| CPC G06V 10/774 (2022.01) [G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06V 2201/06 (2022.01)] | 17 Claims |
|
1. An image processing system comprising:
a vision sensor that obtains an original image in which an object is captured;
a first detector that receives the original image from the vision sensor and uses a model pattern to detect the object contained in the original image, the model pattern being generated based on a physical quantity of each of a plurality of feature points of the object and representing one or more features of the object, the first detector detecting the object contained in the original image by performing matching between the feature points of the object and feature points constituting the model pattern;
a learning device that receives the original image from the vision sensor and learns a learning model using the original image as input data, and using a first detection result of the object contained in the original image detected by performing the matching between the feature points of the object and the feature points constituting the model pattern by the first detector as training data; and
a second detector that detects the object contained in the original image based on the learning model learned by the learning device and outputs a second detection result by the second detector to a user.
|