

\begin{abstractpage}

For years, researchers in machine vision have focused on extracting
object boundary information from luminance derivatives, color
contrast, depth information, and textural patterns.  However, no
single one of these methods is sufficient for detecting all of the
contour information that humans perceive.  Humans have little
difficulty discriminating depth-based contours from the fused images
in a stereogram, extracting illusory contours from a Kanizsa square,
or even in completing contours through the blind spot.

This thesis reformulates the problem of ``edge detection'' into the
recognition of high-level perceptual features which I will call
``contours''. I will present a background on the psychophysical data
that describes different low-level physical means of creating contours
as well as influences from high-level sources. A novel visual
processing framework that deals with contours as high-level image
features will be developed. Finally, I will demonstrate the operation
of this new model on real-world images using a prototype active vision
head that was designed to support this visual architecture.

\end{abstractpage}


\section{Future Avenues of Research}

This thesis has opened more new lines of research than it has provided
with solutions.  The future avenues of research can be split into
three categories: additional components to our implementation of
contour integration, additional high-level behavioral goals to utilize
this system, and evaluation of this methodology on other aspects of
vision.

There are many additions that should be made to the subset of the
integrated contour model that has been implemented. The addition of
depth will provide the first real utilization of the unique qualities
of the active vision platform. Depth also provides a strong means of
contour information that has not yet been well exploited. Another
interesting addition would be a module to implement the filling-in
effects demonstrated by the blind spot. The filling-in effects may be
helpful in providing information for occluded objects, or even in
integrating information between the wide-angle and foveated cameras.
Motion would be an excellent addition for rapid discrimination, and
also aid in the development of processing that was not pipeline-based.
Additional experiments should also focus on the use of multiple C40
boards for parallel computation of the low-level modules. The use of
feedback in the integrated contour model would allow for
investigations of real-time processing and of the interactions between
modalities. Additional high-level procedures, like a model of shape
recognition, would allow the study of how expectations can influence
the low-level modules. Finally, the entire integrated contour software
should be ported to run on Cog to make use of the richer variety of
sensory inputs and behavioral responses.

Additional behavioral goals should also be investigated. The contour
segmentation system outlined in this work is only a partial test of
the integrated contour model. A high-level behavioral goal, like
object tracking or recognition, or learning to follow human faces,
would give a better sense of completeness to this project. By
specifying other unique behavioral goals, the relative importance and
influence of each modality can be more clearly studied. Learning
algorithms for the weightings between modalities would need to be
researched and developed. Future behaviors would also allow the use of
the active vision platform as more than a static camera base.

Finally, it would be interesting to apply the methodology used in
constructing a model of perceptual contours to other areas of machine
vision and artificial intelligence. This type of modeling could be
useful for other machine vision tasks, such as navigation or visual
planning for object manipulation. The methodology of differentiating
carefully between physical and perceptual stimuli could also be
applied to other senses, such as audition or tactile sensation. The
technique of using many simple modules for a common problem may
also be useful to the study of other high-level mental tasks such as
memory retrieval or path planning, but the direct extension of this
technique is not clear at this time.
