Multidirectional Scanning Model, MUSCLE, to Vectorize Raster Images with Straight Lines
Open Access
Abstract
This paper presents a new model, MUSCLE (Multidirectional Scanning for Line Extraction), for automatic vectorization of raster images with straight lines. The algorithm of the model implements the line thinning and the simple neighborhood methods to perform vectorization. The model allows users to define specified criteria which are crucial for acquiring the vectorization process. In this model, various raster images can be vectorized such as township plans, maps, architectural drawings, and machine plans. The algorithm of the model was developed by implementing an appropriate computer programming and tested on a basic application. Results, verified by using two well known vectorization programs (WinTopo and Scan2CAD), indicated that the model can successfully vectorize the specified raster data quickly and accurately.Keywords
This publication has 15 references indexed in Scilit:
- Local Lines: A linear time line detectorPattern Recognition Letters, 2003
- BRDC: binary representation of displacement code for lineComputers & Graphics, 2002
- Extraction of embedded and/or line-touching character-like objectsPattern Recognition, 2002
- Automatic Road Detection in Grayscale Aerial ImagesJournal of Computing in Civil Engineering, 2000
- Straight-line-based primitive extraction in grey-scale object recognitionPattern Recognition Letters, 1999
- Fast and robust techniques for detecting straight line segments using local modelsPattern Recognition Letters, 1999
- From Raster to Vectors: Extracting Visual Information from Line DrawingsPattern Analysis and Applications, 1999
- Chaincode contour processing for handwritten word recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Computer Processing of Line-Drawing ImagesACM Computing Surveys, 1974
- On the Encoding of Arbitrary Geometric ConfigurationsIEEE Transactions on Electronic Computers, 1961