Facial Expression Recognition Using YOLO

面部表情识别 计算机科学 面部识别系统 面部表情 人工智能 模式识别(心理学) 计算机视觉
作者
K C Tejaswi,D Mokshith,Sai Pradeep E,Ch Mahesh Kumar,Manoj Kumar K
标识
DOI:10.1109/rmkmate59243.2023.10369028
摘要

This study presents a facial expression recognition system that utilizes the You Only Look Once (YOLO) object detection framework. The system leverages the capabilities of YOLO to detect and classify facial expressions accurately and efficiently.The main objective is to achieve efficient and real-time detection and classification of facial expressions. By utilizing the YOLO framework's object detection capabilities, the system can accurately locate and extract facial regions of interest for subsequent analysis. To train the system, a large dataset of labeled facial images representing various expressions, such as happiness, sadness, anger, fear, surprise, and neutral, is utilized. Deep learning techniques, including convolutional neural networks (CNNs), are employed to optimize the modified YOLO network's parameters, enhancing expression recognition accuracy.Experimental evaluation on benchmark facial expression datasets demonstrates the effectiveness and efficiency of the proposed YOLO-based facial expression recognition system. It surpasses existing approaches in terms of both accuracy and real-time performance, making it highly suitable for practical applications. The proposed facial expression recognition system based on the YOLO object detection framework demonstrates the capability to detect and classify facial expressions in real-time. This advancement opens up new possibilities in fields such as emotion detection, human-computer interaction, and affective computing. The approach not only improves accuracy but also addresses the crucial requirement for real-time processing, which is essential for various real-world applications. By leveraging the advantages of the YOLO framework, the system achieves a good balance between accuracy and speed, enabling efficient and effective facial expression analysis. With its promising results, the YOLO-based facial expression recognition system holds great potential for advancing fields that rely on accurate and real-time emotion analysis..

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
LMW发布了新的文献求助10
1秒前
tian发布了新的文献求助10
2秒前
小佳今天瘦了没完成签到,获得积分20
2秒前
万能图书馆应助内向安南采纳,获得10
3秒前
dolphin820发布了新的文献求助30
3秒前
3秒前
4秒前
4秒前
4秒前
5秒前
5秒前
Wguan完成签到,获得积分10
5秒前
123完成签到,获得积分10
6秒前
yyyyyxn发布了新的文献求助10
6秒前
sunmcxz完成签到,获得积分20
6秒前
Caroline发布了新的文献求助10
7秒前
8秒前
8秒前
SciGPT应助机智的依珊采纳,获得10
8秒前
坚定的诗双完成签到,获得积分10
8秒前
研友_VZG7GZ应助dali采纳,获得10
8秒前
科研通AI2S应助殷勤的凝海采纳,获得10
8秒前
9秒前
科研通AI6.4应助柒柒_BX采纳,获得10
9秒前
sean晁烁发布了新的文献求助30
9秒前
9秒前
Ava应助高子翔采纳,获得10
10秒前
yingliu发布了新的文献求助10
10秒前
somnus完成签到,获得积分10
10秒前
烟花应助sunmcxz采纳,获得10
10秒前
10秒前
一梦发布了新的文献求助10
10秒前
11秒前
Zhang发布了新的文献求助10
11秒前
11秒前
小马甲应助Caroline采纳,获得10
11秒前
11秒前
12秒前
liu发布了新的文献求助10
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 2500
Atlas of Aligner Treatment and Planning A Case-Based Approach 1000
悉尼大学博士学位论文,题目:Modelling and testing of one-sided stitched laminated composites. 作者:Kristopher P. Plain 700
Soil mites of the family Rhagidiidae (Actinedida: Eupodoidea). Morphology, Systematics, Ecology 520
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Decoding Sensitive Skin Syndrome: International Expert Advisory Insights on Management From India and the United States of America 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7436529
求助须知:如何正确求助?哪些是违规求助? 9038186
关于积分的说明 19259940
捐赠科研通 7062692
什么是DOI,文献DOI怎么找? 3237451
关于科研通互助平台的介绍 2400816
邀请新用户注册赠送积分活动 2221282