CRIS
Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1
Browse
2 results
Search Results
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Image Facial Expression Recognition based on Active Muscles and their Notable Triangle Points(IEEE, 2025); During emotion experience originated in psychological changes, the effect in face muscles results in a characteristic set of contractions associated to specific emotions. This paper propose an intuitive representation of these interactions with the objective of facial expression recognition through geometric features. In medical research, it has generated insights regarding emotional state, cognitive function, and pain level during clinical procedures leading to an effective patient treatment, assisting diagnosis and monitoring disease progression mainly in neurological conditions. Starting from a facial muscle modeling using triangles, it utilizes an initial 68 landmarks fitting algorithm, and later the computation of triangle notable points to work as anchors of specific muscles. Secondly, the optimization process through stochastic techniques is applied to set the point type combination so that the F1-Score is maximized. Experimental results were performed with conventional classifiers and no fine tuning, accomplishing an accuracy, precision, recall and F1-score of 0.88 for KDEF dataset, while 0.84, 0.86, 0.84, and 0.84 respectively for the JAFFE dataset, proving to be a reliable technique in the expression recognition problem. ©The authors ©IEEE. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Optimal Dataset Size for Fine-Tuning sEMG-Based Hand Gesture Recognition in Rehabilitation Prosthesis(IEEE, 2024); ; ; Franco-Gaona, ErickSurface electromyography (sEMG) has become a vital tool for controlling prostheses and rehabilitation using hand gesture recognition. However, the process of fine-tuning machine learning models to individual users often requires considerable amounts of data, which can be challenging to obtain due to user fatigue and discomfort. This work investigates the optimal dataset size needed for fine-tuning a pretrained Convolutional Neural Network (CNN) model for hand gesture recognition, using the NinaPro DB2 dataset. Our results show that training on just a third of the dataset achieves over 90% accuracy, highlighting a significant reduction in the data requirements compared to traditional methods. This approach can minimize the burden of data collection on users, making sEMG-based rehabilitation devices more practical and accessible. ©The authors ©IEEE8