This Technical Report revisits the problem of fitting the strokes of a sketch into elliptical arc... more This Technical Report revisits the problem of fitting the strokes of a sketch into elliptical arcs. Our purpose is to calculate a reasonably good and very fast fit applying a perceptual approach. Hence, the experiments carried out to determine how people perceive elliptical arcs in sketched strokes are described in detail, and the main conclusions are derived.
In this tutorial, we describe the state of the art of sketch input of engineering solid models. T... more In this tutorial, we describe the state of the art of sketch input of engineering solid models. The tutorial is in four parts. In the first part, we show how sketching has historically been an important aspect of engineering culture,and remains a useful tool in the early design phase as it has been demonstrated that sketching enhances creativity.We discuss and classify various current approaches to computer interpretation of sketches.We introduce the problem of deducing design intent, which we understand as a mix of geometry, psychology and engineering, and note how no existing approach to interpretation of sketches has considered the explicit capture of design intent from the input sketch. In the second and third parts, we present our selection of the most important algorithms currently used for interpreting wireframe drawings (part two) and natural line drawings (part three) of engineering objects. In part two, the algorithms we look at are: for finding faces in wireframes; for inflating wireframes to 3D; and for processing rounds and fillets. In part three, we look at: line labelling; inflation to 2.5D; and deducing hidden topology. In part four, we discuss some of the most interesting open problems: making virtual paper and pencil more usable than actual paper and pencil; interpreting annotated engineering sketches; and creating assemblies from sketches.
We outline an artificial perception model for an algorithm that detects junctions in casual sketc... more We outline an artificial perception model for an algorithm that detects junctions in casual sketches. These sketches are used by skilled individuals to visually and quickly convey ideas.
In this article, visual perception principles were used to build an artificial perception model a... more In this article, visual perception principles were used to build an artificial perception model aimed at developing an algorithm for detecting junctions in line drawings of polyhedral objects that are vectorized from hand-drawn sketches. The detection is performed in two dimensions (2D), before any 3D model is available and minimal information about the shape depicted by the sketch is used. The goal of this approach is to not only detect junctions in careful sketches created by skilled engineers and designers but also detect junctions when skilled people draw casually to quickly convey rough ideas. Current approaches for extracting junctions from digital images are mostly incomplete, as they simply merge endpoints that are near each other, thus ignoring the fact that different vertices may be represented by different (but close) junctions and that the endpoints of lines that depict edges that share a common vertex may not necessarily be close to each other, particularly in quickly s...
The Clowes-Huffman catalogue for labelling line drawings of trihedral polyhedra is a well-establi... more The Clowes-Huffman catalogue for labelling line drawings of trihedral polyhedra is a well-established tool in computer vision. We currently use it in processing sketch input of solid models of engineering components. However, many such components also contain tetrahedral vertices. Thus, this paper presents a similar catalogue for tetrahedral polyhedra.
Fitting the strokes of a sketch into geometrical primitives is still an open problem, even for sk... more Fitting the strokes of a sketch into geometrical primitives is still an open problem, even for sketches which depict bare line-drawings without annotations. Such sketches comprise only discrete strokes, sequences of points obtained between a pen down and a pen up. It is commonly accepted that the best perceptual fittings depend on the context. Hence, we will only be able to extract the best line-drawing from a sketch by considering a complex recognition flow, where lines must be iteratively fitted according to different tentative relationships until the most plausible line-drawing is reached. The recognition task considered in this paper is determining whether a stroke represents a straight line. The goal is doing it in a way that allows for iterative recognition flows. The novel contributions are that our approach is more fast and robust than accurate, uses perceptual criteria to classify strokes, and returns likeliness instead of a simple yes/no.
We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a ... more We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a polyhedral shape. The method finds a CSG feature tree compatible with a reverse design history of a 2D line-drawing obtained by vectorising the sketch. The process used seeks the CSG feature tree recursively, combining all design or manu-facturing features embedded in the sketch, proceeding in reverse order from the most detailed features to the blank.
This Technical Report revisits the problem of fitting the strokes of a sketch into elliptical arc... more This Technical Report revisits the problem of fitting the strokes of a sketch into elliptical arcs. Our purpose is to calculate a reasonably good and very fast fit applying a perceptual approach. Hence, the experiments carried out to determine how people perceive elliptical arcs in sketched strokes are described in detail, and the main conclusions are derived.
In this tutorial, we describe the state of the art of sketch input of engineering solid models. T... more In this tutorial, we describe the state of the art of sketch input of engineering solid models. The tutorial is in four parts. In the first part, we show how sketching has historically been an important aspect of engineering culture,and remains a useful tool in the early design phase as it has been demonstrated that sketching enhances creativity.We discuss and classify various current approaches to computer interpretation of sketches.We introduce the problem of deducing design intent, which we understand as a mix of geometry, psychology and engineering, and note how no existing approach to interpretation of sketches has considered the explicit capture of design intent from the input sketch. In the second and third parts, we present our selection of the most important algorithms currently used for interpreting wireframe drawings (part two) and natural line drawings (part three) of engineering objects. In part two, the algorithms we look at are: for finding faces in wireframes; for inflating wireframes to 3D; and for processing rounds and fillets. In part three, we look at: line labelling; inflation to 2.5D; and deducing hidden topology. In part four, we discuss some of the most interesting open problems: making virtual paper and pencil more usable than actual paper and pencil; interpreting annotated engineering sketches; and creating assemblies from sketches.
We outline an artificial perception model for an algorithm that detects junctions in casual sketc... more We outline an artificial perception model for an algorithm that detects junctions in casual sketches. These sketches are used by skilled individuals to visually and quickly convey ideas.
In this article, visual perception principles were used to build an artificial perception model a... more In this article, visual perception principles were used to build an artificial perception model aimed at developing an algorithm for detecting junctions in line drawings of polyhedral objects that are vectorized from hand-drawn sketches. The detection is performed in two dimensions (2D), before any 3D model is available and minimal information about the shape depicted by the sketch is used. The goal of this approach is to not only detect junctions in careful sketches created by skilled engineers and designers but also detect junctions when skilled people draw casually to quickly convey rough ideas. Current approaches for extracting junctions from digital images are mostly incomplete, as they simply merge endpoints that are near each other, thus ignoring the fact that different vertices may be represented by different (but close) junctions and that the endpoints of lines that depict edges that share a common vertex may not necessarily be close to each other, particularly in quickly s...
The Clowes-Huffman catalogue for labelling line drawings of trihedral polyhedra is a well-establi... more The Clowes-Huffman catalogue for labelling line drawings of trihedral polyhedra is a well-established tool in computer vision. We currently use it in processing sketch input of solid models of engineering components. However, many such components also contain tetrahedral vertices. Thus, this paper presents a similar catalogue for tetrahedral polyhedra.
Fitting the strokes of a sketch into geometrical primitives is still an open problem, even for sk... more Fitting the strokes of a sketch into geometrical primitives is still an open problem, even for sketches which depict bare line-drawings without annotations. Such sketches comprise only discrete strokes, sequences of points obtained between a pen down and a pen up. It is commonly accepted that the best perceptual fittings depend on the context. Hence, we will only be able to extract the best line-drawing from a sketch by considering a complex recognition flow, where lines must be iteratively fitted according to different tentative relationships until the most plausible line-drawing is reached. The recognition task considered in this paper is determining whether a stroke represents a straight line. The goal is doing it in a way that allows for iterative recognition flows. The novel contributions are that our approach is more fast and robust than accurate, uses perceptual criteria to classify strokes, and returns likeliness instead of a simple yes/no.
We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a ... more We give a method to obtain a 3D CSG model from a 2D engineering wireframe sketch which depicts a polyhedral shape. The method finds a CSG feature tree compatible with a reverse design history of a 2D line-drawing obtained by vectorising the sketch. The process used seeks the CSG feature tree recursively, combining all design or manu-facturing features embedded in the sketch, proceeding in reverse order from the most detailed features to the blank.
Uploads
Papers by Peter A C Varley