Automatic detection method of salient object based on salience density and edge response
An edge response and automatic detection technology, which is applied in image data processing, instruments, calculations, etc., can solve the problems of low detection accuracy of salient objects and does not consider the edge attributes of salient objects, etc., and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0013] Specific implementation mode one: the following combination figure 1 To illustrate this embodiment, the salient object automatic detection method based on saliency density and edge response described in this embodiment includes the following steps:
[0014] Step 1. Calculate and generate a saliency map S of the input image according to a saliency calculation method combining global color contrast and color space distribution;
[0015] Step 2. On the saliency map S, use a set of Gabor filters to generate an edge response map E;
[0016] Step 3. Use the branch-and-bound algorithm that maximizes saliency density and edge response to search for globally optimal sub-windows containing salient objects in the input image ;
[0017] Step 4: Locate the optimal sub-window in Step 3 As input, initialize the GrabCut image segmentation method;
[0018] Step 5. Run the GrabCut image segmentation method to automatically extract salient objects with very good edges.
[0019] The...
specific Embodiment approach 2
[0020] Specific embodiment 2: This embodiment is a further description of specific embodiment 1. In step 1, the calculation formula used to generate the saliency map method of the input image according to the regional saliency method combined with global color contrast and color space distribution is:
[0021] S ( r k ) = 1 2 ( N ( S sd ( r k ) ) + N ( S rc ( r k ) ) ) ; ...
specific Embodiment approach 3
[0023] Specific embodiment three: this embodiment is a further description of specific embodiment one. In step two, a group of Gabor filters are used on the saliency map S to generate the method for edge response map E. The calculation formula used is:
[0024] E ( p ) = max i = 1 15 | ( S * G i ) ( p ) | 2 ; - - - ( 2 )
[0025] In the formula, E(p) represents the edge response corresponding to pixel p, the symbol * represents the convolution operation...
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