Supercharge Your Innovation With Domain-Expert AI Agents!

Non-component recognition method of architectural drawings based on SSD model

A technology of architectural drawings and recognition methods, applied in character and pattern recognition, computer parts, instruments, etc., can solve problems such as slow convergence speed, consumption, and low recognition accuracy, and achieve the effect of improving efficiency

Active Publication Date: 2019-01-01
HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The traditional drawing training method consumes a lot of computer resources and a lot of time to train the data set, the final convergence speed is very slow, and the final recognition accuracy is not high, so the training and recognition effect of architectural drawings is not optimistic , so the effect obtained by using this kind of drawing training and recognition method cannot meet the application requirements

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
  • Non-component recognition method of architectural drawings based on SSD model
  • Non-component recognition method of architectural drawings based on SSD model
  • Non-component recognition method of architectural drawings based on SSD model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0055] Such as Figure 1-4 As shown, the present invention provides a method for identifying non-components of architectural drawings based on the SSD model, comprising the following steps:

[0056] Step 1: traverse all architectural drawings in PDF format, obtain the original drawing file information set and drawing file sets G1 and G2, and perform format conversion and drawing preprocessing on G2 at the same time, and obtain the preprocessed JPG format drawing file set G3, specifically method s...

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 discloses a non-component identification method of architectural drawings based on SSD model. Firstly, the architectural drawings are converted from PDF format to JPG format by using a rendering library MuPDF of Python, and the architectural drawings are pretreated by grayscale, expansion corrosion and other methods. Then, according to different attenuation learning rates, SSD algorithm is used to train the pre-processed building drawings, and the convergence rate and recognition accuracy of the model under different attenuation learning rates are compared to obtain the optimal non-component detection model set. The method of the invention effectively improves the non-component detection method of the building drawing, accelerates the convergence speed of the training, improves the identification accuracy of the non-component of the building drawing, and increases the use value of the non-component detection model.

Description

technical field [0001] The invention belongs to the field of image processing and image recognition, and particularly designs a non-component recognition method for architectural drawings of SSD models. Background technique [0002] The non-component recognition method of architectural drawings in the present invention has great effect and significance on the traditional supervised recognition of architectural drawings. When faced with the recognition problem of architectural drawings, researchers will choose to preprocess the drawings or adjust the parameters of the training model to speed up the convergence speed and improve the accuracy of recognition, and optimize the SSD model to provide efficient knowledge services and services for related systems. Individualized work assignment programs. [0003] The existing research bases of Feng Wanli, Zhu Quanyin and others include: Wanli Feng. Research of theme statement extraction for chinese literature based on lexical chain. ...

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): G06K9/00G06K9/66
CPCG06V30/422G06V30/194
Inventor 朱全银潘阳周蕾王留洋宗慧冯万利金鹰
Owner HUAIYIN INSTITUTE OF TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com