Year-end Sale % OFF 
Abstract
The existing face detection methods were affected by the network model structure used. Most of the face recognition methods had low recognition rate of face key point features due to many parameters and large amount of calculation. In order to improve the recognition accuracy and detection speed of face key points, a real-time face key point detection algorithm based on attention mechanism was proposed in this paper. Due to the multiscale characteristics of face key point features, the deep convolution network model was adopted, the attention module was added to the VGG network structure, the feature enhancement module and feature fusion module were combined to improve the shallow feature representation ability of VGG, and the cascade attention mechanism was used to improve the deep feature representation ability. Experiments showed that the proposed algorithm not only can effectively realize face key point recognition but also has better recognition accuracy and detection speed than other similar methods. This method can provide some theoretical basis and technical support for face detection in complex environment.
Highlights
Artificial intelligence has made great progress in bridging the gap between human and machine capabilities [1,2,3]
Many superparameters will increase the difficulty of training the algorithm. erefore, face key point detection based on nonanchor box has become a research hotspot of scholars in recent years [53]. e benchmark model algorithm VGG in this paper is one of many nonanchor frame target detection algorithms, and the benchmark model algorithm has some problems: (1) It is more affected by background texture information because it depends on key points
This paper proposes to add the expectation maximization attention mechanism to the benchmark algorithm to reconstruct the extracted feature map, weaken the background texture information, and strengthen the foreground information
Summary
Artificial intelligence has made great progress in bridging the gap between human and machine capabilities [1,2,3]. Face detection plays an important role in the field of artificial intelligence. Facial key point localization plays an important role. Traditional methods (such as the first active shape model, improved model, active appearance model, further improved model, local constraint model, and more variants) try to obtain descriptors that can represent local features, so as to locate facial contour using heuristic rules [6,7,8]. CRM abandons the classical machine learning algorithm, uses convolutional neural network, and gradually (even locally) refines the coordinates of key points, which proves that it is superior to the traditional methods. Under the influence of numerous human factors, when facing the unconstrained face images in the field (such as posture, occlusion, expression, lighting, makeup, blur, etc.), they are still far from a robust and accurate face key point location model [9, 10]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
