Abstract
Integrated Image Sensor and Hyperparameter Optimization of Convolutional Neural Network for Facial Skin Detection
Highlights
Artificial-intelligence image detection has begun to receive increasing attention in facial cosmetology because it can be used to detect skin conditions and identify an appropriate treatment strategy.[1,2] The complex spatial structures of the skin and lesions associated with continuous skin color changes, pigmented spots, wrinkles, red skin, and acne can be identified; such identification is limited by the poor discrimination ability of the human eye
We examined the adjustable factors that affect the accuracy of the convolutional neural network (CNN) predictions and selected eight factors as the control factors
A CNN with Taguchi parametric optimization was proposed for facial skin condition detection
Summary
Artificial-intelligence image detection has begun to receive increasing attention in facial cosmetology because it can be used to detect skin conditions and identify an appropriate treatment strategy.[1,2] The complex spatial structures of the skin and lesions associated with continuous skin color changes, pigmented spots, wrinkles, red skin, and acne can be identified; such identification is limited by the poor discrimination ability of the human eye. The Taguchi method is commonly used for optimizing the parameters of LeNet-5 to increase its classification accuracy It is a useful method for improving the design of experiments according to the parameters, system, and tolerance, and is widely used in quality assurance systems for the statistical analysis of collected data.[17] The Taguchi method is useful for determining the optimal parameter combination with minimum experimentation and the order of importance of control parameters.[18] it is a robust approach for optimizing the control parameters.[19] In the Taguchi method, an orthogonal array (OA) is used. This array comprises horizontal level factors and other factors that are mapped during an experiment.[20]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.