文档介绍：Sven Behnke
Hierarchical works
for Image Interpretation
June 13, 2003
Draft submitted to Springer-Verlag
Published as volume 2766 of Lecture Notes puter Science
ISBN: 3-540-40722-7
Foreword
It is my pleasure and privilege to write the foreword for this book, whose results I
have been following and awaiting for the last few years. This monograph represents
the e of an ambitious project oriented towards advancing our knowledge of
the way the human visual system processes images, and about the way bines
high level hypotheses with low level inputs during pattern recognition. The model
proposed by Sven Behnke, carefully exposed in the following pages, can be applied
now by other researchers to practical problems in the 2eld puter vision and
provides also clues for reaching a deeper understanding of the human visual system.
This book arose out of dissatisfaction with an earlier project: back in 1996, Sven
wrote one of the handwritten digit recognizers for the mail sorting machines of
the Deutsche Post AG. The project was essful because the machines could in-
deed recognize the handwritten ZIP codes, at a rate of several thousand letters per
hour. However, Sven was not satis2ed with the amount of expert knowledge that
was needed to develop the feature extraction and classi2cation algorithms. He won-
dered if puter could be able to extract meaningful features by itself, and use
these for classi2cation. His experience in the project told him that pu-
tation alone would be incapable of improving the results already obtained. From his
knowledge of the human visual system, he postulated that only a two-way system
could work, one that could advance a hypothesis by focussing the attention of the
lower layers of a work on it. He spent the next few years developing a new
model for tackling precisely this problem.
The main result of this book is the proposal of a generic architecture for pattern
recognition problems, called Neural Abstraction Pyramid