A Human Eye Gaze Estimation Method Based on Quantized Minimal Residual Entropy Criterion
A fixation point and residual entropy technology, applied in the field of fixation point estimation in human-computer interaction, can solve problems such as slow estimation speed and strong scene dependence, achieve low hardware requirements, improve estimation accuracy, and ensure similarity effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0044] The present invention will be further described below in conjunction with the accompanying drawings.
[0045] The flow chart of the concrete implementation of the present invention is as figure 1 As shown, the steps involved are as follows:
[0046] Step 1: face image extraction;
[0047] Step 2: Accurate extraction and alignment of human eye images;
[0048] Step 3: Human eye feature extraction and dimensionality reduction;
[0049] Step 4: Estimation of the gaze point of the human eye.
[0050] The specific implementation steps of step 1 are:
[0051] The AdaBoost algorithm is used to locate the face of the collected image, and then the face image is extracted to provide the basis for subsequent processing.
[0052] The specific implementation steps of step 2 are:
[0053] After the face image is extracted in step 1, the human eyes are accurately extracted and aligned using sub-pixel edge detection and affine transformation. The specific method is:
[0054] Fi...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


