Method for screening drug addicts based on eye information

• Main Authors: KONG DESHENYUE, SUN JIAXUE, MENG GUANGHUI, XU YU, WANG KUNHUA, LYU JIA, DU JINZE, WAN TAO
• Format: Patent
• Language: Chinese; English
• Published: 19.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a method for screening drug addicts based on eye information, and the method comprises the steps: collecting the eye video image information of a screened person, constructing a deep learning neural network model, extracting pupil change radius sequence features from the eye video image information, and carrying out the recognition of the pupil change radius sequence features; according to the method, the problems that in the prior art, threshold determination is not accurate, and eye image information of the drug addicts is not fully utilized are solved, and the method is suitable for screening the drug addicts. Compared with a traditional screening method or a single-feature screening method, the method is more effective, reliable and higher in accuracy. 本发明公开了一种基于眼部信息筛查吸毒人员的方法，该方法采集了被筛查者眼部视频图像信息，并构建了深度学习神经网络模型，从眼部视频图像信息中提取了瞳孔变化半径序列特征，然后将图像序列通道的特征与半径序列通道的特征进行特征融合，通过训练和验证后获得能用于筛查吸毒人员的模型，本发明方法解决当前技术阈值确定不准确、不充分利用吸毒人员眼部图像信息的问题，与传统方法筛选方法或单特征筛选方法相比，本发明方法更有效、可靠，准确率更高。