Image processing method and device

Abstract

The invention relates to an image processing method and device. The method comprises the steps that the depth image of a shoot target and at least one pixel in a portrait area of the depth image are acquired; the average depth value of pixels in the portrait area is calculated according to the depth value of pixels in the portrait area; the difference between the depth value of pixels adjacent tothe portrait area in the depth image and the average depth value is calculated; pixels whose difference is less than a preset threshold are determined as pixels in the portrait area, and the step is repeated until pixels whose difference is less than the preset threshold are nonexistent; and an area other than the portrait area in the depth image is determined as the background area of the depth image. According to the invention, the portrait area and the background area in the depth image are accurately divided to ensure the background blur effect of an RGB image; the background blur effect of a single lens reflex is simulated to the greatest extent; and the user experience is improved.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, to an image processing method and device. Background technique [0002] SLR cameras can take portrait photos with background blur effects, which have a strong visual impact. The background blur effect has the following characteristics: 1) The image of the foreground portrait that is focused should be clear; 2) The image of the background scenery outside the portrait is blurred; 3) The farther the background scenery is from the portrait, the greater the degree of blur, and vice versa. That is, the degree of blur varies with the depth of field; 4) The bilinear problem of out-of-focus imaging. [0003] In related technologies, a red-green-blue (RGB) camera is configured in a mobile phone, and a portrait segmentation algorithm based on RGB images is used to segment the human body part and the surrounding background part in the RGB image. After the segmentation is...

AI Technical Summary

Problems solved by technology

The background blur effect has the following characteristics: 1) The image of the foreground portrait that is focused should be clear; 2) The image of the background scenery outside the portrait is blurred; 3) The farther the background scenery is from the portrait, the greater the degree of blur, and vice versa. That is, the degree of blur varies with the depth of field; 4) The bilinear problem of out-of-focus imaging

Images