Graphics-based component identification method, system and device and storage medium
A recognition method and component technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems that affect data processing, component position deviation, and component recognition results that do not meet the background of distribution box quotation business. Requirements and other issues, to achieve the effect of accurate identification range and easy data processing
Active Publication Date: 2019-02-22
广州算易软件科技有限公司
View PDF6 Cites 11 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the current image recognition technology can only roughly identify the position of components, but there may be deviations in the position of components in the recognition results, and the recognition results of some components may not meet the requirements of the distribution box quotation business background, affecting subsequent data processing
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
[0039] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0040] refer to figure 1 , a graph-based component recognition method, comprising the following steps:
[0041] S1. Obtain the electrical drawing to be tested; the electrical drawing can be a CAD drawing or a picture of a common electrical drawing, but the electrical drawing to be tested should conform to the electrical drawing standard.
[0042] S2. Input the electrical drawing to be detected into the trained image recognition model, and obtain the recognition result of each component in the electrical drawing to be detected. The image recognition model can be realized by using a deep convolutional neural network. In this step, the trained image recognition model is used to perform image recognition on the electrical drawings, and the components in the electrical drawings are recognized therefrom. The recognition results are relatively rough....
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 graphics-based component identification method, system and device and a storage medium. The method comprises the following steps: obtaining an electric drawing to be detected; inputting the electric drawings to be detected into the trained image recognition model, and obtaining the recognition results of each component in the electric drawings to be detected. According tothe constituent elements of each component, the identification results of each component are modified to obtain the smallest rectangular bounding frame of each component. The invention recognizes thecomponents from the electric drawing through the image recognition model, and modifies the image recognition result according to the constituent elements of each component to obtain the smallest rectangular bounding frame of the component, so that the identification range of the component is more accurate and the subsequent data processing is convenient. The invention can be widely applied in thefield of artificial intelligence.
Description
technical field [0001] The invention relates to the field of artificial intelligence, in particular to a graphic-based component recognition method, system, device and storage medium. Background technique [0002] In the electrical industry, quoters need to make a list of components based on the CAD electrical design drawings obtained from customers. The list is the most important link in the complete set of electrical quotation, and it is the basis of the complete set of electrical quotation. As a boring and cumbersome link, but it also requires the quotation staff to have certain professional knowledge, the traditional complete electrical quotation method is mainly to extract the component text by manually inputting Excel or using software, and fill it out manually. The quotation list is summarized for the corresponding component types, and finally the quotation is quoted according to such a list. Among them, in the process of making the list, the component types of thes...
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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/214
Inventor 詹建州吴贺扬孙尔安赵引
Owner 广州算易软件科技有限公司