Journal ArticleDOI
Sparse-pixel recognition of primitives in engineering drawings
Dov Dori,Yubin Liang,Joseph Dowell,Ian Chai +3 more
- Vol. 6, Iss: 2, pp 69-82
Reads0
Chats0
TLDR
A set of algorithms that recognize drawing primitives by examining the raster file sparsely by screening a carefully selected sample of the image and focusing attention on identified key areas yield high quality recognition.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Sparse pixel vectorization: an algorithm and its performance evaluation
Dov Dori,Wenyin Liu +1 more
TL;DR: This work presents a thinningless sparse pixel vectorization (SPV) algorithm, which is both time efficient and accurate, as evaluated by the proposed performance evaluation criteria.
Journal ArticleDOI
A protocol for performance evaluation of line detection algorithms
Liu Wenyin,Dov Dori +1 more
TL;DR: 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 is proposed.
Book ChapterDOI
Stable and Robust Vectorization: How to Make the Right Choices
TL;DR: This paper discusses in this paper some qualitative elements which should be taken into account when choosing the different steps of one's vectorization method.
Journal ArticleDOI
From engineering drawings to 3D cad models: are we ready now?
Dov Dori,Karl Tombre,Karl Tombre +2 more
TL;DR: A scheme is proposed for achieving high-level conversion of technical documents of this type into 3D cad models on the basis of the authors' expertise in syntactic (dimension sets) and semantic (functionalities) analysis of mechanical engineering drawings.
Journal ArticleDOI
Adaptive Vectorization of Line Drawing Images
TL;DR: A novel method for vectorizing line drawing images is presented, based on a sequence of a standard vectorization algorithm and maximum threshold morphology, which can be iterated until a fitting criterion is met.
References
More filters
Book
Computer and Robot Vision
TL;DR: This two-volume set is an authoritative, comprehensive, modern work on computer vision that covers all of the different areas of vision with a balanced and unified approach.
Journal ArticleDOI
The Adaptive Hough Transform
John Illingworth,Josef Kittler +1 more
TL;DR: This correspondence illustrates the ideas of the Adaptive Hough Transform, AHT, by tackling the problem of identifying linear and circular segments in images by searching for clusters of evidence in 2-D parameter spaces and shows that the method is robust to the addition of extraneous noise.
Journal ArticleDOI
Finding circles by an array of accumulators
TL;DR: This procedure is an extension and improvement of the circle-finding concept sketched by Duda and Hart as an extension of the Hough straight-line finder.
Book
Decision, Estimation and Classification: An Introduction to Pattern Recognition and Related Topics
TL;DR: Probability theory for random vectors simple statistical decision procedures operations upon random vectors feature extraction and nonlinear mapping quadratic and linear classifiers parameter estimation nonparametric estimation and classification estimating and bounding the probability of error classification of stationary time series context-dependent methods other methods of classification.