Automatic portrait division method

Abstract

An automatic portrait division method disclosed by the present invention comprises the step model training, the portrait initial division and the portrait accurate division, wherein the model training comprises the steps of obtaining the training data, inputting the training data in a neural network, and learning to obtain a network parameter mode; after the neural network converges, storing the network parameter model to finish the model training; the portrait initial division comprises the steps of loading the network parameter model in a mobile client; utilizing the mobile client to obtain an input image; inputting the input image in the network parameter model to obtain a portrait division initial image; and the portrait accurate division comprises the steps of removing the mistakenly divided isolated areas for the portrait division initial image, and retaining a communicated area; utilizing an image matting algorithm to divide the details of the communicated area, and highlighting the edges to obtain a portrait division final image. The automatic portrait division method of the present invention can divide the portrait automatically and accurately, is short in time consumption and small in occupied space, and is suitable for the mobile client.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an automatic portrait segmentation method. Background technique [0002] In recent years, with the development of science and technology, a large number of digital pictures are produced every day, and various image processing technologies are emerging in an endless stream. Among them, the personalized processing of portraits is a very dynamic research field. From skin beautification, facial features beautification, background replacement, every step provides assistance for portrait beautification. Fast and accurate portrait segmentation is the key step of the aforementioned background replacement module. The accuracy of segmentation directly affects the quality and diversity of background replacement, and also affects the consistency of skin beautification. [0003] At present, there are many portrait segmentation algorithms, such as the early interactive segmentation...

AI Technical Summary

Problems solved by technology

The interactive method often requires the user to have a certain understanding of image segmentation, and can draw a better segmentation line. The user experience is slightly worse, and the segmentation speed is relatively slow, usually taking tens of seconds; the segmentation based on crf is also fast Slow; and there are three main problems with the fcn method. One is that the model size is large, usually hundreds of megabytes, which is not conducive to mobile terminals. The other is that the calculation is large and the speed is very slow. Ten seconds; the third is that the calculation process involves pooling layer calculations, which affects the accuracy of segmentation

Images