Accurate and efficient vectorization of line drawings is essential for their higher level processing. We present a thinningless sparse pixel vectorization (SPV) algorithm. Rather than visiting all the points along the wire's black area, SPV sparsely visits selected medial axis points. The result is a crude polyline, which is refined through polygonal approximation by removing redundant points. Due to the sparseness of pixel examination and the use of a specialized data structure, SPV is both time efficient and accurate, as evaluated by our proposed performance evaluation criteria.

Sparse pixel vectorization: an algorithm and its performance evaluation

Accurate and efficient vectorization of line drawings is essential for any higher level processing in document analysis and recognition systems. In spite of the prevalence of vectorization and line detection methods, no standard for their performance evaluation protocol exists. We propose a protocol for evaluating both straight and circular line extraction to help compare, select, improve, and even design line detection algorithms to be incorporated into line drawing recognition and understanding systems. The protocol involves both positive and negative sets of indices, at pixel and vector levels. Time efficiency is also included in the protocol. The protocol may be extended to handle lines of any shape as well as other classes of graphic objects.

http://dori2.technion.ac.il/opm/documents/articles/article166.pdf

A protocol for performance evaluation of line detection algorithms

As a complement to quantitative evaluation methods for raster-to-graphics conversion, we discuss in this paper some qualitative elements which should be taken into account when choosing the different steps of one's vectorization method. We stress the importance of having robust methods and stable implementations, and we base ourselves extensivelyon our own implementations and tests, concentrating on methods designed to have few, if any, parameters.

https://hal.inria.fr/inria-00098774/document

Stable and Robust Vectorization: How to Make the Right Choices

Conversion of engineering drawings into cad format has so far concentrated almost solely on low-level operations, such as vectorization, basic layer separation and very limited symbol recognition. The paper discusses the reasons for the lack of serious attempts at moving into higher levels and what can be done to improve this situation. On the basis of the authors' expertise in syntactic (dimension sets) and semantic (functionalities) analysis of mechanical engineering drawings, a scheme is proposed for achieving high-level conversion of technical documents of this type into 3D cad models.

From engineering drawings to 3D cad models: are we ready now?

Adaptive Vectorization of Line Drawing Images

Recognition of primitives in technical drawings is the first stage in their higher level interpretation. It calls for processing of voluminous scanned raster files. This is a difficult task if each pixel must be addressed at least once, as required by Hough transform or thinning-based methods. This work presents a set of algorithms that recognize drawing primitives by examining the raster file sparsely. Bars (straight line segments), arcs, and arrowheads are identified by the orthogonal zig-zag, perpendicular Bisector tracing, and self-supervised arrowhead recognition algorithms, respectively. The common feature of these algorithms is that rather than applying massive pixel addressing, they recognize the sought primitives by screening a carefully selected sample of the image and focusing attention on identified key areas. The sparse-pixel-based algorithms yield high quality recognition, as demonstrated on a sample of engineering drawings.

http://esml.iem.technion.ac.il/wp-content/uploads/2011/02/fulltext69_82.pdf

Yubin Liang

Papers

Sparse-pixel recognition of primitives in engineering drawings