Construction method and matching method of figure and system
A technology of construction method and matching method, which is applied in the field of geometric figure construction and matching, can solve the problem that the image extraction method cannot extract effective features, etc., and achieve the effect of improving matching accuracy, matching efficiency and good matching results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] In this embodiment, a method for constructing geometric figures is provided, which includes the following processes:
[0037] First, extract linear and non-linear geometric shapes. Detect circles and arcs and separate such non-linear primitives to form non-linear graphics, and the remaining part will automatically form linear graphics.
[0038] Then, the attribute information of the straight line figure is determined, and the attribute information includes one or more of the degree of the node, the attribute of the adjacent edge of the node, and the geometric attribute of the node. The degree of a node refers to the number of branches of a straight line connected to this point, that is to say, there are several branches from this point. The adjacent edge attributes of a node include one or two of the maximum edge length of the adjacent edge and the minimum edge length of the adjacent edge. The geometric attributes of the node include the maximum angle, the minimum angle, w...
Embodiment 2
[0045] In this embodiment, a specific application example of a method for constructing geometric figures is provided. The figures in this embodiment are as diagram 2-1 As shown, there are multiple triangular structures for Figure 2-2 The graph in is constructed by feature extraction, and the process is as follows:
[0046] The first step is image preprocessing, key point and circle detection. Because there is no circle in this geometric figure, there are 6 key points, such as Figure 2-2 6 key points shown in.
[0047] The second step is to construct a two-layer attribute graph structure. Since there are only linear graphics in this embodiment, only the attribute information of the linear image needs to be extracted, and there is no need to extract the attribute information of the non-linear graphics.
[0048] Figure 2-3 In, the key points of linear graphics are given.
[0049] In the third step, feature extraction and description of the two-layer geometric map.
[0050] The attrib...
Embodiment 3
[0086] In this embodiment, another application example of extracting graphical features and constructing geometrical figures is given. The figures in this embodiment are as Pic 4-1 As shown, it contains circular and triangular shapes.
[0087] First, extract the linear and non-linear figures in the figure. In the figure, the linear figures are triangles, and the non-linear figures are circles.
[0088] Then, the attribute information is extracted separately for the linear graph and the non-linear graph.
[0089] Figure 4-2 The key points of linear graphics are given in.
[0090] The circle detection method is to obtain the abscissa, ordinate, and radius of the circle center, such as Figure 4-3 , The detection result is: [centerX, centerY, r]=[228,164,139].
[0091] The node coordinates on the straight line graph are:
[0092] Point 1: (8,287)
[0093] Point 2: (183,8)
[0094] Point 3: (354,289)
[0095] Consistent with the method adopted in the foregoing embodiment, the obtained adjace...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com