Human image segmentation method and mobile terminal

Abstract

The invention discloses a human image segmentation method. The method is suitable for being executed in a mobile terminal, and comprises the following steps of: segmenting a to-be-processed image by utilizing a predetermined segmentation network, wherein the predetermined segmentation network comprises an encoding stage and a decoding stage, the encoding stage comprises a first number of pairs ofconvolution layers and down-sampling layers, which are connected in sequence, and each pair of convolution layer and down-sampling layer forms a convolution-down-sampling pair; outputting a down-sampling characteristic pattern of the encoding stage after carrying out iteration through a first number of convolution-down-sampling pairs, wherein the decoding stage comprise a first number of pairs ofconvolution layer and up-sampling layers, which are connected in sequence, and each pair of convolution layer and up-sampling layer forms a convolution-up-sampling pair; and outputting a segmentationresult map after carrying out iteration through the first number of convolution-up-sapling pairs. The invention furthermore discloses the corresponding mobile terminal.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a portrait segmentation method and a mobile terminal. Background technique [0002] Image segmentation is a basic application in image processing. It can accurately segment the part of the image that needs to be processed, which will help to improve the final processing effect. With the increasing application of mobile terminals, users can use mobile terminals to take portraits, and then automatically segment the portraits to add many other special effects, such as depth of field, changing background, other AR effects, and so on. [0003] Existing image segmentation schemes, one is to directly use image editing software such as Photoshop, users need to be proficient in various operations of Photoshop, and even need to have certain practical experience, which has high requirements for operators; and Photoshop cannot implemented on mobile terminals. The other is to perfo...

AI Technical Summary

Problems solved by technology

It is not ideal for complex background or clothing segmentation, and the method based on color prior will also be affected by lighting, making positioning errors

[0005] The semantic segmentation method based on deep learning can better deal with complex situations in portrait segmentation processing, but the existing network model is generally relatively large, takes a long time to run, and takes up a lot of memory, which is not suitable for use on mobile terminals.

Images