Title: Face recognition algorithm of sprinters based on sliding data camera measurement

Authors: Yujie Fan

Addresses: Sports Training College, Jilin Institute of Physical Education, Changchun 130022, China

Abstract: In order to solve the problems of low accuracy of face key point recognition and large noise error in recognition, a sprinter face recognition algorithm based on sliding data camera measurement is designed. Firstly, the sliding data camera measurements is imported, and the camera calibration method is used to obtain the 3D points and plane projection in the athlete's running scene, which are collected into the same coordinate system through the conversion matrix to extract the taxiing data. Then, the unclear coordinate points are replaced by convolution kernel, and the image noise points are removed by bilateral filter. Finally, multiple key point coordinates are designed in the face image, and face recognition is realised by sparse approximation of the key points, and the most matched feature points in the face image combined with greedy algorithm. The results show that the proposed algorithm can recognise the six key points of human face, and the noise reduction error is less than 1.3%, which achieves the expected goal and has practical application value.

Keywords: taxi data camera measurement; sprinter; face recognition; 3D points; bilateral filtering.

DOI: 10.1504/IJRIS.2023.128377

International Journal of Reasoning-based Intelligent Systems, 2023 Vol.15 No.1, pp.79 - 85

Received: 17 Nov 2021
Accepted: 14 Jul 2022
Published online: 18 Jan 2023 *