The Recognition of Basic Facial Expressions by Neural Network

Kobayashi, Hiroshi; Hara, Fumio

doi:10.9746/sicetr1965.29.112

Cited by 33 publications

(16 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have also been a number of automated facialaffect-detection systems that have been developed for assistive HRI scenarios but that have not yet been implemented and tested on robotic platforms [57,59]. One of the earlier works can be found in [57], where a human affect-recognition system was developed for the purpose of robots carrying out intelligent conversations and for the application of better living.…”

Section: Assistive Hrimentioning

confidence: 98%

“…One of the earlier works can be found in [57], where a human affect-recognition system was developed for the purpose of robots carrying out intelligent conversations and for the application of better living. 60 feature points from the eyebrows, eyes, and mouth were obtained from images provided by a CCD camera.…”

Section: Assistive Hrimentioning

confidence: 99%

“…A number of HRI studies have incorporated the use of affect classification using categorical emotional models for facial expressions [57][58][59][60], body language [61][62][63][64], voice [7,19,[65][66][67][68][69], physiological signals [70][71][72], and multi-modal systems [73,74]. These models allow robots to interpret affective states in a similar manner as humans [75].…”

Section: Affect Models Used In Hrimentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Autonomous Human Affect Detection Methods for Social Robots Engaged in Natural HRI

McColl

Hong

Hatakeyama

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

In Human-Robot Interactions (HRI), robots should be socially intelligent. They should be able to respond appropriately to human affective and social cues in order to effectively engage in bi-directional communications. Social intelligence would allow a robot to relate to, understand, and interact and share information with people in real-world humancentered environments. This survey paper presents an encompassing review of existing automated affect recognition and classification systems for social robots engaged in various HRI settings. Human-affect detection from facial expressions, body language, voice, and physiological signals are investigated, as well as from a combination of the aforementioned modes. The automated systems are described by their corresponding robotic and HRI applications, the sensors they employ, and the feature detection techniques and affect classification strategies utilized. This paper also discusses pertinent future research directions for promoting the development of socially intelligent robots capable of recognizing, classifying and responding to human affective states during real-time HRI.

show abstract

Section: Assistive Hrimentioning

confidence: 98%

Section: Assistive Hrimentioning

confidence: 99%

Section: Affect Models Used In Hrimentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Autonomous Human Affect Detection Methods for Social Robots Engaged in Natural HRI

McColl

Hong

Hatakeyama

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…A classification accuracy of 86% was achieved in this study. Hara and Kobayashi [8,9] also used neural networks approach. The training dataset consisted of from data of 15 subjects (90 images) and these networks were tested using data from another 15 subjects.…”

Section: Introductionmentioning

confidence: 99%

“…The FER system can be applied in different areas of life such security and surveillance, they can predict the offender or criminal"s behavior by analyzing the images of their faces that are captured by the control-camcorder. Furthermore, the FER system has been used in communication to make the "answer machine" more interactive with people.FER has attracted Padgett [7], Hara and Kobayashi [8,9], Zhang [10] and Zhao [11] used neural network approach for expression classification. They classified images into six or seven emotional categories.…”

Section: Introductionmentioning

confidence: 99%

Facial Image based Emotion Recognition System using Neural Network

Dudul¹,

Tayade²,

Talele³

2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Facial emotion plays a vital role for human interactive communication and also used in numerous real applications. Facial expression identification from frontal still images has in recent times become a hopeful investigation area. Their applications include human-computer interface, human emotion examination robot control, driver state surveillance and medical fields. This paper aims to develop emotion classification scheme to identify seven dissimilar facial emotions, such as surprise, sad, neutral, happy, fear, disgust and anger by using JAFFE database. Two different approaches of feature selection and extraction have been used for generation of optimal feature vector. LBP and 2D-DCT coefficients are employed in addition to image statistics, texture and entropy parameters. In order to reduce the high dimensionality of the inputs, the principal component analysis has been used and significant reduction in the input-dimensionality has been achieved. The single hidden layer feed forward neural network has been used as a classifier in order to classify different emotions from frontal facial images. Three learning algorithms such as resilient backpropagation, scaled conjugate gradient and gradient descent algorithm with momentum and adaptive learning rate have been compared. It has been observed that our meticulously designed LBP based hybrid feature vector and a single hidden layer neural network containing only 70 neurons in the hidden layer trained with gradient descent algorithm with momentum and adaptive learning rate delivers the maximum average overall classification accuracy of 97.2%, which has not been reported so far in the literature for the said database. The proposed neural network is very compact, as it is comprised of only 5,607 connection weights including biases.

show abstract