3D Free Form Object Recognition Research Articles

Encoding 3D structural information using multiple self-organizing feature maps

This paper describes a system which encodes a free-form three-dimensional (3D) object using Artificial Neural Networks. The types of surface shapes which the system is able to handle include not only pre-defined surfaces such as simple piecewise quadric surfaces but also more complex free-form surfaces. The system utilizes two Self-Organizing Maps to encode surface parts and their geometrical relationships. Authors demonstrated the use of this encoding technique on “simple” 3D free-form object recognition systems [M. Takatsuka, R.A. Jarvis, Hierarchical neural networks for learning 3D objects from range images, Journal of Electronic Imaging 7 (1) (1998) 16–28]. This paper discusses the design and mechanism of the Multiple SOFMs for encoding 3D information in greater detail including an application to face (“complex” 3D free-form object) recognition.

3D Free-Form Object Recognition Using Indexing by Contour Features

We address the problem of recognizing free-form 3D objects from a single 2D intensity image. A model-based solution within the alignment paradigm is presented which involves three major schemes—modeling, matching, and indexing. The modeling scheme constructs a set of model aspects which can predict the object contour as seen from any viewpoint. The matching scheme aligns the edgemap of a candidate model to the observed edgemap using an initial approximate pose. The major contribution of this paper involves the indexing scheme and its integration with modeling and matching to perform recognition. Indexing generates hypotheses specifying both candidate model aspects and approximate pose and scale. Hypotheses are ordered by likelihood based on prior knowledge of pre-stored models and the visual evidence from the observed objects. A prototype implementation has been tested in recognition and localization experiments with a database containing 658 model aspects from twenty 3D objects and eighty 2D objects. Bench tests and simulations show that many kinds of objects can be handled accurately and efficiently even in cluttered scenes. We conclude that the proposed recognition-by-alignment paradigm is a viable approach to many 3D object recognition problems.