A Survey on Facial Expression Recognition using Machine Learning Techniques

Dixit, Anjali; Kasbe, Tanmay

doi:10.1109/idea49133.2020.9170706

Cited by 11 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to being able to identify faces that cannot be seen in visible light, thermal infrared face recognition can also identify the facial blood vessel structure. It reviews earlier studies on temperature variations, mathematical equations, wave types, and techniques for thermal infrared face recognition [3]. A new area of machine learning (ML) research is deep learning.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Human Face and Facial Expression Recognition Using Deep Learning and SNet Architecture Integrated with BottleNeck Attention Module

Sundaram¹,

Narayanan²

2023

View full text Add to dashboard Cite

Thermal infrared face image recognition with the help of deep learning technology has become the most debated concept in research area nowadays. Many articles are done and being working on this area to discover novel findings. Thermal infrared images can be recognised irrespective of light conditions, aging and facial disguises. This paper proposes a method named SNet integrated with BottleNeck Attention Module (SN-BNAM) for thermal face image recognition using SENet architecture in which the BottleNeck Attention Module is integrated. After squeeze and excitation process, the channel and spatial attention is inferred as two separate branches inside the BottleNeck Attention Module (BAM). This module is placed at each BottleNeck area. The SN-BNAM module can be integrated with any feed forward convolutional neural networks. The efficiency of the proposed system is evaluated by experimenting on various architectures and object validation is done on VOC 2007, MS COCO, CIFAR-100 and ImageNet-1K datasets. These experiments proves that our method shows consistent improvement in image classification and object detection.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…The thermal images are captured between the wavelengths 8μm to 12μm [2]. Human thermal faces images are created by the heat patterns that are emitted from the body and these images are autonomous of the environmental lighting conditions [3].…”

Section: Introductionmentioning

confidence: 99%

Human Face and Facial Expression Recognition Using Deep Learning and SNet Architecture Integrated with BottleNeck Attention Module

Sundaram¹,

Narayanan²

2023

View full text Add to dashboard Cite

show abstract

“…The OneR algorithm is stands for "One Rule," is an easy-to-understand, a precise classification technique that first formulates a rule for each predictor in the data before selecting the rule with the minimum overall error as its "one rule" and only allows level one decision trees [30]. The One Rule algorithm has a single parameter, which is the threshold for the minimum frequency of an attribute value.…”

Section: One Rule (Oner) Algorithmmentioning

confidence: 99%

“…This algorithm generates the rules from which the particular identity of that data is generated. The goal is to gradually generalize a decision tree until it achieves balance between flexibility and accuracy [30]. J48 has several default parameters that can be adjusted to optimize its performance which are: confidence factor that controls the degree of pruning, minimum number of instances, binary splits specify whether the algorithm should use binary splits or multiway splits, and subtree raising specify whether the algorithm should raise the subtree of a pruned node to replace the pruned node [23], [30].…”

Section: J48 Decision Tree Algorithmmentioning

confidence: 99%

Efficient Iris Image Recognition System Based on Machine Learning Approach

2023

IJCCCE

View full text Add to dashboard Cite

Iris identification is a well‐known technology used to detect striking biometric identification techniques for recognizing human beings based on physical behavior. The texture of the iris is essential and its anatomy varies from individual to individual. Humans have distinctive physical characteristics that never change. This has resulted in a considerable advancement in the field of iris identification, which inherits the random variation of the data and is often a dependable technological area. This research proposes three algorithms to examine the classifications in machine learning approaches using feature extraction for the iris image. The applied recognition system used many methods to enhance the input images for iris recognition using the Multimedia University (MMU) database. Linear Discriminant Analysis (LDA) feature extraction method is applied as an input of three algorithms of machine learning approaches that are OneR, J48, and JRip classifiers. The result indicates that the OneR classifier with LDA achieves the highest performance with 94.387 % accuracy, while J48 and JRip reached to 90.151% and 86.885% respectively. Index Terms— Iris recognition, LDA, OneR, J48, JRip.

show abstract

“…FER is defined as a technique of defining the mental state of humans by evaluating the motion or position of facial components such as blinking of eyes, expansion or contraction of eyelids, movement of lips, skewed eyebrows, and creasing nose. The expression on the face relies on skeptical things like the movement of facial muscles, surroundings, and mind condition [2]. Human facial expression is generally divided into seven categories i.e., anger, disgust, fear, happiness, surprise, sadness, and neutral [3].…”

Section: Introductionmentioning

confidence: 99%

Efficient-SwishNet Based System for Facial Emotion Recognition

et al. 2022

View full text Add to dashboard Cite

Facial emotion recognition (FER) is an important research area in artificial intelligence and has many applications i.e., face authentication systems, e-learning, entertainment, deepfakes detection, etc. FER is still a challenging task due to more intra-class variations of emotions. Although existing deep learning methods have achieved good performance for FER. However, still there exists a need to develop efficient and effective FER systems robust to certain conditions i.e., variations in illumination, face angles, gender, race, background settings and people belonging to diverse geographical regions. Moreover, a generalized model for classification of human emotions is required to be implemented in computer systems so that they can interact with humans according to their emotions and improve their interaction. This work presents a novel light-weight Efficient-SwishNet model for emotion recognition that is robust towards the aforementioned conditions. We have introduced a low-cost, smooth unbounded above and bounded below Swish activation function in our model. Property of unboundedness helps to avoid saturation while smoothing helps in optimization and generalization of the model. Performance of the proposed model is evaluated on five diverse datasets including CK+, JAFFE, FER-2013, KDEF and FERG datasets. We also performed cross-corpora evaluation to show the generalizability of our model. The proposed model achieves very high recognition rate for all datasets that proves the merit of the proposed framework for both the human facial images and stylized cartoon characters. Moreover, we conducted an ablation study with different variants of our model to prove its efficiency and effectiveness for emotions identification.

show abstract

A Survey on Facial Expression Recognition using Machine Learning Techniques

Cited by 11 publications

References 29 publications

Human Face and Facial Expression Recognition Using Deep Learning and SNet Architecture Integrated with BottleNeck Attention Module

Human Face and Facial Expression Recognition Using Deep Learning and SNet Architecture Integrated with BottleNeck Attention Module

Efficient Iris Image Recognition System Based on Machine Learning Approach

Efficient-SwishNet Based System for Facial Emotion Recognition

Contact Info

Product

Resources

About