Method for positioning region of interest

A technology of region of interest and positioning method, which is applied in the field of image processing and pattern recognition, can solve the problems of insufficient original image features, interference of irradiation angle, and difficult recognition, etc., and achieves extremely easy detection and recognition, strong robustness, Solve the effect that the category is difficult to distinguish

Inactive Publication Date: 2015-02-04
SHANDONG UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There are many coding combinations of two-dimensional codes. For example, Qrcode and Datamatrix barcodes can store up to 2K information, but it will be very difficult to identify them if they store so much information.
The traditional ROI positioning strategy of the region of interest is often a series of complex preprocessing operations such as erosion, sharpening, filtering, denoising, and tilt correction on the original content of the digital image. Even so, a good ROI sense may not be achieved. Region of interest positioning; in addition, these strategies are also very susceptible to interference from light brightness, illumination angle, etc.; in addition, in many occasions, the original features in the image are not obvious enough, and it is very difficult to extract. To locate the region of interest ROI, you need Very complex preprocessing operations, constantly looking for new features to complete the positioning

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
  • Method for positioning region of interest
  • Method for positioning region of interest
  • Method for positioning region of interest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] A method for locating a region of interest, the specific steps comprising:

[0053] A. Paste a two-dimensional code, that is, a Marker, at a certain position on the edge of the region of interest ROI; the determined position means that the region of interest ROI can be located by the size and position of the Marker mark through a scale or other measuring tools;

[0054] B. Detect the Marker mark and locate the ROI region of interest. The specific steps are as follows:

[0055] (1) Image grayscale;

[0056] (2) Image binarization;

[0057] (3) Detect image contour;

[0058] (4) search for possible Marker marks in the image;

[0059] (5) Detect and decode possible Marker marks;

[0060] (6) screen the possible Marker marks after decoding to find out the correct Marker mark;

[0061] (7) Position the region of interest ROI, and complete the positioning of the region of interest ROI according to the determined position of the Marker and the region of interest ROI;

[...

Embodiment 2

[0069] According to a method for locating a region of interest described in Embodiment 1, the difference is that the detection of image contours specifically refers to using the findContours() function in the opencv library to obtain a series of polygonal contours from the image.

Embodiment 3

[0071] According to the positioning method of a region of interest described in Embodiment 1, the difference is that the possible Marker marks in the search image specifically refer to obtaining from the polygon outline through the findMarkerCandidates() method in the MarkerDetector class For possible Marker marks, use the approxPolyDP() function to filter out a convex polygon with 4 vertices from the polygon outline, and detect the side length of the convex polygon. If the minimum side length of the convex polygon is less than 10pixel, it is not considered to be A possible Marker, otherwise, it is considered a possible Marker.

[0072] Only a convex polygon with 4 vertices may be a Marker.

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

No PUM Login to view more

Abstract

The invention relates to a method for positioning a region of interest. The method comprises the specific steps of: A, sticking a two-dimensional code, namely, a Marker label, at a determined position of an edge, of the region of interest; B, detecting the Marker label and positioning the ROI region of interest, wherein the step B specifically comprises the sub-steps of: (1) performing image graying; (2) performing image binaryzation; (3) detecting image profile; (4) searching possible Marker labels in the image; (5) detecting and decoding the possible Marker labels; (6) sieving the decoded possible marker labels and finding a correct Marker label; (7) positioning he region of interest. The Marker label are only black and white in color, so that the image after binaryzation is obvious, and the region of interest can be positioned rapidly and exactly, the image pre-treatment operation is simplified, the condition of light change can be adapted to, and the robustness is very strong.

Description

technical field [0001] The invention relates to a method for locating an area of ​​interest, and belongs to the technical field of image processing and pattern recognition. Background technique [0002] With the development of image processing technology, the application field of automatic positioning method is more and more extensive. In many practical applications, automatically locating the region of interest in an image is the key to the problem and the basis for image analysis and understanding. There are many methods for locating a certain area of ​​an image, among which the template matching locating method, the geometric feature locating method, and the wavelet transform locating method are common. These methods are widely used in face detection, human eye positioning, periodical image file processing systems, license plate recognition and other fields. [0003] There are many coding combinations of two-dimensional codes. For example, Qrcode and Datamatrix barcodes...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/46
CPCG06V10/44G06V10/46
Inventor 姜威于向阳李振宇朱秀娟
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap