Open AccessMethods for pattern detection based on colour and size features in video streams
Author(s) -
Nguyen Cuong The,
V. I. Syryamkin,
Nguyen Trang Hoang Thuy
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1843/1/012009
Subject(s) - computer science , artificial intelligence , computer vision , pattern detection , face detection , field (mathematics) , face (sociological concept) , architecture , pattern recognition (psychology) , facial recognition system , geography , social science , mathematics , archaeology , sociology , pure mathematics
Detecting pattern in images plays a huge role in the field of computer vision. The article summarizes methods for detecting patterns by their properties, such as colours, shapes in images. And with video, the detection of patterns is also based on their movement. Human face recognition problem is also mentioned in the application of MTCNN network architecture and reconfiguring FaceNet to suit actual requirements. Test results are given and recommendations with data and program operating conditions are provided for the reference.