Eye state detection method based on pupil features
An eye state and pupil technology, applied in the field of image recognition, can solve the problems of slow processing and large amount of calculation, and achieve the effect of high accuracy, simple algorithm and high calculation efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] See figure 1 , figure 1 It is a schematic diagram of an eye state detection method based on pupil features provided by an embodiment of the present invention. The method comprises the steps of:
[0054] Step 1. Locate the pupil center point according to the eye image;
[0055] Step 2, forming a plurality of gray value rays in the eye image with the center point of the pupil as the starting point;
[0056] Step 3, determine the pupil boundary point through the gray value ray calculation;
[0057] Step 4, using the pupil boundary point to determine the state of the eye.
[0058] Among them, for step 1, may include:
[0059] Converting the eye image into an eye grayscale image;
[0060] Carrying out gray-scale contrast enhancement preprocessing to the eye gray-scale image;
[0061] The pupil center point is estimated according to the preprocessed eye grayscale image.
[0062] Wherein, estimating the pupil center point according to the preprocessed eye grayscale ima...
Embodiment 2
[0088] On the basis of the above-mentioned embodiments, this embodiment further explains the eye state detection method based on pupil features.
[0089] The method comprises the steps of:
[0090] Step 1. Obtain the eye image
[0091] After the eye image is acquired, the eye image is processed to adjust the eye part to a horizontal position.
[0092] The eye image is converted into an eye grayscale image, and the grayscale contrast enhancement preprocessing is performed on the eye grayscale image. The processing method is as follows:
[0093] f=c*log(1+double(f 0 ))
[0094] Among them, f 0 represents the original image, and f represents the contrast-enhanced image.
[0095] The contrast-enhanced image is processed by Laplacian filtering.
[0096] The gray contrast enhancement preprocessing of the gray image of the eye is more conducive to the distinction between the pupil and the outer area; in addition, the non-directional nature of the Laplacian filter can denoise th...
Embodiment 3
[0121] On the basis of the foregoing embodiments, this embodiment illustrates an eye state detection method based on pupil features.
[0122] See figure 2 , figure 2 A schematic diagram of pupil boundary points in an open state provided for an embodiment of the present invention. As shown in the figure, select the first closure threshold as 0.8 and the second closure threshold as 0.2, start from the pupil center point along the direction of the upper eyelid and emit M (M takes 50) gray value rays along the direction of the lower eyelid Launch N (N is taken as 50) gray value rays; a total of X (90) pupil boundary points can be determined in the ray direction, which is brought into the eye closure formula, and θ is obtained as 0.1, and θ is less than the second closure threshold value of 0.2 , so the eyes are open.
[0123] Please continue to see image 3 , image 3 The schematic diagram of the pupil boundary point in the closed state provided by the embodiment of the pre...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More