Unlock instant, AI-driven research and patent intelligence for your innovation.
Method for detecting binary robust scale invariable feature of color of color image
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 scale-invariant feature, color image technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as inapplicability to color images, and achieve the effect of good color invariance
Inactive Publication Date: 2015-02-11
HARBIN INST OF TECH
View PDF2 Cites 0 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] The purpose of the present invention is to solve the problem that the current method based on binary descriptor robust scale invariant features is not suitable for color images. The present invention provides a binary robust scale invariant feature detection method suitable for color 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
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
[0015] Specific implementation mode 1: Combination figure 1 To explain this embodiment, the binary robust scale-invariant feature detection method suitable for color image color in this embodiment includes the following steps:
[0016] Step 1: Convert the color image to be detected from RGB color space to Gaussian opposition color space;
[0017] Step 2: Calculate the color invariant of the color image transformed into the Gaussian opposition color space;
[0018] Step 3: According to the color invariant obtained in Step 2, use the AGAST feature detector to detect the feature points of the color image;
[0019] Step 4: Obtain 60 sampling points normalized by the direction in the area around each feature point detected in Step 3;
[0020] Step 5: Generate a binary descriptor about the color information of the pixels around the feature point according to the sampling points obtained in Step 4;
[0021] Step 6: According to the binary descriptors related to the color information of the pix...
specific Embodiment approach 2
[0023] Embodiment 2: This embodiment is a further limitation of the binary robust scale invariant feature detection method suitable for color image color in Embodiment 1. In the step 1, the color image to be detected is changed from RGB color The method of transforming space to Gaussian opposition color space is:
[0024] E ^ ( x , y ) E λ ^ ( x , y ) E ^ λλ ( x , y ) = 0.06 0.63 0.27 0.30 0.04 - 0.35 0.34 - 0.60 0.17 R ( x , y ) G ( x , y ) B ( x , y )
[0025] Where R (x, y), G (x, y), and B (x, y) are the three color components of R, G, and B of the pixel with coordinates (x, y) in the color image to be detected, Is the brightness component of the color image to be detected in the Gaussian opposite color space, Is the blue-yellow color component of the color image to be detected in the Gau...
specific Embodiment approach 3
[0026] Embodiment 3: This embodiment is a further limitation of the binary robust scale-invariant feature detection method suitable for the color of color images described in Embodiment 1. In the second step, the color converted to the Gaussian opposing color space is calculated. The method of image color invariance is:
[0027] C = E ^ λλ E ^
[0028] Where C is the color invariant, Is the luminance component, It is the green-red color component.
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
The invention discloses a method for detecting binary robust scale invariable features of colors of a color image, and relates to a method for detecting binary robust scale invariable features of the colors, to solve the problem that a binary descriptor-method for detecting the robust scale invariable features at present is not applicable to color images. The method comprises the following steps of: firstly, transforming the color image to be detected from an RGB (Red, Green, Blue) color space to a Gaussian opposition color space; secondly, calculating the color invariant of the color image transformed to the Gaussian opposition color space; thirdly, detecting feature points of the color image by using an AGAST (Adaptive and Generic Accelerated Segment Test) feature detector; fourthly, obtaining sixty sampling points subjected to directional normalization in the peripheral region of each detected feature point; fifthly, generating binary descriptors of the color information of the peripheral pixels of relevant feature points according to the obtained sampling points; and sixthly, generating binary descriptors of the binary robust scale invariable features of the colors according to the generated binary descriptors.
Description
Technical field [0001] The invention relates to a color binary robust feature detection method, belonging to the technical field of color image local invariantfeature detection. Background technique [0002] The extraction, description and matching of image features are the basis of feature-based image processing and computer vision applications. The efficiency and accuracy of these image processing and computer vision applications depend on the detection performance of the detector and the characterization performance of the feature descriptor. With the rapid development, popularization and application of digital technology, a large amount of image / video content is generated every day and these visual content need to be processed in real time. Efficient and fast feature detection methods have become the key to meeting the above requirements. However, traditional feature detection methods rely on complex and time-consuming feature detection and descriptor matching processes, s...
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