Method for identifying suspected drug addicts, device and storage medium

Abstract

The invention provides a method for identifying suspected drug addicts, a device for identifying suspected drug addicts and a storage medium. The method comprises an acquisition step and a detection step. According to the acquisition step, a to-be-processed face image img is acquired. According to the detection step, a trained deep neural network model is adopted to identify the to-be-processed face image img; and if a probability value output by the neural network is greater than a threshold value, it is determined that a person corresponding to the face image is a suspected drug addict. According to the method of the invention, drug addicts are identified through facial features. According to the method, the device and the storage medium of the invention, a deep learning technology is utilized; a special deep neural network algorithm is designed; a large number of face pictures of drug addicts and non-drug addicts are used to train the neural network algorithm, so that the algorithmcan learn the difference between the facial features of the drug addicts and non-drug addicts; and the weight of the neural network algorithm is solidified, so that the algorithm can extract the facial features of people in a targeted mode and can classify the facial features so as to identify whether one person is suspected to addict drugs or not, and identification is convenient and fast.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method, device and storage medium for identifying suspected drug addicts. Background technique [0002] Smoking drugs is very harmful. People who take drugs for a long time will have red eyelids and nose, small pupils, scattered and unfocused eyes, listlessness, or other difficult-to-observe features. For a long time, the identification of drug addicts has been mainly through blood testing, urine testing, hair testing, urine and other methods. [0003] The methods mentioned above to identify drug addicts: blood test, urine test, hair test, urine test, although the accuracy rate is high, but there are several shortcomings or disadvantages: 1. Need to find the drug addict himself, how to find people, who to find Both the detection process requires a lot of manpower and material resources; 2. It requires the cooperation of drug addicts. Some drug addicts are emoti...

AI Technical Summary

Problems solved by technology

[0003] The methods mentioned above to identify drug addicts: blood test, urine test, hair test, urine test, although the accuracy rate is high, but there are several shortcomings or disadvantages: 1. Need to find the drug addict himself, how to find people, who to find Both the detection process requires a lot of manpower and material resources; 2. It requires the cooperation of drug addicts. Some drug addicts are emotionally unstable when they are drug addicts, and a low degree of cooperation will cause great inconvenience; 3. The detection process takes time. , not all methods give immediate results

Due to the shortcomings of the above points, the current identification methods for drug users cannot quickly identify all people. Many drug users cannot be detected in time even if they take drugs for a long time, which will cause great harm to drug users and their families, and bring great harm to the public. Safety comes with potential safety hazards

Images