I Know How You Feel: Emotion Recognition with Facial Landmarks

Tautkute, Ivona; Trzciński, Tomasz Piotr; Bielski, Adam

doi:10.1109/cvprw.2018.00246

Cited by 35 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we overview extension of our previous method [29] for emotion recognition that allows to exploit facial landmarks. Although the results computed on the JAFFE dataset show that there is still Figure 6.…”

Section: Resultsmentioning

confidence: 99%

Classifying and Visualizing Emotions with Emotional DAN

Tautkute

Trzciński

2019

View full text Add to dashboard Cite

Classification of human emotions remains an important and challenging task for many computer vision algorithms, especially in the era of humanoid robots which coexist with humans in their everyday life. Currently proposed methods for emotion recognition solve this task using multi-layered convolutional networks that do not explicitly infer any facial features in the classification phase. In this work, we postulate a fundamentally different approach to solve emotion recognition task that relies on incorporating facial landmarks as a part of the classification loss function. To that end, we extend a recently proposed Deep Alignment Network (DAN) with a term related to facial features. Thanks to this simple modification, our model called Emotion-alDAN is able to outperform state-of-the-art emotion classification methods on two challenging benchmark dataset by up to 5%. Furthermore, we visualize image regions analyzed by the network when making a decision and the results indicate that our EmotionalDAN model is able to correctly identify facial landmarks responsible for expressing the emotions.

show abstract

Section: Resultsmentioning

confidence: 99%

Classifying and Visualizing Emotions with Emotional DAN

Tautkute

Trzciński

2019

View full text Add to dashboard Cite

show abstract

“…Facial landmark point is also one of the typical geometric feature. [16], [17] and [18] use facial landmarks as geometric feature of their networks. Hasani et al [9] additionally utilize landmarks to emphasis the difference between the importance of main facial components and other parts of the face which are less expressive of facial expressions.…”

Section: Temporal Geometric Networkmentioning

confidence: 99%

Real-time Facial Expression Recognition using 3D Appearance and Geometric Network for Public Security

Kim¹

2020

J. Def. Acquis. Technol.

View full text Add to dashboard Cite

Facial expression recognition is a promising technology that can be used in various fields of artificial intelligence. There are several challenges to deal this task, one of which is recognizing a facial expression in sequential input data for real-time recognition. Many types of convolutional neural networks have been proposed to consider temporal information together. Typically, there are appearance networks that utilize facial appearance information, geometric networks that use facial landmark points, and hybrid approaches that combined these two networks. In this paper, we compare various methods proposed so far and identify the best approach for each network. We also have an experiment the initial architecture of our proposed 3D appearance and geometric network based on these researches and validate that its 97.22% accuracy on CK+ dataset is comparable to state-of-the-art techniques.

show abstract

“…The studies in references [3,[5][6][7] classified six universal emotions as happiness, angry, sadness, surprise, fear, and disgust. In [9, 13,15,[23][24] have classified one more class as neutral and [8,17,23] have done contempt class. All of eight classes have been classified by the studies in [11,10,16].…”

Section: Introductionmentioning

confidence: 99%

Feature extraction and classification methods of facial expression: a survey

Htay

2021

Comput. Sci. Inf. Technol.

View full text Add to dashboard Cite

Facial Expression is a significant role in affective computing and one of the non-verbal communication for human computer interaction. Automatic recognition of human affects has become more challenging and interesting problem in recent years. Facial Expression is the significant features to recognize the human emotion in human daily life. Facial Expression Recognition System (FERS) can be developed for the application of human affect analysis, health care assessment, distance learning, driver fatigue detection and human computer interaction. Basically, there are three main components to recognize the human facial expression. They are face or face’s components detection, feature extraction of face image, classification of expression. The study proposed the methods of feature extraction and classification for FER.

show abstract

I Know How You Feel: Emotion Recognition with Facial Landmarks

Cited by 35 publications

References 12 publications

Classifying and Visualizing Emotions with Emotional DAN

Classifying and Visualizing Emotions with Emotional DAN

Real-time Facial Expression Recognition using 3D Appearance and Geometric Network for Public Security

Feature extraction and classification methods of facial expression: a survey

Contact Info

Product

Resources

About