Effective face detection, feature extraction &amp; neural network based approaches for facial expression recognition

Muttu, Yeshudas; Virani, H. G.

doi:10.1109/infop.2015.7489359

Cited by 19 publications

(4 citation statements)

References 5 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It describes the process used to detect the face, preprocessing involved in the approach, the feature extraction approach, the classifiers used for emotion classification, and the reported accuracy. The most common classifier used for emotion detection are decision tree [13][14][15], SVM [24][25][26][27][28][29] and neural networks [23,30]. SVM is very effective in terms of memory management and dimensionality.…”

Section: Related Workmentioning

confidence: 99%

Emotion Detection Using Facial Expression Involving Occlusions and Tilt

et al. 2022

View full text Add to dashboard Cite

Facial emotion recognition (FER) is an important and developing topic of research in the field of pattern recognition. The effective application of facial emotion analysis is gaining popularity in surveillance footage, expression analysis, activity recognition, home automation, computer games, stress treatment, patient observation, depression, psychoanalysis, and robotics. Robot interfaces, emotion-aware smart agent systems, and efficient human–computer interaction all benefit greatly from facial expression recognition. This has garnered attention as a key prospect in recent years. However, due to shortcomings in the presence of occlusions, fluctuations in lighting, and changes in physical appearance, research on emotion recognition has to be improved. This paper proposes a new architecture design of a convolutional neural network (CNN) for the FER system and contains five convolution layers, one fully connected layer with rectified linear unit activation function, and a SoftMax layer. Additionally, the feature map enhancement is applied to accomplish a higher detection rate and higher precision. Lastly, an application is developed that mitigates the effects of the aforementioned problems and can identify the basic expressions of human emotions, such as joy, grief, surprise, fear, contempt, anger, etc. Results indicate that the proposed CNN achieves 92.66% accuracy with mixed datasets, while the accuracy for the cross dataset is 94.94%.

show abstract

Section: Related Workmentioning

confidence: 99%

Emotion Detection Using Facial Expression Involving Occlusions and Tilt

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Recently, a significant improvement has been made by researchers in developing expression classifiers [25], [26], [27]. Many deep learning techniques which function on data representing symbols, such as Convolutional Neural Networks (CNNs) have been developed in order to acquire better facial expression representation.…”

Section: Related Workmentioning

confidence: 99%

Untitled

2020

IJGCA

View full text Add to dashboard Cite

This paper proposes the design of a Facial Expression Recognition (FER) system based on deep convolutional neural network by using three model. In this work, a simple solution for facial expression recognition that uses a combination of algorithms for face detection, feature extraction and classification is discussed. The proposed method uses CNN models with SVM classifier and evaluates them, these models are Alex-net model, VGG-16 model and Res-Net model. Experiments are carried out on the Extended Cohn-Kanada (CK+) datasets to determine the recognition accuracy for the proposed FER system. In this study the accuracy of AlexNet model compared with Vgg16 model and ResNet model. The result show that AlexNet model achieved the best accuracy (88.2%) compared to other models.

show abstract

“…Yeshudas Muttu et al [8] have utilized Viola -Jones algorithm to the collect the required information from the input image. Face features such as eye, mouth, nose and eye brows are considered for extraction of facial features.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Approach for Facial Expression Recognition using HJDLBP and LBP Histogram in Video Sequences

Nagaral¹,

Reddy²

2018

IJIGSP

View full text Add to dashboard Cite

Any kind of compassionate thoughts can't be expressed through words, but it appears on their facial expression. So, the facial expression reveals the emotions of individuals. The recognition of such emotions can be understood correctly or sometimes ambiguously from the opponent. Hence, there is a scope for automatic facial expression recognition (FER) in the context of image processing. The FER system has three different phases: face detection, feature extraction and expression classification. In face detection phase, Viola Jones face detector is used to crop the original image such that only the face region is retained by removing the unwanted region. In feature extraction stage, High-order Joint Derivative Local Binary Pattern (HJDLBP) and Local Binary Pattern (LBP) histogram algorithms are used for extracting features from the cropped image. In last stage, Support Vector machine (SVM) classifier is used in finding the precise facial expression.CK+ dataset has been used for training and testing, which consist of 442 image samples. We have considered six different universal possible expressions such as, happy, anger, disgust, fear, surprised, and sad for identification. The experimental results indicate that the overall accuracy of the proposed system was 74.8%, which is high compare to the results available in literature.

show abstract

Effective face detection, feature extraction & neural network based approaches for facial expression recognition

Cited by 19 publications

References 5 publications

Emotion Detection Using Facial Expression Involving Occlusions and Tilt

Emotion Detection Using Facial Expression Involving Occlusions and Tilt

Untitled

Hybrid Approach for Facial Expression Recognition using HJDLBP and LBP Histogram in Video Sequences

Contact Info

Product

Resources

About