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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com