New Method of Feature Recognition from Engineering Drawings Based on Multi-granularity Information Acquisition

2009 ◽  
Author(s):  
Bangyan Ye ◽  
Jianping Liu ◽  
Bo Wu ◽  
Chunling Wu
Keyword(s):  
Information Acquisition ◽  
Feature Recognition ◽  
New Method ◽  
Engineering Drawings

View Loops Separation from Engineering Drawings Based on Multi-Granularity Information Acquisition

2010 ◽  
Vol 108-111 ◽  
pp. 543-548
Author(s):  
Jian Ping Liu ◽  
Bang Yan Ye ◽  
Jian Xi Peng
Keyword(s):  
3D Reconstruction ◽  
Information Acquisition ◽  
Feature Recognition ◽  
New Method ◽  
Engineering Drawing ◽  
Development Tools ◽  
Engineering Drawings ◽  
Partition Method ◽  
Relationship Of ◽  
Application Module

To improve the validity and efficiency of feature recognition for 3D reconstruction from engineering drawings, this paper presents a new method of view loops separation based on multi-granularity information acquisition. By analyzing the line-frames of combined primitive views and hidden semantics in engineering drawing, combined relationship of graphics primitives can be identified, then applies line-frames partition method of figuration analysis, view loop separation of individual primitive is realized by inertial loop search with pre-set priority. This algorithm is actualized in AutoCAD 2008 platform with development tools of Object ARX2008 and Visual C#2.0. With this algorithm, an application module of 3D intelligent reconstruction system is developed and finally the validity of this research is verified by examples.

Research on the Recognition Method of Exploded Dimension Based on 2D Engineering Drawings

2012 ◽  
Vol 215-216 ◽  
pp. 1169-1172
Author(s):  
Li Xin Wang ◽  
Yan Wang ◽  
Jun Zhou ◽  
Hui Ling Xue
Keyword(s):  
Feature Recognition ◽  
New Method ◽  
Recognition Method ◽  
Bottom Up ◽  
Engineering Drawings ◽  
Feature Information

Dimension feature recognition plays an important role in feature recognition in 2D engineering drawings. At present, in most dimension feature recognition methods, the first step is the recognition of whole feature, and then to extract feature information. These methods have some disadvantages, especially in exploded dimension feature recognition. Aimed to solve this problem, this paper introduces a new algorithm of intelligent dimension feature recognition. According to the position relationship with basic elements of dimension, the dimension is recognized in a bottom-up approach. This new method can solves the problem of recognizing the exploded dimension

ORTHOGONAL MOMENTS AND THEIR APPLICATION TO MOTION DETECTION IN IMAGE SEQUENCES

2004 ◽  
Vol 01 (01) ◽  
pp. 77-87 ◽  
Author(s):  
JUN SHEN ◽  
WEI SHEN ◽  
DANFEI SHEN ◽  
YOUFU WU
Keyword(s):  
Motion Detection ◽  
Information Acquisition ◽  
Image Sequences ◽  
Experimental Results ◽  
The Other ◽  
New Method ◽  
Dynamic Scenes ◽  
Orthogonal Moments ◽  
Modern Information

Motion detection is one of the most important subjects in modern information acquisition systems for dynamic scenes. In this paper, we address motion detection in image sequences by the use of smoothed orthogonal Gaussian-Hermite moments. After introducing the orthogonal moments, with their fast calculations and the analysis on their behavior, we present a new method of motion detection in image sequences by the use of temporal Gaussian-Hermite moments. Experimental results are presented and are compared with the other methods, which shows the good performance of smoothed orthogonal Gaussian-Hermite moments for motion detection.

A Novel Hybrid Design Representation for Automatic Design Features Recognition Systems

2015 ◽  
Vol 809-810 ◽  
pp. 847-852
Author(s):  
Cezary Grabowik ◽  
Rafał Zbiciak
Keyword(s):  
Product Design ◽  
Feature Recognition ◽  
Group Technology ◽  
Quantitative Description ◽  
Design Feature ◽  
Qualitative Description ◽  
New Method ◽  
Automatic Design ◽  
Design Representation ◽  
Recognition Systems

Problems of design similarity identification and elements grouping play a key factor in the development of design standardization and the group technology methods. Design similarity identification methods are most often based on a comparison of codes ascribed to products design. Basically the code makes a quantitative product description including different product features. Whereas a qualitative description has constituted rather supplement of a quantitative description. The most important issue in a process of design similarity identification is a method of a product design description. This description is usually made with use of special codes composed of alphanumeric characters. The coding process allows reducing the number of data which are being processed during design similarity evaluation, but on the other hand in some cases it could cause information loss. Taking into account above there is still a need of working out of a new method of a product design description which will be able to reduce these negative features of coding techniques. In the paper a novel approach for a product design description is presented. It is proposed to apply a hybrid method for a design representation purpose. This method uses a combination of code chains for a product longitudinal cross-section representation and a spatial matrix for transvers sections. As a result of the conducted research a new method of a product design description was worked out. This method is especially suggested for application in automatic design feature recognition systems (AFR systems) in which a design feature database (DFD) is present.

A New Opinion Information Acquisition System of Mop Forum

2012 ◽  
Vol 263-266 ◽  
pp. 2764-2767
Author(s):  
Feng Jun Miao ◽  
Xin Chao Han ◽  
Qiu Sheng Zhen
Keyword(s):  
Public Opinion ◽  
Structure Analysis ◽  
Information Acquisition ◽  
New Method ◽  
Acquisition System

For resolved the problem to collect public opinion information of the Mop forum, the paper proposed a new method to obtain a URL link ,and obtain the appropriate URL Document by the Jsoup method, post HTML structure analysis, accesse to post content, and at last save these to the folder by txt file. After the test, the method is effective and the system is stable.

Sign in / Sign up

Export Citation Format

Share Document