inspection target defect detection method based on feature point detection and an SVM classifier
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 feature point detection and target defect technology, applied in the field of computer vision, to achieve the effect of high environmental adaptability, reduced detection error, and low computational complexity
Active Publication Date: 2019-05-24
BEIJING AEROSPACE FUDAO HIGH TECH
View PDF5 Cites 11 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
[0009]
For this reason, the present invention provides a detection method of inspection target defect based on feature point detection
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
Embodiment 1
[0114] In this embodiment, the detection method is used to detect the missing parts of the simulation equipment, wherein the detection target selected in this embodiment is a nut, and the simulation equipment is completed by embedding studs on the foam board and randomly installing nuts on the studs .
[0115] Use the above steps to detect the analog device, the detection steps are as follows:
[0116] Step A: Obtain the inspection target image captured in real time, and perform grayscale value transformation on it, and convert the image from RGB space to grayscale space;
[0117] Step B: use the maximum inter-class variance method and the SUSAN edge detection method to process the converted inspection map to determine the candidate area of the target to be inspected;
[0118] Step C: Filter and fuse the candidate regions according to the shape features of the target to be detected, so as to delete the falsely detected target regions;
[0119] Step D: Extract LBP and LPQ f...
Embodiment 2
[0127] In this embodiment, the detection method is used to detect missing parts of the field equipment, wherein the detection target selected in this embodiment is the handwheel. And the detection steps are the same as those in Example 1.
[0128] After the image collected in this embodiment is processed by the step A, it is converted from an RGB image to a grayscale image. After the conversion, the target area in the image is selected using the maximum inter-class variance method and the SUSAN edge detection method, and the processed image Image feature edge connectivity areas such as Figure 6 as shown in (a);
[0129] After the selection is completed, mark the selected target areas with the circumscribed candidate boxes, and the marking results are as follows Figure 6 as shown in (b);
[0130] After the candidate frame marking is completed, the overlapped candidate frames are fused by bringing the overlap rate into the matrix calculation. The result after fusion is as f...
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 relates to an inspection target defect detection method based on feature point detection and an SVM classifier, and the method comprises the steps: obtaining an inspection target image which is shot in real time, and carrying out the gray value transformation of the inspection target image; processing the converted image by using a maximum between-cluster variance method and a SUSANedge detection method, and determining a candidate region of the to-be-detected target; screening and fusing the candidate areas according to the shape characteristics of the to-be-detected target; and performing LBP and LPQ feature extraction on the processed candidate region, fusing the LBP and LPQ features, and inputting the fused LBP and LPQ features into a pre-trained SVM classifier for classification and recognition. Compared with a traditional template matching method, the detection method disclosed by the invention does not need to carry out early-stage complex registration work on thetwo images, and meanwhile, by adopting a mode of combining LBP and LPQ characteristics, the target characteristics can be described more accurately, and the accuracy of a defect recognition result isimproved; The method is simple to operate, has high environmental adaptability, and can meet the requirement for identifying the integrity of parts of the oil extraction equipment.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a target defect detection method based on feature point detection and SVM classifier. Background technique [0002] Target defect detection is an important content in the field of computer vision. For traditional defect detection, the basic operation is to use the method of template matching. First, image registration technology needs to be used to convert the image to be inspected and the reference image into the same imaging space. , and then make the residual between the reference image and the converted inspection image to directly determine whether the target to be inspected is missing. [0003] Due to the harsh environment and climate in most oil fields, oil production equipment is exposed to wind and sand all the year round, and oil corrosion and other conditions will deform the appearance of bolts, handwheels and other parts on the equipment. In this case, using ...
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