Automatic vectorization of scanned engineering drawings

Author(s):  
A. Manesh ◽  
J. Wrobel ◽  
J. Gao
Keyword(s):  
1982 ◽  
Vol 20 (3) ◽  
pp. 244-258 ◽  
Author(s):  
Robert M. Haralick ◽  
David Queeney
Keyword(s):  

Author(s):  
Andrew Brock ◽  
Theodore Lim ◽  
J. M. Ritchie ◽  
Nick Weston

End-to-end machine analysis of engineering document drawings requires a reliable and precise vision frontend capable of localizing and classifying various characters in context. We develop an object detection framework, based on convolutional networks, designed specifically for optical character recognition in engineering drawings. Our approach enables classification and localization on a 10-fold cross-validation of an internal dataset for which other techniques prove unsuitable.


Author(s):  
Lindley Manning

The purpose of this paper is to inform the Academy of an application of computer graphics that has been successful in the court room and which has the potential for extension to many related needs of the forensic engineer. An additional purpose is to examine the possibility of cooperation within the Academy to make a broad database and selection of equipment available to the members. Attentive engineers of today are well aware of the growing use and impact of computer-aided drafting, design and analysis in a wide variety of industries. In our field, we are aware of large analysis programs which have been used with success in court, for example the CRASH series. The authors forensic engineering partnership has developed ways to utilize the more widely available drafting systems to inexpensively fill the gap between photographic evidence and full engineering drawings. We have also found that CAD drawings appear to have more impact in court than hand done drawings. In some cases


Sign in / Sign up

Export Citation Format

Share Document