Recognition of 3D Objects in Arbitrary Pose Using a Fuzzy
Associative Database Algorithm
Aaron Mavrinac, Xiang Chen, and Ahmad Shawky
Abstract— Once the human vision system has seen a 3D
object from a few different viewpoints, depending on the nature
of the object, it can generally recognize that object from new
arbitrary viewpoints. This useful interpolative skill relies on
the highly complex pattern matching systems in the human
brain, but the general idea can be applied to a computer
vision recognition system using comparatively simple machine
learning techniques. An approach to the recognition of 3D
objects in arbitrary pose relative to the vision equipment
with only a limited training set of views is presented. This
approach involves computing a disparity map using stereo
cameras, extracting a set of features from the disparity map,
and classifying it via a fuzzy associative map to a trained object.
I. INTRODUCTION
HUMANS are generally able to recognize 2D shapes,regardless of changes in orientation, scale, or skew,
after having seen the shape in one such configuration. This
shape recognition has a very wide range of applications,
and accordingly, much work has gone into automating it
with computers. The basic theory is that shapes can be
extracted from otherwise cluttered and cumbersome images,
from which some set of quantifiers efficiently describing
the shapes can be obtained and compared to known values
through some algorithm for classification. The nature of
these quantifiers and the classification algorithm are a subject
of much research; most use quantifiers invariant to the
aforementioned transformations (rotation, scale, skew, etc.)
such as Fourier descriptors, moment invariants, and Hough
transformations, and most use machine learning methods
such as fuzzy logic and neural networks for classification.
Humans are also generally able to recognize 3D objects,
regardless of their orientation, after having seen a sufficient
number of different views (depending, of course, on the
nature of the object itself). To generalize from the 2D case,
it is possible to automate this process in a similar manner
by obtaining quantifiers describing the 3D surface rather
than the 2D shape. Such quantifiers can be extracted from
range images, or in the case of stereo vision, disparity
maps. However, a single such image gives information only
from a certain perspective; this is commonly referred to
as 2.5D. To approach full 3D information, range images
must be taken from different perspectives around the object.
For classification to continue to work as generalized from
The authors are with the Department of Electrical and Computer
Engineering, University of Windsor, Windsor, Ontario, Canada (email:
{mavrin1,xchen,shawky}@uwindsor.ca).
This research was funded in part by the Natural Sciences and Engineering
Research Council of Canada (NSERC).
the 2D case, the sets of quantifiers from each perspective
must be combined to fully describe the object, and the
classification algorithm must be designed to operate on this
type of information.
In this paper, we expand on previous work in object recog-
nition using invariant values on 2D images [5], justifying the
selection of proper invariant descriptors for 3D shapes based
on disparity maps and modifying the classification scheme
to reflect the new object description. The result is a system
capable of recognizing a trained object based on a disparity
map taken by a stereo camera rig from any view, where
training requires only a few different such views.
II. PRIOR WORK
A. 3D Recognition
There are several cases where 2D moment invariants have
been used for recognition of 3D objects. In both [10] and
[8], moment invariants are computed on a series of intesity
images of the object taken from a variety of positions around
it; it is demonstrated that with a sufficient number of images
and proper handling of the multi-image input in an artificial
neural network scheme, 2D moments are applicable to 3D
recognition. However, these methods do not examine 3D
information about the object directly, and require a large
number of explicitly-ordered views to operate. In addition to
the cost of capturing these views, objects are not identified
from an arbitrary unknown pose.
Methods have also been proposed which operate on in-
variants of 3D range data. In [9], the concept of computing
characteristic vectors of multiple images is extended to range
images, allowing for object recognition in arbitrary pose
unaffected by illumination. In [6], local feature histograms,
invariant to translations and rotations as well as being robust
to partial occlusions, are computed directly on range images;
recognition is then performed using histogram matching or
probabilistic recognition.
There are a number of alternate possibilities which employ
other descriptors entirely. One example is [7], in which chro-
maticity distributions from a variety of images of the object
are used to identify the object; this method of recognition,
while pose-invariant, is adversely affected by variations in
illumination, though the work attempts to alleviate these
problems.
B. Neuro-Fuzzy Recognition
Neuro-fuzzy classifiers are used to solve a wide range of
recognition problems [19]. In particular, a number of fuzzy
Fourth International Workshop on Advanced Computational Intelligence
Wuhan, Hubei, China; October 19-21, 2011
978-1-61284-375-9/11/$26.00 @2011 IEEE 542