A fast technique for vectorization of engineering drawings using morphology and digital straightness

Authors:
Sekhar Mandal;Amit K. Das;Partha Bhowmick
Affiliations:
Bengal Engineering and Science University, Shibpur, India;Bengal Engineering and Science University, Shibpur, India;Indian Institute of Technology, Kharagpur, India
Venue:
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Year:
2010

Citing 10
Cited 0

An Object-Oriented Progressive-Simplification-Based Vectorization System for Engineering Drawings: Model, Algorithm, and Performance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Symbol Recognition: Current Advances and Perspectives

GREC '01 Selected Papers from the Fourth International Workshop on Graphics Recognition Algorithms and Applications
Prototyping Structural Descriptions: An Inductive Learning Approach

SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Indexing of Technical Line Drawings Based on F-Signatures

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Extraction, layout analysis and classification of diagrams in PDF documents

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Digital Geometry: Geometric Methods for Digital Picture Analysis

Digital Geometry: Geometric Methods for Digital Picture Analysis
Document zone content classification and its performance evaluation

Pattern Recognition
An interactive example-driven approach to graphics recognition in engineering drawings

International Journal on Document Analysis and Recognition
Digital Straight Line Segments

IEEE Transactions on Computers
Image classification by a two-dimensional hidden Markov model

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel technique for vectorization of engineering drawings is presented. The novelty of the algorithm lies in exploiting certain digital-geometric properties of straightness to vectorize inclined line segments and curve segments after vectorizing the horizontal and the vertical pieces using the conventional morphological opening. The primitives, hence vectorized, are classified into (i) horizontal, (ii) vertical, (iii) inclined line segments, and (iv) curved segments. Such a classification expedites the reconstruction of an engineering drawing from the vector format. Experimental results on several benchmark datasets have been given to demonstrate its efficiency and elegance.