Abstract
The present invention discloses an image recognition method and a system, which provides a plurality of recognition images, and the objects to be recognized in each recognition image must account for more than a preset proportion of the entire recognition image, and then inputs each recognition image into a neural network, wherein the neural network has an object recognition model that has been trained. The neural network uses the object recognition model to recognize the objects in each recognition image, gives recognition values respectively, compares all recognition values, and takes the largest recognition value as the recognition result.
| Translated title of the contribution | Image recognition method and system |
|---|---|
| Original language | Chinese (Traditional) |
| Patent number | I792511 |
| IPC | G06T 1/40(2006.01); G01N 3/08(2006.01); G06K 9/78(2006.01) |
| State | Published - 11 02 2023 |
Bibliographical note
公開公告號: I792511Announcement ID: I792511