Association identification method and equipment based on generative adversarial network
A recognition method and generative technology, applied in the field of target recognition, can solve problems such as restricting the practical process and application scenarios of target recognition technology, increasing system complexity, affecting recognition speed, etc., and shortening the time for data collection and processing.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0035] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0036] see figure 1 , the present invention uses the handwritten picture corresponding to the letter ABCDEFGHIJ and the number 0123456789 as the target object, and defines the category label corresponding to the target ABCDEFGHIJ and 0123456789 as 0123456789. After the GAN network training is completed, the test data is input and the corresponding category label is output.
[0037] see figure 2 , the present invention is based on the association recognition method of generative confrontation network, mainly comprises the following steps:
[0038] S1. Taking the category of the object to be recognized as the target of network training, and applying a set of random speckle sequences to objects of the same type and different shapes as the object to be recognized, including the following steps: using a set of known sequences of random speckles i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


