Sangam: A Confluence of Knowledge Streams

3D freeform surfaces from planar sketches using neural networks

Show simple item record

dc.creator Khan, U
dc.creator Terchi, A
dc.creator Lim, S
dc.creator Wright, D
dc.creator Qin, S F
dc.date 2008-06-02T14:39:16Z
dc.date 2008-06-02T14:39:16Z
dc.date 2006
dc.date.accessioned 2022-05-25T13:22:49Z
dc.date.available 2022-05-25T13:22:49Z
dc.identifier The 13th International Conference on Neural Information Processing, Hong Kong, 3-6 October 2006. pp. 651-660
dc.identifier http://bura.brunel.ac.uk/handle/2438/2337
dc.identifier.uri http://localhost:8080/xmlui/handle/CUHPOERS/165508
dc.description A novel intelligent approach into 3D freeform surface reconstruction from planar sketches is proposed. A multilayer perceptron (MLP) neural network is employed to induce 3D freeform surfaces from planar freehand curves. Planar curves were used to represent the boundaries of a freeform surface patch. The curves were varied iteratively and sampled to produce training data to train and test the neural network. The obtained results demonstrate that the network successfully learned the inverse-projection map and correctly inferred the respective surfaces from fresh curves.
dc.format 390384 bytes
dc.format application/pdf
dc.language en
dc.publisher Springer
dc.subject Neural networks
dc.subject Freeform surfaces
dc.subject Sketch-based interfaces
dc.title 3D freeform surfaces from planar sketches using neural networks
dc.type Conference Paper
dc.coverage 10


Files in this item

Files Size Format View
3D Freeform Sur ... Planar Sketches Using.pdf 390.3Kb application/pdf View/Open

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse