A Facial Expression Recognition System To Predict Emotions

Pathak, Kaustav Mani; Yadav, Swati; Jain, Priyanka; Tanwar, Poonam; Kumar, Brijesh

doi:10.1109/iciem48762.2020.9160229

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this, they used a deep convolution network that trained the model and gave good results by applying a filter to detect the face of a person from multiple gestures [17][18]. Stochastic gradient descent (SGD) was used to train the network using the Celeb Faces attribute dataset (Celeb A) and achieved 99.7% accuracy on the Labeled wild_ Faces and 94% on YTF databases [19][20][21].…”

Section: Literature Surveymentioning

confidence: 99%

Human Face Recognition and Age Estimation with Machine Learning

Kavita

Chhillar

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Face Recognition (FR) applications are becoming more and more common these days. Face recognition, techniques, tools, and performance are all shown in this work, along with a literature review and gaps in many areas. Some of the most common uses of the FR include medical and government sectors as well as educational institutions. The FR technique can identify an appropriate individual through a camera. Online courses, online FDPs, and Webinars are becoming more interactive nowadays. Using Machine Learning, it is possible to quickly and securely determine a student's unique id to administer virtual online tests. The paper is an analysis of Machine learning and deep learning algorithms as well as tools such as Matlab and Python. The paper covers a survey of different aspects such as face detection, face recognition, face expressions, and age estimation. Hence, this is helpful for researchers to choose the right direction for their research. Future face recognition research is also considered in the paper which is now trending in face recognition systems. Data from recent years are used to evaluate the performance.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Human Face Recognition and Age Estimation with Machine Learning

Kavita

Chhillar

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…Another attempt was made to create a deep CNN based framework for emotion classification in real-time [13]. The proposed network consisted of four separate modules, each of which had multiple layers.…”

Section: Related Workmentioning

confidence: 99%

“…Deep learning algorithms have been used to categorize emotion from images [10], [13], [15]. However, feeding deep models directly with face images considers the color distribution within pixels by representing all pixels in an image to be equally important.…”

Section: Related Workmentioning

confidence: 99%

Lateralized Approach for Robustness Against Attacks in Emotion Categorization from Images

Shehu

Siddique

Browne

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep learning has achieved a high classification accuracy on image classification tasks, including emotion categorization. However, deep learning models are highly vulnerable to adversarial attacks. Even a small change, imperceptible to a human (e.g. one-pixel attack), can decrease the classification accuracy of deep models. One reason could be their homogeneous representation of knowledge that considers all pixels in an image to be equally important is easily fooled. Enabling multiple representations of the same object, e.g. at the constituent and holistic viewpoints provides robustness against attacking a single view. This heterogeneity is provided by lateralization in biological systems. Lateral asymmetry of biological intelligence suggests heterogeneous learning of objects. This heterogeneity allows information to be learned at different levels of abstraction, i.e. at the constituent and the holistic level, enabling multiple representations of the same object. This work aims to create a novel system that can consider heterogeneous features e.g. mouth, eyes, nose, and jaw in a face image for emotion categorization. The experimental results show that the lateralized system successfully considers constituent and holistic features to exhibit robustness to unimportant and irrelevant changes to emotion in an image, demonstrating performance accuracy better than (or similar) to the deep learning system (VGG19). Overall, the novel lateralized method shows a stronger resistance to changes (10.86 − 47.72% decrease) than the deep model (25.15 − 83.43% decrease). The advances arise by allowing heterogeneous features, which enable constituent and holistic representations of image components.

show abstract