The invention discloses a mask wearing condition monitoring method based on face and posture recognition. The mask wearing condition monitoring method comprises the following steps of: step 1, acquiring a monitoring video; step 2, performing face detection on an image in the video data, and detecting whether a face exists in the image or not; step 3, if a face exists in the image, identifying theface and performing identity authentication, determining a target identity corresponding to the face, and if all target identities cannot be determined, returning to the step 1; step 4, performing mask detection on a detected face region, and detecting whether the target wears a mask or not and whether the target wears the mask correctly or not; step 5, if the target does not wear the mask or doesnot wear the mask correctly, transmitting a prompt to the target; and step 6, performing posture detection on the target, if a hand touches mouth and nose regions, sending a prompt to the target, andotherwise, continuing the posture detection. According to the mask wearing condition monitoring method, the condition of mask wearing can be automatically monitored and reminded, and the bad habit ofwearing the mask can be corrected.