The design of facial expression recognition system based on YOLO

Le résumé fourni par la source

Afacial expression recognition system is designed, Combining deep learning image processing and embedded techniques, With Jetson Nano as the data processing center, Monocular camera IMX219 collects image information, After the detection of the face information, For image preprocessing, local feature extraction, Using the weight gravity of distributed and convolutional neural network for image segmentation, end and end learning, Target detection using SVM (Support Vector Machine), LBP (Local Binary Pattern), YOLO (You Only Look Once) algorithms, Using the sparse exponential simulation datasets JAFFE and CKK+ at the GUI interface, SVM algorithm, neural network to realize MALTAB automatic classification of expressions. After verification by MATLAB simulation, the design makes facial expressions easier to be recognized and then applied to social scenes, which can be used in a wide range of fields such as representation learning and medical treatment.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.