Face mask identification system using artificial intelligence to determine whether person is wearing mask or not has hyper-parameters e.g. learning rate, number of epochs, and batch size for fine-tuning model trained on photos divided into two categories with and without mask with considered dataset
2023-10-16
专利权人BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
申请日期2023-10-16
专利号IN202341069909-A
成果简介NOVELTY - The system has a pre-trained mobile net which is openly placed with high functional application esteem. A face is detected from an image with multiple attributes according to research into face detection requires expression recognition, face tracking, and pose estimation given a solitary image and is identified from the picture. The hyper-parameters e.g. learning rate, number of epochs, and batch size are used to fine-tune a model. The model is trained on multiple photos which are divided into two categories with and without mask with the considered dataset. USE - Face mask identification system using artificial intelligence (AI) to determine whether a person is wearing a mask or not. ADVANTAGE - The system ensures that individuals are following mask-wearing protocols to avoid the spread of virus, is trained on a real-world dataset and tested successfully using live video streaming and tests model accuracy using multiple hyper-parameters and persons at various distances.
IPC 分类号A41D-013/11 ; A62B-018/02 ; G06N-003/04 ; G06N-003/08 ; G16H-050/80
国家印度
专业领域信息技术
语种英语
成果类型专利
文献类型科技成果
条目标识符http://119.78.100.226:8889/handle/3KE4DYBR/19823
专题中国科学院新疆生态与地理研究所
作者单位
BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
推荐引用方式
GB/T 7714
KALIYAMURTHIE K P,KUMAR V K,BABU R P,et al. Face mask identification system using artificial intelligence to determine whether person is wearing mask or not has hyper-parameters e.g. learning rate, number of epochs, and batch size for fine-tuning model trained on photos divided into two categories with and without mask with considered dataset. IN202341069909-A[P]. 2023.
条目包含的文件
条目无相关文件。
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。