Facial landmark localization: Past, present and future

Ouanan, Hamid; Ouanan, Mohammed; Aksasse, Brahim

doi:10.1109/cist.2016.7805097

Cited by 21 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Facial landmarks are a relatively new method to determine interest points in a person's face, and this method manages to not only locate the face with precision but also necessary interest points for determining many aspects of a human face [22]. In this study, a detector with 68 markups had been used as shown in Fig.…”

Section: Finding Facementioning

confidence: 99%

Easymatch- An Eye Localization Method for Frontal Face Images Using Facial Landmarks

Colak

Varol

2020

Teh. vjesn.

View full text Add to dashboard Cite

Eye detection algorithms are being used in many fields such as camera applications for entertainment and commercial purposes, gaze detection applications, computer-human interaction applications, and eye recognition applications for security, etc. Successful and fast eye detection is an essential step for all these applications in order to achieve good results. There are many eye detection methods in the literature, and most of them rely on the Viola-Jones method to detect the face before localizing eyes. In this paper, a straightforward approach to detect eyes from images which contain a frontal face is proposed. The approach can be used for real-time eye detection using cheap web cameras or other cameras. First, face landmarks are detected from the image, and by utilizing these landmarks; the eye region is determined. The eye radius is estimated by utilizing eye corners. Then, reduced input images are tested with a tailored matching algorithm which does not need image reduction to determine where the eye is.

show abstract

Section: Finding Facementioning

confidence: 99%

Easymatch- An Eye Localization Method for Frontal Face Images Using Facial Landmarks

Colak

Varol

2020

Teh. vjesn.

View full text Add to dashboard Cite

show abstract

“…In contrast to previous work [16], [19]- [21], we perform harmonic/percussive separation to reduce noise in audio samples [23]. Furthermore, since facial landmark localization is sensitive to resolution, occlusion, illumination, and background [24], [25], we propose robust visual features using a Convolutional Neural Network (CNN). Our contributions are as follows (1) we present an audio emotion recognition module using pitch, energy, zero-crossing rates (ZCR), entropy and Mel Frequency cepstral coefficients (MFCCs) based on percussive and harmonic separation; (2) we create a video emotion recognition module extracting robust image features through transfer learning based on VGG16;…”

Section: Related Workmentioning

confidence: 99%

Real-time Emotion Recognition for Sales

Naas

Sigg

2020

2020 16th International Conference on Mobility, Sensing and Networking (MSN)

View full text Add to dashboard Cite

Positive emotion is a pre-condition to any sales contract. Likewise, the ability to perceive the emotions of a customer impacts sales performance.To support emotional perception in buyer-seller interactions, we propose an audio-visual emotion recognition system that can recognize eight emotions: neutral, calm, sad, happy, angry, fearful, surprised, and disgusted. We reduced noise in audio samples and we applied transfer learning for image feature extraction based on a pre-trained deep neural network VGG16. For emotion recognition, we successfully obtained an audio emotion-recognition accuracy of 62.51% and 68% and video emotion-recognition accuracy of 97.13% and 97.77% on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and Surrey Audio-Visual Expressed Emotion (SAVEE) datasets respectively. For the combination of the two models, our proposed merging mechanism without re-training achieved an accuracy of close to 100% on both datasets. Finally, we demonstrated our system for a customer satisfaction use case in a real customer-to-salesperson interaction using audio and video models, achieving an average accuracy of 78%.

show abstract

“…Las partes de referencia generalmente usadas son los ojos, la boca, la nariz, las cejas, el mentón y los bordes del rostro (Ouanan, Ouanan y Aksasse, 2016).…”

Section: Facial Landmarksunclassified

“…Entre las diversas aplicaciones se encuentran la compresión de la expresión, el registro facial, el reconocimiento facial y el seguimiento facial, como también la utilizada para la reconstrucción de modelos de rostros en 3D (Ouanan et al, 2016). Para poder determinar estos puntos característicos del rostro, es necesario el uso de algoritmos que permitan localizarlos.…”

Section: Interfasesunclassified

“…Para poder determinar estos puntos característicos del rostro, es necesario el uso de algoritmos que permitan localizarlos. A pesar de las investigaciones realizadas hasta la fecha, la localización de estos puntos es un tema desafiante, considerando entre los principales obstáculos la variabilidad, debido a factores intrínsecos, como por ejemplo la variación de las caras entre los individuos, y a valores extrínsecos, como la oclusión, la iluminación y la resolución de la imagen (Ouanan et al, 2016).…”

Section: Interfasesunclassified

See 1 more Smart Citation

Sistema de reconocimiento de gestos faciales captados a traves de camaras para analizar el nivel de satisfaccion de clientes en restaurantes

Lara-Lévano

2019

Interfases

View full text Add to dashboard Cite

Camera-based facial expression recognition system to analyze customer satisfaction level in a restaurant The main objective of this research is to develop a system that recognizes customers' satisfaction or dissatisfaction in a restaurant based on their facial expressions when receiving the service provided by the establishment. The implementation of the system has a series of stages common to the development of a visual computing project, which will begin with data preprocessing to train the classifier to be used in this case: a support vector machine. This data preprocessing uses the histogram of oriented gradients for detecting a face inside an image, so that only the face outline is cut. In this way, facial landmarks of the image are extracted, the probability that each of the basic feelings appears in the facial expression of people is established, and, based on these probabilities, customers' satisfaction or dissatisfaction is determined. The results show that the system correctly detected most of the images entered for the tests; however, there were some cases in which, despite the fact that customers were satisfied, they showed certain dissatisfaction expressions caused by external factors.

show abstract

Facial landmark localization: Past, present and future

Cited by 21 publications

References 37 publications

Easymatch- An Eye Localization Method for Frontal Face Images Using Facial Landmarks

Easymatch- An Eye Localization Method for Frontal Face Images Using Facial Landmarks

Real-time Emotion Recognition for Sales

Sistema de reconocimiento de gestos faciales captados a traves de camaras para analizar el nivel de satisfaccion de clientes en restaurantes

Contact Info

Product

Resources

About