An anti-eye-closing photographing method

Abstract

The invention discloses an anti-eye-closing photographing method. The method comprises the following steps: firstly, carrying out face detection on each frame of image of a shot video file; obtaininga face image, carrying out key positioning detection of a human face area on the human face image to obtain human eye key point positioning information; inputting the key points as initial points intoa human eye key point positioning model; calculating the opening and closing states of the human eyes according to the obtained processed human eye key point positioning information; and counting thenumber of faces and the number of people who close eyes in each frame of image, judging whether the number of people who close eyes is greater than 0 or not, if so, calculating an image quality coefficient by utilizing an image quality evaluation algorithm, sorting the images according to the image quality coefficient, and screening out an original image of which the image quality coefficient islocated at a front digit for a user to select. According to the design, the positioning precision of key points of human eyes is improved, the monitoring of the opening and closing state is simplified, and the image shooting effect is improved.

Description

technical field [0001] The invention belongs to the field of face photographing by mobile hardware, and in particular relates to a photographing method for preventing eyes from closing. Background technique [0002] With the popularization of smart terminals and the continuous development of camera technology, more and more users take selfies or group shots. When taking pictures, you often encounter the situation of closing your eyes, the picture effect is not good, and you need to take a new shot, but you will miss the scene you want to shoot when you take a picture again, which will affect the user experience. [0003] In the existing photographing scheme, for the detection of eye closure, the state of the eye is generally judged by capturing the shape of the eye, mainly based on the method of geometric features to detect the state of eye opening and closing. In the process of calculating the geometric features, the human eye area The positioning accuracy of key points is...

AI Technical Summary

Problems solved by technology

When taking pictures, you often encounter the situation where your eyes are closed, the picture taken is not good, and you need to take it again, but you will miss the scene you want to shoot when you take a picture again, which will affect the user experience

Images