Method and system for positioning pupil center of optometry unit
A technology of center positioning and optometry, which is applied in the field of image processing, can solve the problems of affecting the accuracy of diopter inspection results, insufficient focus of the target, and large difference in power, etc., to achieve real-time detection, high robustness, and accurate pupil center position Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] This embodiment provides a method for locating the pupil center of a refractometer, such as figure 1 with figure 2 As shown, the method includes the steps of:
[0063] S1: Collect the pupil image information on the refractometer, mark the preset area on the pupil image information, and use the preset area as the feature area for detection network learning;
[0064] S2: mark the intersection point of the centerlines of each point on the preset area as the target center point of the detection network learning;
[0065] S3: Use the marked pupil image information as a data set, divide the data set into a training set and a test set according to a preset ratio, and train and test the marked pupil image information through a face detection neural network;
[0066] S4: Predict the prediction center point and prediction area position of the preset area through the target detection network;
[0067] S5: Perform a cross-entropy loss function on the position of the predicted a...
Embodiment 2
[0086] This embodiment provides a system for positioning the pupil center of a refractometer, such as Figure 5 with Image 6 As shown, the system includes:
[0087] Acquisition module: used to collect the pupil image information on the refractometer, and mark the preset area on the pupil image information, and use the preset area as the characteristic area for detection network learning;
[0088] Labeling module: used to mark the intersection of the centerlines of each point on the preset area as the target center point of the detection network learning;
[0089] Divide the training module: used to use the marked pupil image information as a data set, and divide the data set into a training set and a test set according to a preset ratio, and train the marked pupil image information through the face detection neural network;
[0090] Prediction module: predict the prediction center point and prediction area position of the preset area through the target detection network;
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More