Multi-feature based automatic facial expression recognition using deep convolutional neural network

Dixit, Anjali; Kasbe, Tanmay

doi:10.11591/ijeecs.v25.i3.pp1406-1419

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gradient values of the central pixel are then contrasted with the gradient values of the predefined threshold. There are two sets in the convolution template, one at the level edge of detection and the other for the vertical edge of detection [21,[33][34][35]. Since it operates on the gradient expression and the f(x,y) twodimensional image function, it is presented as follows:…”

Section: Sobel Edge Detectionmentioning

confidence: 99%

Non-Invasive Machine Learning-Based Classification of Bone Health

Bhise¹,

Havaldar²

2022

View full text Add to dashboard Cite

Osteoporosis is a disease that affects both men and women of all ages but is more commonly seen in women. A measure called Bone Mineral Density (BMD) is often used to raise a warning about the disease. BMD is calculated using a variety of image processing algorithms in both X-ray and dual energy X-ray absorptiometry (DEXA) images. It is a measure of the important T-score, which reflects the degree of osteoporosis. There are many ways to quantify BMD, but DEXA is often regarded as the gold standard. The significance of DEXA images for osteoporosis detection was found in several research. The healthcare system has a serious issue with the lack of osteoporosis education and screening. There is a ton of literature available for diagnosing osteoporosis as well. The numerous methods for detecting osteoporosis will be covered in this review. The problems from the literature analysis, image processing algorithms for detecting osteoporosis, interpretations of the results, and potential recommendations are all included in this work.

show abstract

Section: Sobel Edge Detectionmentioning

confidence: 99%

Non-Invasive Machine Learning-Based Classification of Bone Health

Bhise¹,

Havaldar²

2022

View full text Add to dashboard Cite

show abstract

“…There are still just a few problems with higher computation cost, lowered reliability, redundant information, and more computational time demand. The level of sensitivity, specificity, precision, and detection rate of the face emotion recognition system may all be significantly impacted by these issues [21][22][23]. Therefore, the goal of this study is to create a classification model based on artificial intelligence that accurately detects facial expressions from images of human faces.…”

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

A novel weighted deep convolution model – African vultures optimization algorithm for an automated facial emotion recognition system

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Multi-feature based automatic facial expression recognition using deep convolutional neural network

Cited by 4 publications

References 17 publications

Non-Invasive Machine Learning-Based Classification of Bone Health

Non-Invasive Machine Learning-Based Classification of Bone Health

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

A novel weighted deep convolution model – African vultures optimization algorithm for an automated facial emotion recognition system

Contact Info

Product

Resources

About