Image data processing method and device

Abstract

The embodiment of the invention discloses an image data processing method and device. The method comprises the following steps: obtaining the original image information including a target object; detecting a plurality of pixel points in the original image information based on a first neural network model; and setting a corresponding mask value for each pixel point according to the detection result; dividing the original image information according to the pixel value and the mask value of each pixel point in the original image information to obtain a foreground area including the pixel point having the first mask value as a target area corresponding to the target object; identifying the target object in the target area, and determining the corresponding physical sign classification information of the target object according to the recognition result; and searching material information matching with physical sign classification information is searched, and integrating the searched material information to generate the first virtual character data corresponding to the target object. By adopting the invention, the identification efficiency and the identification accuracy of the data canbe improved, and the display effect of the image data can be enriched.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to an image data processing method and device. Background technique [0002] With the rapid development and popularization of computers, the Internet, and mobile phones, virtual pets are gradually emerging. Existing virtual pets are often virtual images obtained by man-made image processing on original images. That is, when the terminal acquires an original picture of a pet dog, it can artificially process the image data of the area where the pet dog is located on the basis of the original picture of the pet dog. The dog's nose is enlarged, reduced or replaced to obtain the corresponding virtual image of the pet dog. It can be seen that the virtual image obtained after image processing and the original image still have the same variety attributes, which leads to a relatively single display effect of the image data after image processing. [0003] In addition, for some existi...

AI Technical Summary

Problems solved by technology

It can be seen that the virtual image obtained after image processing and the original image still have the same variety attributes, which leads to a relatively simple display effect of the image data after image processing

[0003] In addition, for some existing image processing technologies (for example, automatically enlarging or reducing the eyes of the pet dog in the original image), it is necessary to identify the entire original image in advance to find out the eyes of the pet dog. , when there is a large amount of background data in the original image, these background data will generate a large amount of redundant data processing in the process of recognizing the pet dog's eyes, which reduces the data recognition efficiency, and a large amount of background data It will also interfere with the recognition of the pet dog's eyes, and even cause false recognition, thereby reducing the recognition accuracy of the image data

Images