Idioma:

Efficientnet-Lite and Hybrid CNN-KNN Implementation for Facial Expression Recognition on Raspberry Pi

Ab Wahab, Mohd Nadhir ; Nazir, Amril ; Zhen Ren, Anthony Tan ; Mohd Noor, Mohd Halim ; Akbar, Muhammad Firdaus ; Mohamed, Ahmad Sufril Azlan

IEEE access, 2021, Vol.9, p.134065-134080 [Periódico revisado por pares]

Piscataway: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
Efficientnet-Lite and Hybrid CNN-KNN Implementation for Facial Expression Recognition on Raspberry Pi
Autor: Ab Wahab, Mohd Nadhir ; Nazir, Amril ; Zhen Ren, Anthony Tan ; Mohd Noor, Mohd Halim ; Akbar, Muhammad Firdaus ; Mohamed, Ahmad Sufril Azlan
Assuntos: Accuracy ; Algorithms ; Artificial neural networks ; Computational modeling ; Convolutional neural networks ; Datasets ; Deep learning ; EfficientNet-Lite ; emotion recognition ; facial expression recognition ; Feature extraction ; Hidden Markov models ; hybrid CNN-KNN ; Machine learning ; Optimization ; Raspberry Pi ; Real-time systems ; Storage capacity ; Support vector machines ; Training
É parte de: IEEE access, 2021, Vol.9, p.134065-134080
Descrição: Facial expression recognition (FER) is the task of determining a person's current emotion. It plays an important role in healthcare, marketing, and counselling. With the advancement in deep learning algorithms like Convolutional Neural Network (CNN), the system's accuracy is improving. A hybrid CNN and k-Nearest Neighbour (KNN) model can improve FER's accuracy. This paper presents a hybrid CNN-KNN model for FER on the Raspberry Pi 4, where we use CNN for feature extraction. Subsequently, the KNN performs expression recognition. We use the transfer learning technique to build our system with an EfficientNet-Lite model. The hybrid model we propose replaces the Softmax layer in the EfficientNet with the KNN. We train our model using the FER-2013 dataset and compare its performance with different architectures trained on the same dataset. We perform optimization on the Fully Connected layer, loss function, loss optimizer, optimizer learning rate, class weights, and KNN distance function with the k-value. Despite running on the Raspberry Pi hardware with very limited processing power, low memory capacity, and small storage capacity, our proposed model achieves a similar accuracy of 75.26% (with a slight improvement of 0.06%) to the state-of-the-art's Ensemble of 8 CNN model.
Editor: Piscataway: IEEE
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Efficientnet-Lite and Hybrid CNN-KNN Implementation for Facial Expression Recognition on Raspberry Pi

Ab Wahab, Mohd Nadhir ; Nazir, Amril ; Zhen Ren, Anthony Tan ; Mohd Noor, Mohd Halim ; Akbar, Muhammad Firdaus ; Mohamed, Ahmad Sufril Azlan

Piscataway: IEEE

Buscando em bases de dados remotas. Favor aguardar.