1998
DOI: 10.1016/s0010-4485(98)00059-1
|View full text |Cite
|
Sign up to set email alerts
|

The Heriot-Watt FeatureFinder: CIE97 results

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2000
2000
2010
2010

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 16 publications
(4 citation statements)
references
References 4 publications
0
4
0
Order By: Relevance
“…The concept of a face set from an inner loop on a single face can be extended conceptually to a loop of edges straddling several faces. This type of face set is new, though in some cases it could be equivalent to depressions from multiple faces proposed in the Heriot-Watt FeatureFinder [20]. This face set is referred to as multiple-face inner loop set and an example is shown in Fig.…”
Section: Individual Feature Detection Methodsmentioning
confidence: 99%
“…The concept of a face set from an inner loop on a single face can be extended conceptually to a loop of edges straddling several faces. This type of face set is new, though in some cases it could be equivalent to depressions from multiple faces proposed in the Heriot-Watt FeatureFinder [20]. This face set is referred to as multiple-face inner loop set and an example is shown in Fig.…”
Section: Individual Feature Detection Methodsmentioning
confidence: 99%
“…It is over ten years since the special panel session for FR at the ASME 'Computers in Engineering Conference' in 1997 presented a comparison among different systems (Abdel-Malek et al 1998, Han and Rosen 1998, Little et al 1998, Sonthi and Gadh 1998, Wang and Kim 1998) and a set of standard test components became available at NIST (Regli and Gaines 1997). Yet no easy way of comparing functionality has yet appeared.…”
Section: Introductionmentioning
confidence: 99%
“…On the one hand, a great deal of research work has been done on the recognition of machining feature from product models [3][4], but most of them can recognize regular and 2.5 dimensional features only, and it is still difficult in the recognition of three-dimensional or sculptured surface features. The methods of feature recognition can be summarized as follows [5]: (1) hint-based reasoning [6,7]; (2) convex decomposition [8]; (3) face-edge graph based approach [9]; (4) curvature region approach [10] and (5) cellbased decomposition [11]. On the other hand, a feature database needs to be created so that the process planning can be performed based on it.…”
Section: Introductionmentioning
confidence: 99%