3D-handwritten-recognition SVM classifier nuclear-parameter selection method and purpose thereof
A technology of handwriting recognition and kernel parameters, which is applied in the field of 3D handwriting recognition, can solve problems such as limited application, unstable algorithm convergence, and insufficient convergence speed of the firefly algorithm, so as to make up for the decline in accuracy, increase the convergence speed, and improve the recognition rate.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0020] The present invention mainly relates to the algorithm improvement of SVM kernel parameter selection, such as figure 1 As shown, it shows that adding the brightness factor when updating the position will affect the size of the moving step; combined with figure 1 The specific process of selecting SVM kernel parameters is as follows:
[0021] In the basic firefly algorithm, firstly, n fireflies are randomly distributed in the solution space, each firefly has its own brightness initial value, and their brightness is related to the function value of the current position, the better the position, the The higher the brightness. Each firefly has a line of sight (also known as a dynamic decision-making domain), within which it looks for fireflies that are brighter than itself, and forms a neighbor set, and then selects the firefly with the highest relative brightness through the roulette probability method and move towards it. After moving, update its own brightness, position...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 