
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

3D Object Recognition Using HopfieldStyle Neural Networks
Tsuyoshi KAWAGUCHI Tatsuya SETOGUCHI
Publication
IEICE TRANSACTIONS on Information and Systems
Vol.E77D
No.8
pp.904917 Publication Date: 1994/08/25
Online ISSN:
DOI:
Print ISSN: 09168532 Type of Manuscript: PAPER Category: BioCybernetics and Neurocomputing Keyword: biocybernetics and neurocomputing, computer graphics and pattern recognition,
Full Text: PDF(1.2MB)>>
Summary:
In this paper we propose a new algorithm for recognizing 3D objects from 2D images. The algorithm takes the multiple view approach in which each 3D object is modeled by a collection of 2D projections from various viewing angles where each 2D projection is called an object model. To select the candidates for the object model that has the best match with the input image, the proposed algorithm computes the surface matching score between the input image and each object model by using Hopfield nets. In addition, the algorithm gives the final matching error between the input image and each candidate model by the error of the posetransform matrix proposed by Hong et al. and selects an object model with the smallest matching error as the best matched model. The proposed algorithm can be viewed as a combination of the algorithm of Lin et al. and the algorithm of Hong et al. However, the proposed algorithm is not a simple combination of these algorithms. While the algorithm of Lin et al. computes the surface matching score and the vertex matching score berween the input image and each object model to select the candidates for the best matched model, the proposed algorithm computes only the surface matching score. In addition, to enhance the accuracy of the surface matching score, the proposed algorithm uses two Hopfield nets. The first Hopfield net, which is the same as that used in the algorithm of Lin et al., performs a coarse matching between surfaces of an input image and surfaces of an object model. The second Hopfield net, which is the one newly proposed in this paper, establishes the surface correspondences using the compatibility measures between adjacent surfacepairs of the input image and the object model. the results of the experiments showed that the surface matching score obtained by the Hopfield net proposed in this paper is much more useful for the selectoin of the candidates for the best matched model than both the sruface matching score obtained by the first Hopfield net of Lin et al. and the vertex matching score obtained by the second Hopfield net of Lin et al. and, as the result, the object recognition algorithm of this paper can perform much more reliable object recognition than that obtained by simply combining the algorithm of Lin et al. and the algorithm of Hong et al.

