Human Face and Facial Expression Recognition Using Deep Learning and SNet Architecture Integrated with BottleNeck Attention Module

Abstract

Thermal infrared face image recognition with the help of deep learning technology has become the most debated concept in research area nowadays. Many articles are done and being working on this area to discover novel findings. Thermal infrared images can be recognised irrespective of light conditions, aging and facial disguises. This paper proposes a method named SNet integrated with BottleNeck Attention Module (SN-BNAM) for thermal face image recognition using SENet architecture in which the BottleNeck Attention Module is integrated. After squeeze and excitation process, the channel and spatial attention is inferred as two separate branches inside the BottleNeck Attention Module (BAM). This module is placed at each BottleNeck area. The SN-BNAM module can be integrated with any feed forward convolutional neural networks. The efficiency of the proposed system is evaluated by experimenting on various architectures and object validation is done on VOC 2007, MS COCO, CIFAR-100 and ImageNet-1K datasets. These experiments proves that our method shows consistent improvement in image classification and object detection.

Enhancing Online Teaching Effectiveness Through Computer Vision Analysis of Teacher Expressions and Gestures in Educational Videos

“…Although many studies have attempted to use computer vision technology to analyze teachers' facial expressions and movements, these methods often rely too much on static features and fail to fully consider the temporal changes and spatial distribution of expressions [14][15][16][17]. Additionally, some methods have low accuracy in recognizing complex expressions and movements, making it difficult to comprehensively evaluate teachers' teaching behaviors [18][19][20][21][22][23]. These limitations indicate the urgent need for more flexible and accurate analysis methods to improve the depth and breadth of research.…”