CPC G06V 10/26 (2022.01) [G06T 7/11 (2017.01); G06V 10/7715 (2022.01); G06V 10/7747 (2022.01); G06V 10/776 (2022.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10081 (2013.01); G06V 10/82 (2022.01); G06V 2201/031 (2022.01)] | 18 Claims |
1. An image processing method, comprising the following steps:
acquiring at least one image-to-be-trained sample and a label segmentation image corresponding to the at least one image-to-be-trained sample;
inputting the at least one image-to-be-trained sample into an image segmentation model to be trained, obtaining a first image feature of a last one output layer in the image segmentation model to be trained and a second image feature of a second last output layer in the image segmentation model to be trained when the at least one image-to-be-trained sample is being extracted by using the image segmentation model to be trained, and based on the first image feature and the second image feature, outputting corresponding segmented-image samples respectively;
based on the label segmentation image and the corresponding segmented-image samples, calculating a model loss function of the image segmentation model to be trained, optimizing a model parameter of the image segmentation model to be trained by using the model loss function, and generating an optimized image segmentation model; and
inputting an acquired image to be processed into the optimized image segmentation model, and generating segmented images corresponding to the acquired image to be processed.
|