Facial Emotion Recognition (FER) is essential for enhancing human-computer interaction and psychological analysis. Despite the progress in classical approaches, Quantum Convolutional Neural Networks (QCNNs) offer promising advancements by leveraging quantum parallelism and entanglement for more efficient feature processing. Combining the advantages of both classical and quantum domains, this study introduces a hybrid classical to enhanced QCNN (CEQCNN) framework for FER. The process begins with the pre-processing of facial images, followed by a supervised auto-encoder that leverages an additional classification loss, along with the reconstruction loss, to effectively extract discriminatively informative emotional features suitable for input to the QCNN. Traditional QCNN architectures suffer from a less expressive quantum feature space and insufficient post-pooling qubit correlation. The proposed enhanced QCNN architecture overcomes these limitations by introducing two new layers: the Expressible Convolutional Layer (Ex-Conv), which enhances quantum feature space representation utilizing a high expressibility ansatz, and the Entangled Convolutional Layer (En-Conv), which increases qubit entanglement after pooling to mitigate information loss. Extensive experimentation reveals that the supervised auto-encoder is effective for class-specific, organized feature extraction, and the combined integration of Ex-Conv and En-Conv layers within QCNN significantly improves the performance compared to traditional QCNN. Further analysis of expressibility and entangling capability justifies the effectiveness of these new layers. The proposed CEQCNN approach achieves 80.12% accuracy on FER-2013 and 91.98% on KDEF dataset, demonstrating a competitive position in the literature.
Facial Emotion Recognition (FER) is essential for enhancing human-computer interaction and psychological analysis. Despite the progress in classical approaches, Quantum Convolutional Neural Networks (QCNNs) offer promising advancements by leveraging quantum parallelism and entanglement for more efficient feature processing. Combining the advantages of both classical and quantum domains, this study introduces a hybrid classical to enhanced QCNN (CEQCNN) framework for FER. The process begins with the pre-processing of facial images, followed by a supervised auto-encoder that leverages an additional classification loss, along with the reconstruction loss, to effectively extract discriminatively informative emotional features suitable for input to the QCNN. Traditional QCNN architectures suffer from a less expressive quantum feature space and insufficient post-pooling qubit correlation. The proposed enhanced QCNN architecture overcomes these limitations by introducing two new layers: the Expressible Convolutional Layer (Ex-Conv), which enhances quantum feature space representation utilizing a high expressibility ansatz, and the Entangled Convolutional Layer (En-Conv), which increases qubit entanglement after pooling to mitigate information loss. Extensive experimentation reveals that the supervised auto-encoder is effective for class-specific, organized feature extraction, and the combined integration of Ex-Conv and En-Conv layers within QCNN significantly improves the performance compared to traditional QCNN. Further analysis of expressibility and entangling capability justifies the effectiveness of these new layers. The proposed CEQCNN approach achieves 80.12% accuracy on FER-2013 and 91.98% on KDEF dataset, demonstrating a competitive position in the literature.
Face recognition has become an essential biometric technology for applications such as security monitoring, user authentication, and intelligent surveillance systems. Conventional approaches based on deep neural networks, particularly convolution-based architectures, provide high recognition performance but often demand considerable computational resources and extended training durations as network complexity increases. To overcome these challenges, Quantum Machine Learning (QML) utilizes quantum computing concepts, including quantum superposition and entangled states, to achieve efficient feature representation and processing. This paper presents a Hybrid Quantum-Classical Face Recognition System built on a Multi-Gate Quantum Convolutional Neural Network (MG-QCNN). The proposed framework employs a 4-qubit variational quantum circuit that incorporates RY state encoding together with RX, RZ, and CNOT quantum operations to extract discriminative facial representations. In addition, a structural ablation analysis is conducted to investigate the influence of individual quantum components on the overall recognition capability of the model. To enhance spatial feature learning and classification performance, several classical neural network layers, namely convolution, batch normalization, max-pooling, dropout, and fully connected layers, are integrated after the quantum feature extraction stage. Within the hybrid framework, the quantum circuit is responsible for generating meaningful feature representations, whereas the classical neural network performs feature refinement and final identity classification. The framework is further combined with the DeepFace verification approach to perform facial similarity analysis and identity verification. Moreover, an Open-Set Face Recognition mechanism is incorporated to determine if an input facial image corresponds to a registered identity or represents an unseen individual. This capability increases system reliability and supports accurate unknown-person identification
The incorporation of modern technologies into education has transformed how learning is seen and assessed, with a rising emphasis on understanding student behavior using facial expression recognition (FER). Recognizing students' emotional and cognitive states can provide vital insights into their engagement and learning styles, allowing teachers to adjust their teaching tactics in real time. Traditional machine learning algorithms have been used to solve this problem, but they frequently struggle with the complexity of facial expressions and big datasets, resulting in limitations in accuracy and processing efficiency. This study explores the potential of quantum computing in addressing these challenges through the development of a Deep Quantum Convolutional Neural Network (QCNN) architecture. By combining the advanced image processing capabilities of convolutional neural networks (CNNs) with the computational power of quantum features such as superposition and entanglement, we aim to enhance the detection of facial expressions that reflect students' engagement, concentration, frustration, and satisfaction. Finally, the result demonstrates a classification accuracy of 91.58
The purpose of this work is to analyze how new technologies can enhance clinical practice while also examining the physical traits of emotional expressiveness of face expression in a number of psychiatric illnesses. Hence, in this work, an automatic facial expression recognition system has been proposed that analyzes static, sequential, or video facial images from medical healthcare data to detect emotions in people's facial regions. The proposed method has been implemented in five steps. The first step is image preprocessing, where a facial region of interest has been segmented from the input image. The second component includes a classical deep feature representation and the quantum part that involves successive sets of quantum convolutional layers followed by random quantum variational circuits for feature learning. Here, the proposed system has attained a faster training approach using the proposed quantum convolutional neural network approach that takes [Formula: see text] time. In contrast, the classical convolutional neural network models have [Formula: see text] time. Additionally, some performance improvement techniques, such as image augmentation, fine-tuning, matrix normalization, and transfer learning methods, have been applied to the recognition system. Finally, the scores due to classical and quantum deep learning models are fused to improve the performance of the proposed method. Extensive experimentation with Karolinska-directed emotional faces (KDEF), Static Facial Expressions in the Wild (SFEW 2.0), and Facial Expression Recognition 2013 (FER-2013) benchmark databases and compared with other state-of-the-art methods that show the improvement of the proposed system.
