On-line multi-stroke axonometric sketch clustering method based on common boundaries of regions

A clustering method and stroke technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of poor practicability and achieve good practicability

Active Publication Date: 2018-01-09
NORTHWESTERN POLYTECHNICAL UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the poor practicability of the existing sketch clustering methods, the pr...

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
  • On-line multi-stroke axonometric sketch clustering method based on common boundaries of regions
  • On-line multi-stroke axonometric sketch clustering method based on common boundaries of regions
  • On-line multi-stroke axonometric sketch clustering method based on common boundaries of regions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] refer to Figure 1-7 . The specific steps of the online multi-stroke axonometric sketch clustering method based on the regional common boundary of the present invention are as follows:

[0032]Step 1: Obtain the closed area of ​​the sketch and its boundary tolerance zone based on image processing technology, which is divided into three steps:

[0033] Step 1.1: Use the existing segmentation method based on the trapped ball to extract the closed area of ​​the sketch, and the initial radius of the trapped ball is 8 pixels.

[0034] Step 1.2: Carry out the processes of dilation, erosion and the difference between the two in turn for each sketch area, and obtain the annular tolerance band surrounding the border of the sketch area, referred to as the area boundary band, whose width is l r The radius m of the minor axis of the ellipse circumscribing the region r Depends on: α is the empirical coefficient, take 1.1.

[0035] Step 1.3: First, use a circular structural ele...

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 an on-line multi-stroke axonometric sketch clustering method based on common boundaries of regions, and is used for solving the technical problem of poor practicability of an existing sketch clustering method. The technical scheme includes the steps of first obtaining a closed region formed by sketch strokes and an annular tolerance band surrounding a region boundary through image processing; then performing segmentation on cross-region strokes whose trajectories exceed any sketch region boundary zone, and clustering short strokes which belong to a boundary zone of twoadjacent regions together; simplifying clustered multi-stroke groups in sequence to obtain a single-stroke sketch; and merging adjacent single strokes according to a primitive identification result ofa long stroke after connection and an original input stroke, and performing pixel identification and fitting. The method does not limit the overlapping degree and primitive type of strokes to be clustered, can handle a multi-stroke repeated drawing situation, and can also handle a multi-stroke non-repeated drawing situation, thereby efficiently converting an on-line multi-stroke drawn axonometricsketch into a two-dimensional line graph, and the practicability is good.

Description

technical field [0001] The invention relates to a sketch clustering method, in particular to an online multi-stroke axonometric sketch clustering method based on a common boundary of a region. Background technique [0002] Sketch-based 3D reconstruction technology has been extensively studied, with the aim of providing users with a more intuitive and realistic sketch interface. Due to the three-dimensional and intuitive nature of the axonometric drawing, it can help people understand the product structure faster and more clearly, so the 3D reconstruction technology based on sketches generally starts with drawing the axonometric drawing of the object. Multi-stroke drawing, especially the phenomenon of repeated multi-stroke drawing is very common in the concept design stage, and designers often use multiple strokes to draw the outline of the product. Transforming rough sketches into clean line drawings is an important step in sketch-based 3D reconstruction techniques. How to...

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
IPC IPC(8): G06K9/62G06T7/11G06T7/136
Inventor 王淑侠王守霞荆晓珂何卫平
Owner NORTHWESTERN POLYTECHNICAL 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