Method and apparatus for processing image

An apparatus for processing an image, the apparatus comprising:

• at least one processor;
• and
• a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
• acquiring a target image comprising a polygon image;
• inputting the target image into a pre-trained convolutional neural network to obtain a characteristic vector of the target image, the convolutional neural network being used to represent a correspondence relationship between an image and a characteristic vector, and the characteristic vector being a vector comprising a category feature, a position feature, and a keypoint feature of the polygon image;
• and
• recognizing an image area of the polygon image based on the category feature, the position feature, and the keypoint feature, wherein the recognizing an image area of the polygon image based on the category feature, the position feature, and the keypoint feature, comprises:
• inputting an attribute feature into a pre-trained model to obtain an attribute of the polygon image, wherein the pre-trained model is configured to represent a correspondence relationship between the attribute feature and the attribute of the polygon image, wherein the attribute feature comprises at least one of the category feature, the position feature, or the keypoint feature, and the attribute comprises at least one of a category, a position or a keypoint.

A non-transitory computer storage medium, storing a computer program, the computer program, when executed by a processor, causes the processor to perform operations, the operations comprising:

• acquiring a target image comprising a polygon image;
• inputting the target image into a pre-trained convolutional neural network to obtain a characteristic vector of the target image, the convolutional neural network being used to represent a correspondence relationship between an image and a characteristic vector, and the characteristic vector being a vector comprising a category feature, a position feature, and a keypoint feature of the polygon image;
• and
• recognizing an image area of the polygon image based on the category feature, the position feature, and the keypoint feature, wherein the recognizing an image area of the polygon image based on the category feature, the position feature, and the keypoint feature, comprises:
• inputting an attribute feature into a pre-trained model to obtain an attribute of the polygon image, wherein the pre-trained model is configured to represent a correspondence relationship between the attribute feature and the attribute of the polygon image, wherein the attribute feature comprises at least one of the category feature, the position feature, or the keypoint feature, and the attribute comprises at least one of a category, a position or a keypoint.