|
|
|
Foundation ::
Artificial Intelligence and Expert Systems ::
HONTIOR
|
HONTIOR
Higher-Order Neural Network for Transformation Invariant Object Recognition
|
 |
Moderators:
Adopt This Application!
|
SOURCE CODE AVAILABLE
|
|
Neural networks have been applied in numerous fields, including transformation
invariant object recognition, wherein an object is recognized
despite changes in the object's position in the input field, size, or rotation.
One of the more successful neural network methods used in invariant
object recognition is the higher-order neural network (HONN) method.
With a HONN, known relationships are exploited and the desired invariances
are built directly into the architecture of the network, eliminating the
need for the network to learn invariance to transformations. This results
in a significant reduction in the training time required, since the network
needs to be trained on only one view of each object, not on numerous transformed
views. Moreover, one hundred percent accuracy is guaranteed for images
characterized by the built-in distortions, providing noise is not introduced
through pixelation.
The program HONTIOR implements a third-order neural network having invariance
to translation, scale, and in-plane rotation built directly into
the architecture, Thus, for 2-D transformation invariance, the network
needs only to be trained on just one view of each object. HONTIOR can also be
used for 3-D transformation invariant object recognition by training the
network only on a set of out-of-plane rotated views. Historically, the major
drawback of HONNs has been that the size of the input field was limited
to the memory required for the large number of interconnections in a fully
connected network. HONTIOR solves this problem by coarse coding the input
images (coding an image as a set of overlapping but offset coarser images).
Using this scheme, large input fields (4096 x 4096 pixels) can easily
be represented using very little virtual memory (30Mb).
The HONTIOR distribution consists of three main programs. The first
program contains the training and testing routines for a third-order neural
network. The second program contains the same training and testing procedures
as the first, but it also contains a number of functions to display and
edit training and test images. Finally, the third program is an auxiliary
program which calculates the included angles for a given input field size.
HONTIOR carries the NASA case number ARC-13187. It was originally released as part of the NASA COSMIC collection.
|
|
More software from National Technology Transfer Center
|
|
|
|
|
|
|
Open Channel Software runs entirely on Open Source Software. We return
value to the Software community in the form of
services and original software. Most of our
content is currently available as source code, with the
copyright owned by the original author, All
Rights Reserved. Everything else is Copyright
©2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 Open Channel Software.
View our privacy statement.
Contact webmaster at openchannelsoftware dot org with questions.
|
|
|
