Element representation-based polygon detection method in digital image
A digital image and detection method technology, applied in image analysis, image data processing, instruments, etc., can solve the problem of not being able to know the polygon type in advance, and achieve the effect of wide applicability
Inactive Publication Date: 2011-12-14
HENAN POLYTECHNIC UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] On the one hand, the various existing polygon detection algorithms are still aimed at the detection of certain specific polygons (such as triangles, rectangles, etc.), and few algorithms can be used for simultaneous detection of various polygons; on the other hand, in many images In tasks such as recognition analysis, the type of polygon cannot be known in advance
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] Such as figure 1 Shown is the flowchart of the polygon detection method based on the primitive representation in the digital image of the present invention, comprising: collecting the image and inputting it into the computer; calculating the direction descriptor of each point in the image; using the direction descriptor to detect the feature points in the image; Obtain the 1-dimensional primitive determined by the feature points; verify and combine two 1-dimensional primitives to obtain a 2-dimensional primitive; verify and combine the obtained 2-dimensional primitive and 1-dimensional primitive to obtain a triangle or 3-dimensional primitive; combine the obtained 3-dimensional Verification and combination of dimensional primitives and 1-dimensional primitives to obtain quadrilaterals or 4-dimensional primitives; verification and combination of n-dimensional primitives and 1-dimensional primitives obtained by the same process as the previous step to obtain n+1-dimensiona...
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 element representation-based polygon detection method in a digital image, which comprises the following steps of: acquiring an image and inputting the image into a computer; computing direction descriptors of each point in the image; detecting characteristic points in the image by means of direction descriptors; obtaining one-dimensional elements defined by the characteristic points; combining with the two one-dimensional elements in a checking way to obtain two-dimensional elements; combining the two-dimensional elements with the one-dimensional elements in a checking way to obtain triangular or three-dimensional elements; combining the obtained three-dimensional elements with the one-dimensional elements in a checking to obtain quadrangular or four-dimensional elements; combining n-dimensional elements which are obtained by the same former processing step with the one-dimensional elements in a checking way to obtain n+1 polygonal or n+1-dimensional elements; and repeating the former step till that the elements with higher dimensions can not be obtained. The method can detect various polygons in the image and has wide applicability.
Description
technical field [0001] The invention relates to the field of automatic detection of image features in computer vision, in particular to a method for detecting polygons in digital images. Background technique [0002] Polygon detection has important applications in computer vision and pattern recognition systems. For example, for buildings and other artificial scenes mainly composed of lines, polygon detection is often a necessary step for tasks such as recognition and analysis. At present, the existing polygon detection algorithm mainly detects a specific type: Aarts et al. first detect the boundary of the target, and then establish a regression function and then build a model. If the model satisfies the triangle condition, the detected target is a triangle. . Ge et al. proposed a method of detecting targets using symmetry, combining the number of sides and the angles of the sides to be detected, and using symmetry to locate the center point of the target to achieve target ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/13
Inventor 刘红敏王志衡朱世松贾宗璞侯占伟
Owner HENAN POLYTECHNIC UNIV