From the zones of influence of skeleton branch points to meaningful - - PowerPoint PPT Presentation

▶
from the zones of influence of skeleton branch points to
SMART_READER_LITE
LIVE PREVIEW

From the zones of influence of skeleton branch points to meaningful - - PowerPoint PPT Presentation

Apr 23, 2023 294 likes •489 views

From the zones of influence of skeleton branch points to meaningful object parts Luca Serino, Carlo Arcelli and Gabriella Sanniti di Baja Istituto di Cibernetica E. Caianiello , CNR Pozzuoli, Naples, Italy {l.serino, c.arcelli,

slide-1
SLIDE 1

From the zones of influence

  • f skeleton branch points

to meaningful object parts

Luca Serino, Carlo Arcelli and Gabriella Sanniti di Baja

Istituto di Cibernetica “E.Caianiello”, CNR Pozzuoli, Naples, Italy {l.serino, c.arcelli, g.sannitidibaja}@cib.na.cnr.it

DGCI 2013

slide-2
SLIDE 2

Outline

 Why decompose?  3D curve skeleton  Object decomposition into disjoint regions

via skeleton decomposition

 Results

DGCI 2013

slide-3
SLIDE 3

Why decompose?

  • bject recognition as a

hierarchical process

  • decompose into parts
  • analyze the parts
  • describe the object by

a graph

 nodes: parts  edges: adjacency between parts

DGCI 2013

slide-4
SLIDE 4

Different approaches

  • pre-defined shape primitives
  • irregularities in the boundary
  • object decomposition by means of skeleton

decomposition

DGCI 2013

slide-5
SLIDE 5

2D objects’ decompostion

  • G. Sanniti di Baja, E. Thiel, "(3,4)-weighted skeleton decomposition for pattern

representation and description", Pattern Recognition, 27, 1039-1049, 1994.

DGCI 2013

slide-6
SLIDE 6

3D objects’ decompostion

  • L. Serino, G. Sanniti di Baja, C. Arcelli, Object decomposition via curvilinear skeleton

partition, Proc. 20th ICPR, 2010, pp. 4081–4084.

  • L. Serino, G. Sanniti di Baja, C. Arcelli, Using the skeleton for 3D object

decomposition, Proc. SCIA 2011, LNCS 6688, Springer, 2011, pp. 447–456.

DGCI 2013

slide-7
SLIDE 7

The 3D curve skeleton

C.Arcelli, G.Sanniti di Baja, L.Serino, Distance driven skeletonization in voxel images, IEEE Trans. PAMI, vol. 33, no. 4, pp. 709-720, 2011.

DGCI 2013

slide-8
SLIDE 8

The method

 Skeleton decomposition

Identification of all skeleton branches

Detection of the significant branches by means of the zones of influence of the branch points

 Object decomposition

Detection of the overlapping regions via the reverse distance transformation of the zones of influence

Detection of the object’s parts via the subtraction of the

  • verlapping regions from the input object

Assignment of the overlapping regions to the adjacent object’s parts

DGCI 2013

slide-9
SLIDE 9

Running example

DGCI 2013

slide-10
SLIDE 10

Skeleton decomposition

DGCI 2013

slide-11
SLIDE 11

From skeleton to object decomposition

DGCI 2013

slide-12
SLIDE 12

Overlapping regions detection

slide-13
SLIDE 13

Object’s parts via overlapping regions subtraction

DGCI 2013

slide-14
SLIDE 14

Assignment of the overlapping regions

DGCI 2013

OR1 P1 P2 P3 P4 R1= AP1/AOR1 R2= AP2/AOR1 R3= AP3/AOR1 R4= AP4/AOR1

slide-15
SLIDE 15

Some results

DGCI 2013

slide-16
SLIDE 16

Results for 3D objects in different poses/sizes

DGCI 2013

slide-17
SLIDE 17

Stability

DGCI 2013

slide-18
SLIDE 18

Extending the image domain

DGCI 2013

slide-19
SLIDE 19

Thank you!

Questions?

DGCI 2013