<p>The fundamental aim of this study is to examine whether itis possible to automatically convert vector-based drawings toproduct models. The reason fordoing this is that the newobject-based systems cannot make use of the information storedin CAD drawings, which limits the usability of thesesystems.</p><p>Converting paper drawings to vector-format is used today andprovides recognition of lines and text, but does not interpretwhat the shapes represent. A language for describing thegeometrical representations that could be processed directlyinto a recognition program for building elements is missing. Itis easier to describe how to recognize a line as a series ofdots in a raster image, than it is to describe how a complexsymbol of a building element looks like.</p><p>The approach in this research work has been to testdifferent shape recognition algorithms. The proposed method canbe divided into four processes: grouping of geometricalprimitives, classifying these groups, interpreting the contentand analyzing the relationships between the groups. Thealgorithms developed here are based on research within relateddomains, such as pattern recognition and artificialintelligence.</p><p>The algorithms have been developed in a prototypeimplementation and were tested with three layer-structureddrawings used in practice. The results of the tests show thatthere are no crucial obstacles to recognizing a large part ofthe symbols of building elements in a CAD drawing. Therequirement is that the recognition system is able todifferentiate one from another and be tolerant of errors andvariations in the shapes.</p><p><b>Keywords:</b>Shape recognition, shape interpretation,product models</p>
| Identifer | oai:union.ndltd.org:UPSALLA/oai:DiVA.org:kth-1247 |
| Date | January 2001 |
| Creators | Noack, Robert |
| Publisher | KTH, Real Estate and Construction Management, Institutionen för fastigheter och byggande |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Licentiate thesis, monograph, text |
Page generated in 0.0023 seconds