Functional parts detection in engineering drawings: Looking for the screws
Author(s) -
María A. Capellades,
Octavia Camps
Publication year - 1996
Publication title -
lecture notes in computer science
Language(s) - English
Resource type - Book series
SCImago Journal Rank - 0.249
H-Index - 400
eISSN - 1611-3349
pISSN - 0302-9743
ISBN - 3-540-61226-2
DOI - 10.1007/3-540-61226-2_20
Subject(s) - schematic , computer science , engineering drawing , representation (politics) , set (abstract data type) , function (biology) , line (geometry) , technical drawing , protocol (science) , hinge , artificial intelligence , computer vision , algorithm , mechanical engineering , programming language , engineering , medicine , geometry , mathematics , alternative medicine , pathology , electronic engineering , evolutionary biology , politics , political science , law , biology
Functional parts — i.e. mechanical parts with intrinsic functionality — such as screws, hinges and gears, are appealing high level entities to be used in line drawing understanding systems. This is because their functionality can be used by a reasoning agent to infer surrounding objects and because they are usually drawn following standards making them easier to be detected. In this chapter, an algorithm for the automatic detection of the schematic representation of screws in mechanical engineering drawings is being presented as a first step towards a function-based line drawing understanding system. All the running parameters required by the algorithm are set according to the American National Standards Institute standards and by using a rigorous experimental protocol characterizing the algorithm performance in the presence of image degradation, thus eliminating the need for ad hoc parameter tuning. Experimental results on several real line drawings are also presented.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom