An optimal selection method and device based on face capture
A face position and face technology, applied in the field of data processing, can solve problems such as waste of storage space
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0078] In the above, the ranges of face position score, face brightness score, face size score, face angle score, gain score, face speed score and face quality score in the scoring process are 0-100;
[0079] In the optimal process, the face position score weight of weighted summation is 0.19, the face brightness score weight is 0.19, the face size score weight is 0.01, the face angle score weight is 0.1, the gain score weight is 0.01, and the face speed is The score weight is 0.01, and the face quality score weight is 0.19.
[0080] It should be noted that the values given above are only an example of an embodiment, and may be adjusted according to application requirements in actual situations.
[0081] The present invention also relates to an optimization method based on face capture, including a scoring process and an optimization process;
[0082] The scoring process includes:
[0083] The step of judging the position of the face in the face capture image, the positio...
Embodiment 2
[0094] In the above, the ranges of face position score, face brightness score, face size score, face angle score, gain score, face speed score and face quality score in the scoring process are 0-100;
[0095] In the optimal process, the face position score weight of weighted summation is 0.01, the face brightness score weight is 0.01, the face size score weight is 0.19, the face angle score weight is 0.1, the gain score weight is 0.19, and the face speed is The score weight is 0.19, and the face quality score weight is 0.01.
[0096] It should be noted that the values given above are only an example of an embodiment, and may be adjusted according to application requirements in actual situations.
Embodiment 3
[0098] In the above two solutions, the facial features include facial features eyebrows, eyes, mouth, ears, and nose.
[0099] Selecting facial features as facial features to distinguish whether it is positive or not can greatly simplify the amount of data for image comparison processing, and the accuracy is relatively high.
[0100] Implementation example 1:
[0101] see figure 2 To illustrate the surveillance video image, the width and height of each frame of the surveillance video are width and height respectively, and the target is approaching from far to near. Assume that the upper left coordinates of the target face are (sx, sy), and the lower right coordinates are (ex, ey).
[0102] The present invention provides a scheme based on an optimal method of face capture, and the scoring process scores (weights) the face capture from 7 dimensions:
[0103] 1. Face position score
[0104] Here, different face location scoring strategies are used for daytime and nighttime.
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More