Emotion recognition in speech is essential for human-computer interaction. This study introduces a refined hybrid Quantum Convolutional Neural Network (QCNN) framework designed to substantially enhance Speech Emotion Recognition (SER). It addresses major challenges such as speaker variability, noise robustness, and cross-domain applicability that often limit classical deep learning models. By Utilizing quantum principles like superposition and entanglement within a 6-qubit, 8-layer parameterized circuit, the model derives highdimensional, noise-resistant features from speech signals. The method includes sophisticated preprocessing steps, such as bandpass filtering and energy-based Voice Activity Detection (VAD), followed by Mel-Frequency Cepstral Coefficients (MFCC) extraction. Evaluated on a diverse dataset of 4,515 samples across eight emotions (Angry, Calm, Disgust, Fear, Happy, Neutral, Sad, Surprised), the QCNN achieved an accuracy of 86 %, setting a new benchmark. It surpasses classical approaches such as a CNN with attention(77%), a traditional QCNN(77.87%), and a hybrid quantum-classical network(76%). The model demonstrated balanced performance, with precision scores ranging from 0.79 to 1.0 (including a perfect 1.0 for Fear) and recall scores from 0.82 to 0.94. These results underscore the promise of quantum-enhanced neural networks in capturing complex, nonlinear speech emotion patterns and establishing a new standard for robust, generalizable SER systems.
Facial expression recognition (FER) underpins applications in affective computing but remains challenged by computational cost and the ambiguity of compound emotions. We introduce a Hybrid-Quantum Convolutional Neural Network (HQ-CNN) that integrates quantum principles (superposition, entanglement) into a classical CNN pipeline to enhance representational power and efficiency. Evaluated on the Real-World Affective Faces Database (RAF-DB), the HQ-CNN improves accuracy by 4.60% on basic emotions and 4.47% on compound emotions, while reducing computation time by up to 22.11% and 6.20%, respectively, relative to a VGG16 baseline. Confusion-matrix analysis shows fewer misclassifications on challenging compound categories, indicating better separation of overlapping affective cues. These results support the use of quantum-enhanced architectures as a viable path toward robust, real-time FER systems.
Quantum machine learning is emerging as a promising frontier at the intersection of quantum computing and Artificial Intelligence, offering potential gains in speed, efficiency, and robustness. In this paper, a hybrid Quantum Convolutional Neural Network (QCNN) architecture is presented for visual pattern recognition tasks, leveraging quantum superposition and entanglement for enhanced feature extraction. Unlike previous studies that focus on small-scale or simplified datasets, this study systematically evaluates QCNNs across multiple benchmark datasets and provides a direct comparison with classical CNNs, highlighting practical quantum advantages such as parameter efficiency and noise-resilience. The proposed approach encodes classical image data from benchmark datasets, including70K28×28grayscale images from MNIST and FashionMNIST, and60Kdownsampled grayscale CIFAR-10 images, into quantum states using amplitude encoding, followed by hierarchical quantum convolution and pooling layers implemented via parametrised quantum circuits (PQCs). The model culminates in a classical dense layer for final classification. Experimental results demonstrate that the QCNN achieves competitive performance on low-dimensional grayscale datasets with 93.2 % accuracy on MNIST and 88.5% on Fashion MNIST, though it underperforms on more complex datasets like CIFAR-10 with 67.8 % accuracy due to current quantum hardware limitations. While not yet surpassing classical CNNs in raw accuracy, the proposed QCNN exhibits notable parameter efficiency, noise resilience, and theoretical potential for energy-efficient computation, highlighting its promise for future applications as quantum technologies mature.