Method for carrying out segmentation and depth-of-field rendering on monocular portrait based on WNET

Abstract

The invention discloses a method for carrying out segmentation and depth-of-field rendering on a monocular portrait based on WNET. A WNET network parameter model is constructed by superposing UNET, the trained WNET network parameter model is loaded into a mobile client, preliminary segmentation of a portrait picture is realized in the mobile client, and a mask image subjected to preliminary segmentation is zoomed to the size of an original image by adopting a bilinear interpolation method; morphological operation is carried out on the mask image, corrosion and expansion processing is carried out on the mask image, connected regions with edges not in a preset region are removed, remaining connected regions are reserved, edge refinement processing is carried out to obtain a portrait mask image, and the separated foreground and the background after Gaussian blur are synthesized to obtain a depth-of-field rendering image; according to the method, the calculation amount and the model size can be greatly reduced, and the portrait segmentation precision is improved, so that portrait depth-of-field rendering of the monocular camera of the mobile terminal is realized.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for segmenting and rendering a monocular portrait based on WNET. Background technique [0002] With the popularity of smart phones and the improvement of mobile computing performance, there are more and more applications for mobile portrait processing, and real-time portrait segmentation is becoming more and more important. With the rise of deep learning in recent years and the outstanding performance of CNN networks in the field of image processing, image segmentation using CNN has gradually become the mainstream and is also the best choice. More and more people are beginning to use FCN networks for front-end feature extraction. Conditional random fields or hidden Markov do back-end processing. This method improves the accuracy to a certain extent, but such a network model is too time-consuming to be real-time on the mobile terminal. [0003] We design a simpl...

AI Technical Summary

Problems solved by technology

Although the method based on dual cameras can achieve the effect of blurring the background, such equipment needs to be equipped with dual cameras, which increases the cost. Therefore, it is particularly necessary to develop a depth-of-field rendering method based on a single camera.

Images