Facial Emotion Recognition Using HOG and Convolution Neural Network

Ghalib, Raghad; Ibrahim, Abdul-Wahab Sami; Noor, Ameen A.

doi:10.18280/isi.280118

Cited by 5 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When noise levels varied, some existing methods for emotion recognition did not perform as well as the dual feature fusion method [39]. HOG and CNN [40] are combinedly used in detecting facial emotions. When HOG and SVM were employed to extract the features of facial expressions and the emotions were classified using ALEXNET, the results improved [41].…”

Section: Related Workmentioning

confidence: 99%

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Anji Reddy,

Regula,

Sharmila

et al. 2023

ISI

View full text Add to dashboard Cite

The human face serves as a potent biological medium for expressing emotions, and the capability to interpret these expressions has been fundamental to human interaction since time immemorial. Consequently, the extraction of emotions from facial expressions in images, using machine learning, presents an intriguing yet challenging avenue. Over the past few years, advancements in artificial intelligence have significantly contributed to the field, replicating aspects of human intelligence. This paper proposes a Facial Emotion Recognition Convolutional Neural Network (FERCNN) model, addressing the limitations in accurately processing raw input images, as evidenced in the literature. A notable improvement in performance is observed when the input image is injected with noise prior to training and validation. Gaussian, Poisson, Speckle, and Salt & Pepper noise types are utilized in this noise injection process. The proposed model exhibits superior results compared to well-established CNN architectures, including VGG16, VGG19, Xception, and Resnet50. Not only does the proposed model demonstrate greater performance, but it also reduces training costs compared to models trained without noise injection at the input level. The FER2013 and JAFFE datasets, comprising seven different emotions (happy, angry, neutral, fear, disgust, sad, and surprise) and totaling 39,387 images, are used for training and testing. All experimental procedures are conducted via the Kaggle cloud infrastructure. When Gaussian, Poisson, and Speckle noise are introduced at the input level, the suggested CNN model yields evaluation accuracies of 92.17%, 95.07%, and 92.41%, respectively. In contrast, the highest accuracies achieved by existing models such as VGG16, VGG19, and Resnet 50 are 45.97%, 63.97%, and 54.52%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Anji Reddy,

Regula,

Sharmila

et al. 2023

ISI

View full text Add to dashboard Cite

show abstract

“…In this study, scales have been meticulously chosen to align with the objectives of the research, ensuring a comprehensive and lucid insight into both the strengths and limitations of the model. To this end, the following formulae are employed to calculate the performance metrics, namely accuracy, precision, recall, and F1-score [17,18]:…”

Section: Evaluation Metricsmentioning

confidence: 99%

Abnormal Behavior Detection in Gait Analysis Using Convolutional Neural Networks

Alhuseen,

Joda,

Naser

2023

ISI

View full text Add to dashboard Cite

The focus of this study encompasses the burgeoning field of abnormal behavior detection through computer vision, with a specific emphasis on gait analysis. A foundational gait model has been constructed, deriving from an extensive analysis of various gait types. The research endeavors to establish a model capable of discerning individual abnormal behavior, predicated on their walking patterns. A meticulous evaluation and comparison of three predominant feature extraction methodologies-Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP), and Center Symmetric Local Binary Pattern (CS-LBP)-constitute the core of this study. These techniques have been selected owing to their prevalent application and validated efficacy across numerous computer vision domains. Following feature extraction, the classification stage is initiated, utilizing Convolutional Neural Networks (CNNs), a paradigm of deep learning algorithms. The methodology has undergone rigorous testing and evaluation on a comprehensive dataset, inclusive of both standard and aberrant behavioral instances. A high performance level, signified by a 99% accuracy rate, was achieved through the application of the CS-LBP method for abnormal behavior detection. The empirical results underscore the significance of gait feature extraction methods in augmenting the system's proficiency in anomaly detection.

show abstract

“…But, it is difficult to capture the temporal features from the video-sequences, and also it is highly required to encode the input videosequences for recognition. So, the majority of the application system could use the image-based recognition systems [8][9][10]. Numerous facial expression recognition algorithms have been investigated in the fields of computer vision and International Journal of Intelligent Engineering and Systems, Vol.…”

Section: Introductionmentioning

confidence: 99%

A Systematic Pelican Optimization based Weight Extreme Learning Machine Algorithm for Face Emotion Recognition

2023

IJIES

View full text Add to dashboard Cite

Recognizing the facial expressions from the given input is one of the challenging and demanding tasks in recent days owing to the low-resolution images and different backgrounds. Also, the facial emotional/expression recognition system has gained a significant attention in the field of computer vision. The conventional works implemented a variety of machine learning algorithms for face emotion recognition, but higher computation costs, decreased reliability, redundant information, and increased computational time requirement are still only a few of the issues. In this case, an image face filtering method is employed in the beginning to produce a normalized output image with high contrast and quality, which is used to increase the classifier's overall rate of emotion recognition. Then, the novel pelican optimization algorithm (POA) is used to optimize the feature set in order to guarantee the success of classifier training and testing. Prior to emotion recognition, this technique is used to reduce the dimensionality of information. Based on the given face image's optimized attributes, the weight optimized extreme learning machine (WOELM) algorithm is used to reliably identify the emotions. By using well-known datasets like CK+ and MMI, a wide range of factors are taken into consideration for study in order to compare and evaluate the outcomes of the proposed POA-WOELM face emotion identification system. The obtained results reveal that the combination of POA-WOELM provides an increased 99% of emotion recognition accuracy to all kinds of emotions, with the sensitivity of 98.8% and specificity of 98.9%.

show abstract

Facial Emotion Recognition Using HOG and Convolution Neural Network

Cited by 5 publications

References 27 publications

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Performance Enhancement in Facial Emotion Classification Through Noise-Injected FERCNN Model: A Comparative Analysis

Abnormal Behavior Detection in Gait Analysis Using Convolutional Neural Networks

A Systematic Pelican Optimization based Weight Extreme Learning Machine Algorithm for Face Emotion Recognition

Contact Info

Product

Resources

About