Object Recognition with a Limited Database Using Shape Space Theory

Object Recognition with a Limited Database Using Shape Space Theory

Yuexing Han (National Institute of Advanced Industrial Science and Technology, Japan), Bing Wang (University of Tokyo, Japan), Hideki Koike (University of Electro-Communications, Japan) and Masanori Idesawa (University of Electro-Communications, Japan)
Copyright: © 2013 |Pages: 20
DOI: 10.4018/978-1-4666-3994-2.ch011
OnDemand PDF Download:
No Current Special Offers


One of the main goals of image understanding and computer vision applications is to recognize an object from various images. Object recognition has been deeply developed for the last three decades, and a lot of approaches have been proposed. Generally, these methods of object recognition can successfully achieve their goal by relying on a large quantity of data. However, if the observed objects are shown to diverse configurations, it is difficult to recognize them with a limited database. One has to prepare enough data to exactly recognize one object with multi-configurations, and it is hard work to collect enough data only for a single object. In this chapter, the authors will introduce an approach to recognize objects with multi-configurations using the shape space theory. Firstly, two sets of landmarks are obtained from two objects in two-dimensional images. Secondly, the landmarks represented as two points are projected into a pre-shape space. Then, a series of new intermediate data can be obtained from data models in the pre-shape space. Finally, object recognition can be achieved in the shape space with the shape space theory.
Chapter Preview

2. Background

The problem in object recognition is to determine what the observed objects are, if a given set of data objects includes analogues of the observed objects. Current understanding of the recognition process divides recognition into three phases (Grimson, 1990):

  • 1.

    Selection: what subset of the data corresponds to the object?

  • 2.

    Indexing: which object model corresponds to the data subset?

  • 3.

    Correspondence: which individual model features correspond to each data feature?

Complete Chapter List

Search this Book: