Smile expression detection method and device, computer equipment and storage medium

Abstract

The invention discloses a smile expression detection method and a device, computer equipment and a storage medium. The method comprises the steps of determining identity information of a person according to an image of the person at a preset sound source position when text data obtained by converting voice data at the preset sound source position through sound source positioning is successfully matched with target text data; when the gesture type obtained in the image of the person is a preset gesture item, determining that smile expression detection is started, and a camera device is made tostart continuous shooting of video information of the person; identifying the amplified picture of the preset position of the face in the video information of the person through a smile identificationmodel, and obtaining an identification result output by the smile identification model; and when a smile expression detection termination instruction is received, enabling the camera equipment to stop shooting the video information of the person. According to the invention, the data volume of the stored video information is reduced, the query amount of the video information in the time period ofmanually tracing the expression is also reduced, and the smile expression detection accuracy is improved.

Description

technical field [0001] The invention relates to the field of image detection, in particular to a smile expression detection method, device, computer equipment and storage medium. Background technique [0002] For the smile service detection of the toll booth service personnel (that is, the smile expression detection on the service personnel's face), currently the toll station can only manually detect whether all the on-duty service personnel captured by the camera equipment have video data of smiling service to the owner of the paying vehicle , so as to make a certain evaluation of the service staff's work quality; but this method has the following problems: there are not always vehicles passing through the toll booth, and when no vehicles pass, the service staff is not required to smile all the way, but Because the video data is always aimed at the service personnel to shoot the whole process, and the detection process is also aimed at all the above-mentioned video data, so...

AI Technical Summary

Problems solved by technology

[0002] For the smile service detection of the toll booth service personnel (that is, the smile expression detection on the service personnel's face), currently the toll station can only manually detect whether all the on-duty service personnel captured by the camera equipment have video data of smiling service to the owner of the paying vehicle , so as to make a certain evaluation of the service staff's work quality; but this method has the following problems: there are not always vehicles passing through the toll booth, and when no vehicles pass, the service staff is not required to smile all the way, but Because the video data is always aimed at the service personnel to shoot the whole process, and the detection process is also aimed at all the above-mentioned video data, so, first of all, it will result in recording a lot of video data of the smile service during non-service hours, which will cause the evaluation of the smile service to be unobjective Accurate, and thus can not accurately reflect the service quality of employees; In the scene where vehicles pass by, operations such as zooming in or zooming out may be required to view clear video data. The operation is cumbersome. After the detection is completed, the database also needs to occupy a large amount of storage space to save all video data, and the maintenance cost is relatively high. ; Therefore, needing to find a kind of technical scheme that can solve the above-mentioned problem becomes the problem that those skilled in the art urgently need to be solved

Images