Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Saliency detecting method applied to static image human segmentation

A static image and detection method technology, applied in the field of image processing, can solve the problems of low salient value, low salient value, and the skin color of the human body does not appear very prominent.

Active Publication Date: 2015-12-02
GUANGDONG UNIV OF TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the current image saliency detection algorithms assign higher saliency values ​​to areas with prominent image features and concentrated distribution, and lower saliency values ​​to other areas to facilitate subsequent image processing, but this method is not suitable for static images. Human Body Segmentation of Images
Human skin color is an indispensable part of human body segmentation, but human skin color does not appear very prominent in static images, and the distribution of skin color is wide, and the saliency value in image saliency detection is not high, so if the traditional saliency detection is still used method, in the later stage of human body segmentation, part of the skin color is often removed due to the low saliency value, which seriously affects the human body segmentation effect of static images

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Saliency detecting method applied to static image human segmentation
  • Saliency detecting method applied to static image human segmentation
  • Saliency detecting method applied to static image human segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] refer to Figure 6 , the saliency detection method of the present invention mainly includes six aspects: image segmentation, human face detection, skin color detection, color uniqueness calculation, color space distribution calculation and saliency map calculation. The contents of these six aspects are introduced in detail below.

[0096] (1) Image preprocessing

[0097] Image preprocessing is mainly divided into three parts, namely image segmentation, face detection, and skin color detection.

[0098] (1) Image segmentation

[0099] The invention divides the image to be detected into superpixels, and uses the superpixels as calculation objects to reduce the amount of calculation. This embodiment adopts the improved SLIC superpixel segmentation method, performs K-means clustering according to the geodesic image distance in CIELab space, and generates a superpixel segmented image with substantially uniform size and color boundaries, such as Figure 7 (a) shown.

[0...

no. 2 example

[0134] Such as Figure 8 and 9 Shown, (SFa) is the color uniqueness saliency map that adopts SF (saliency filter) method to obtain, (Oursa) is the color uniqueness saliency map that adopts the method of the present invention to obtain, (SFb) is that adopts SF method to obtain Color space distribution saliency map, (Oursb) is a color space distribution saliency map obtained by the method of the present invention, (SFc) is a saliency map that combines uniqueness and spatial distribution obtained by using the SF method, (Oursc) is a saliency map obtained by using the method of the present invention The method obtains a saliency map that combines uniqueness and spatial distribution. pass Figure 8 and Figure 9 It can be seen from the comparison that the method of the present invention has significantly improved the detection effect of the salience of skin color.

[0135] In order to better illustrate this point, an example will be used below to illustrate the final realizatio...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a saliency detecting method applied to static image human segmentation. The method comprises the following steps of performing superpixel segmentation on a static image to be detected; performing face detection on the image after the superpixel segmentation to acquire a face area; performing skin color detection on the face area to acquire skin color information; performing color uniqueness calculation and color spatial distribution calculation according to the skin color information to acquire a color uniqueness value with the skin color information fused therein and a color spatial distribution value with the skin color information fused therein; performing saliency calculation according to the acquired color uniqueness value and the color spatial distribution value to acquire a saliency map used for static image human segmentation. Based on a conventional saliency detecting method, the method provided in the invention makes the skin color well detected by making the skin color information fused in the color uniqueness calculation and color spatial distribution calculation. The human skin color saliency is enhanced. Better and more accurate static image human segmentation effects are achieved. The method can be widely applied to the image processing field.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a saliency detection method applied to still image human body segmentation. Background technique [0002] A salient region in an image refers to the target region that is most concerned by human vision in a picture. Image saliency detection, as an important research topic in computer vision, is a technology that generates image saliency maps by analyzing salient regions in images based on features such as image color, intensity, direction, and edges. The saliency map generated by image saliency detection can be used in many image processing fields such as retrieval of similar images, image and video compression, detection of specific objects in images, image and video segmentation, etc., thereby improving the performance of image processing and promoting these fields. development of. [0003] Most of the current image saliency detection algorithms assign higher saliency values ​...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00
Inventor 曾碧何元烈陈佳洲马晓东
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products