification accuracy, two selection methods and four classifiers were tested. The first selection method, principal component analysis (PCA), obtained 39 features. The second selection method, a genetic algorithm (GA), obtained 47 features. The experiments ran on the Bosphorus and UIVBFED data sets with 86.62% and 93.92% median accuracy, respectively. Our main finding is that the reduced feature set obtained by the GA is the smallest in comparison with other methods of comparable accuracy. This has implications in reducing the time of recognition.

show abstract

“…global region) and features are extracted from this region. There are variety of methods available for feature extraction for local as well as global region and called as local features (model based methods) [4]- [5] and global features (appearance based methods) [6] respectively. Some of the popularly used methods for local feature extraction are LDN -Local directional number, LBPlocal binary pattern, HOG -Histogram of gradients, geometric features etc.…”

Section: Introductionmentioning

confidence: 99%

Facial Features Based Hybrid Methods for Emotion Recognition

2019

IJRTE

View full text Add to dashboard Cite

Effective human machine interaction systems are need of the time so the work carried out deals with one of such significant HMI tasks- automatic emotion recognition. The experimentation carried out for this study is focused to facial expressions based emotion recognition. Two techniques of emotion recognition based on hybrid features are designed and experimented using JAFFE database. The first technique referred as "Hybrid Method1" is designed around feature descriptor obtained through local directional number & principal component analysis and feed forward neural network used as classifier. The second technique referred as "Hybrid Method 2" is designed around feature descriptor obtained through histogram of oriented gradients, local binary pattern and Gabor filters. PCA- principal component analysis is used for dimensionality reduction of feature descriptor and k-nearest neighbors as classifier. The average emotion recognition accuracy achieved through method 1 and method 2 is 85.24% and 93.86% respectively. Effectiveness of both the techniques is compared on the basis of performance parameters such as accuracy, false positive rate, false negative rate and emotion recognition time. Emotion recognition has wide application areas so the work carried out can be applied for suitable application development.

show abstract

Impact of the face registration techniques on facial expressions recognition

Abstract: International audienc

Cited by 20 publications

References 19 publications

Micro and Macro Facial Expression Recognition Using Advanced Local Motion Patterns

Micro and Macro Facial Expression Recognition Using Advanced Local Motion Patterns

Feature Selection on 2D and 3D Geometric Features to Improve Facial Expression Recognition

Facial Features Based Hybrid Methods for Emotion Recognition

Contact Info

Product

Resources

About