A low footprint and high discriminative CNN for face recognition

20th Italian National Conference on Photonic Technologies (Fotonica 2018)(2018)

引用 0|浏览2
暂无评分
摘要
Nowadays, facial recognition is one of the most faced problems in the field of computer vision. In this arena, the most robust techniques have been proven to be those based on Convolution Neural Networks (CNNs). In this paper a new CNN, characterized by a lower computational complexity with reference to the ones currently present in the state of the art, jointly with a highly discriminating learning methodology, is presented.
更多
查看译文
关键词
Computer Vision,Face Recognition,Deep Learning,Convolution Neural Networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要