Facial expression recognition on a quantum computer

Mengoni, Riccardo; Incudini, Massimiliano; Pierro, Alessandra Di

doi:10.1007/s42484-020-00035-5

Cited by 12 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph theory may best encode the human face and can be used to identify facial expressions. Quantum computing has recently tried to address the problem of graph classification for emotions like happy or sad using facial expressions [65]. The proposed research primarily intends to quantify the intensities related to happy and sad emotions using a quantum computer, This research intends to address the future scope of [65] by including a variational algorithm.…”

Section: Methodsmentioning

confidence: 99%

“…Quantum computing has recently tried to address the problem of graph classification for emotions like happy or sad using facial expressions [65]. The proposed research primarily intends to quantify the intensities related to happy and sad emotions using a quantum computer, This research intends to address the future scope of [65] by including a variational algorithm. The proposed variational algorithm established the intensity of the identified emotions with the help of quantum circuits.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Emotion Quantification Using Variational Quantum State Fidelity Estimation

et al. 2022

View full text Add to dashboard Cite

Sentiment analysis has been instrumental in developing artificial intelligence when applied to various domains. However, most sentiments and emotions are temporal and often exist in a complex manner. Several emotions can be experienced at the same time. Instead of recognizing only categorical information about emotions, there is a need to understand and quantify the intensity of emotions. The proposed research intends to investigate a quantuminspired approach for quantifying emotional intensities in runtime. The inspiration comes from manifesting human cognition and decision-making capabilities, which may adopt a brief explanation through quantum theory. Quantum state fidelity was used to characterize states and estimate emotion intensities rendered by subjects from the Amsterdam Dynamic Facial Expression Set (ADFES) dataset. The Quantum variational classifier technique was used to perform this experiment on the IBM Quantum Experience platform. The proposed method successfully quantifies the intensities of joy, sadness, contempt, anger, surprise, and fear emotions of labelled subjects from the ADFES dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Emotion Quantification Using Variational Quantum State Fidelity Estimation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The model by Mengoni et al [20] utilizes Schuld et al's [5] quantum interference circuit for classifying facial expressions. However, Mengoni et al [20] identified the closest match by evaluating the distance between a test instance and a random instance from each training batch. Hence, representative selection becomes crucial for the model.…”

Section: Related Workmentioning

confidence: 99%

Real-time hybrid facial expression analysis model using quantum distance-based classifier and classical artificial neural networks: QUADCANN

Rengasamy,

Joshi,

Raveendra

2024

Quantum Inf Process

View full text Add to dashboard Cite

Facial expressions bring human interactions to life with nonverbal cues that convey hues of emotions, feelings, and cultural intent. Analyzing these expressions is essential in the age of digital transformation. Traditional approaches to real-time facial expression analysis have limitations in capturing the complexity of these expressions and consume enormous computational power. The promising computing capacity of quantum computers is poised to solve current problems and set new standards by meeting growing demands. We have created a hybrid model that leverages the capabilities of the classical and quantum domains. The proposed model uses a quantum distance-based classifier along with classical artificial neural networks to perform real-time facial expression analysis and classification. Based on a thorough review of the literature, this novel and comprehensive work is, to the best of our knowledge, one of the few that addresses eight different emotions in the quantum domain. The implementation of a novel quantum error correction method has improved the accuracy of this hybrid model. Our model was trained on the CK+ facial expression database. To ensure fairness of the study, we tested our model on the largest facial expression database, AffectNet-8, Sponsored by TATA Consultancy Services

show abstract

“…Figure 4 shows the third component of the feature vector f k= (2,4,6,8),nmax=8 for all the 75 embeddable graphs, calculated by three methods:…”

Section: Feature Vectors Comparisonmentioning

confidence: 99%

“…At the same time, improvements on graph neural networks [6] show that graph isomorphism plays a central role in the classification itself. The emergence of their quantum counterparts [7] with already proven applications [8] motivated us to investigate how photonics chips could help in this field. A preliminary part of our study was to determine to which extent graphs can be embedded on a photonic device and how one can derive isomorphism properties from it.…”

Section: Introductionmentioning

confidence: 99%

Towards graph classification with Gaussian Boson Sampling by embedding graphs on the X8 photonic chip

Pierre¹,

Nowak²

2021

Preprint

View full text Add to dashboard Cite

Photonics chips on which one can perform Gaussian Boson Sampling have become accessible on the cloud, in particular the X8 chip of Xanadu. In this technical report, we study its potential use as a first step towards graph classification on quantum devices. In order to achieve this goal, we study the generated samples of the graph embedding method which leads to feature vectors. This is done on a restricted class of unweighted, undirected and loop-free graphs. Hardware constraints are matched to properties of graphs that can be encoded. We report experiments on the X8 chip as well as comparisons to numerical simulations on a classical computer and analytical solutions. We conclude this technical report by trying to take photon loss into account and explain the observed results accordingly.

show abstract

Facial expression recognition on a quantum computer

Cited by 12 publications

References 17 publications

Emotion Quantification Using Variational Quantum State Fidelity Estimation

Emotion Quantification Using Variational Quantum State Fidelity Estimation

Real-time hybrid facial expression analysis model using quantum distance-based classifier and classical artificial neural networks: QUADCANN

Towards graph classification with Gaussian Boson Sampling by embedding graphs on the X8 photonic chip

Contact Info

Product

Resources

About