Local shape features for object recognition

We present a shape matching algorithm based on the chamfer distance transform which can be easily integrated into the well-known SIFT framework. The shape matching was designed to overcome the limitations of SIFT matching for objects which lack texture and have the majority of their features located on the object boundary.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Bernd Heisele, Carlos Rocha
• Keywords: Computer Vision, ICPR 2008, Shape Matching Algorithm, Well-known Sift Framework