Method for extracting foreground images

Abstract

The invention discloses a method for extracting foreground images. The method comprises the steps of classification of the field depth of images and segmentation of color information. According to the step of the classification of the field depth of the images, field depth areas of the foreground images, field depth areas of background images and a judgment area where the field depth is not detected are found out by adopting a Kinect device. The method for segmenting the color information includes the first step of converting the images from RGB color space to L*a*b color space, the second step of performing Sobel edge detection on the images, the third step of performing watershed segmentation on edge gradient values obtained from the second step, the fourth step of allowing the L*a*b color information to correspond to the blocks after the watershed segmentation and performing the computation of average values and the computation of the standard deviation, the fifth step of comparing the characteristic values of foreground image areas and the characteristic values of the judgment area, adding the similar areas into the foreground image areas and adding the dissimilar areas into the background images. According to the method for extracting the foreground images, the Kinect classification area is supplemented and corrected by combining the color characteristics of the images, the precision rate of the Kinect device for extracting the foreground images is improved, meanwhile, the operation time for extracting is shortened, and computational efficiency is enhanced.

Description

technical field [0001] The invention relates to the field of image acquisition and processing, in particular to a method for extracting the foreground of an acquired image. Background technique [0002] Among the popular smart devices in recent years, human-computer interaction is emphasized so that people can communicate with machines in a simple, correct and rapid manner. In order to make human-machine interaction richer and more delicate, face recognition can be added. , Gesture recognition and somatosensory recognition and other functions, among them, somatosensory recognition is currently often used in business and entertainment, and is a relatively popular technology. The key to this technology lies in image processing. In the technical field of image processing, it is a complicated problem to effectively cut the foreground image in any scene environment. Although many scholars have proposed various ways to solve it, such as for low depth of field images Carry out cut...

AI Technical Summary

Problems solved by technology

It uses infrared projection to calculate the image depth of field. Since infrared rays may be refracted by smooth objects or absorbed by darker objects during the entire projection process, it will cause the problem that information cannot be received, and the depth information will be lost. Finally, The result of cutting the foreground image with irregular jagged edges or holes

Images