Vectorization

by Adaptive Sampling with Domain Knowledge

Algorithm

Paramita De, Sekhar Mandal, Partha Bhowmick, Amit Das,
ASKME: Adaptive Sampling with Knowledge Driven Vectorization of Mechanical Engineering Drawings,
International Journal on Document Analysis and Recognition, 2015 (accepted).

Contribution

We have proposed an efficient algorithm for high-level vectorization of scanned images of mechanical engineering drawings. The algorithm is marked by several novel features, which merit its superiority over the existing techniques. After preprocessing and necessary refinement of junction points in the image skeleton, it first extracts the graphic primitives, such as lines, circles, and arcs, based on certain digital-geometric properties of straightness and circularity in the discrete domain. The primitives are classified to different types with all associated details based on fast and efficient geometric analysis. The vector set is succinctly reduced by such classification in tandem with further consolidation to make out meaningful objects like rectangles and annuli, together with hatching information. Exhaustive testing shows the efficiency of the algorithm, and also its robustness and stability towards any affine transformation and injected noise. Easy reconstruction to scalable vector graphics demonstrates its readiness and usability as a state-of-the-art solution.

Figure on right: Animation showing the basic steps in order.
Input image → Skeleton (black) → Lines and arcs detected on the skeleton image → Classification and consolidation → SVG reconstruction of the output vector set (green: object line, blue: centerline, yellow: arrowhead, saffron: circular arc).

Total CPU time per image (300 DPI) is less than a second, and the Vector Recovery Index (VRI) lies around 70% on the average. 		6.gif