Unlock instant, AI-driven research and patent intelligence for your innovation.
Salient region detecting method combining spatial distribution and global contrast
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of spatial distribution and global comparison, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem of low efficiency of distinguishing regions
Inactive Publication Date: 2012-07-04
HARBIN INST OF TECH
View PDF4 Cites 10 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to solve the problem that the existing salient region detection method does not consider the influence of spatial distribution factors on regional saliency, which makes the judgment efficiency of salient regions low, a salient region detection method that combines spatial distribution and global comparison is provided.
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach 1
[0032] Specific implementation mode one: the following combination figure 1 Describe this embodiment, the salient region detection method that combines spatial distribution and global contrast described in this embodiment, it comprises the following steps:
[0033] Step 1: Segment the input image according to the graph-cutimage segmentation method to obtain N sub-image regions, where N is an integer greater than or equal to 2;
[0034] Step 2: Calculate each sub-image region r k The spatial distribution of the significant value S sd (r k ), k represents the serial number of the sub-image area, and takes a value from 1 to N;
[0035] Step 3: Calculate each sub-image region r k The global contrast saliency value S of rc (r k );
[0036] Step 4: According to the spatial distribution saliency value S obtained in Step 2 and Step 3 sd (r k ) and the global contrast saliency value S rc (r k ), calculate the sub-image area r k The significant value S(r k );
[0037] Ste...
specific Embodiment approach 2
[0039] Specific Embodiment 2: This embodiment is a further description of Embodiment 1. In the step 2, each sub-image area r is calculated k The spatial distribution of the significant value S sd (r k ) specific method is:
[0040] First, calculate the sub-image region r k The mean value of the x component of the coordinates of all pixels in the and y-component mean
[0041] x r k ‾ = Σ i = 1 M x r k i M ,
[0042] y r k ‾ = Σ ...
specific Embodiment approach 3
[0050] Embodiment 3: This embodiment is a further description of Embodiment 2. In the step 3, each sub-image area r is calculated k The global contrast saliency value S of rc (r k ), using the formula:
[0051] S rc ( r k ) = Σ r k ≠ r l exp ( - D S ( r k , r l ) / δ s 2 ) ω ( r l ) D ...
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
Login to View More
Abstract
A salient region detecting method combining spatial distribution and global contrast belongs to the technical field of saliency detection and solves the problem that the judgment efficiency of a salient region is low as an existing salient region detecting method neglects the influence of a spatial distribution factor on region saliency. The salient region detecting method includes: segmenting input images by a graph-cutimage segmentation method to obtain N sub-image zones; computing spatial distribution saliency Ssd (rk) of each sub-image zone rk; computing global contrast saliency Src (rk)of each sub-image zone rk; computing saliency S (rk) of each sub-image zone rk according to the spatial distribution saliency Ssd (rk) and the global contrast saliency Src (rk); and marking the saliency S (rk) of the N sub-image zones in the sequence from high to low to obtain salient regions of the input images and detect the salient regions of the input images. The salient region detecting method is applicable to detection of the salient regions of the input images.
Description
technical field [0001] The invention relates to a salient area detection method combining spatial distribution and global contrast, and belongs to the technical field of salient detection. Background technique [0002] The human visual system can quickly detect important or interesting regions from images or videos to reduce the amount of computation. It is well known that visual saliency plays a very important role in making those important or interesting regions "stand out" from their surroundings and thus attract human attention. Therefore, saliency detection is an indispensable and important part of visual attention theory. At present, visual detection has been widely used in object detection, image cropping, image browsing and image / video compression and other fields. [0003] Saliency detection is mainly divided into two categories: bottom-up saliency detection and top-down saliency detection. Bottom-up saliency detection methods refer to those detection mechanisms ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More