Principal Components Analysis Of Images Via Back Propagation

Garrison W. Cottrell; Paul Munro

doi:10.1117/12.969060

25 October 1988 Principal Components Analysis Of Images Via Back Propagation

Garrison W. Cottrell, Paul Munro

Proceedings Volume 1001, Visual Communications and Image Processing '88: Third in a Series; (1988) https://doi.org/10.1117/12.969060
Event: Visual Communications and Image Processing III, 1988, Cambridge, MA, United States

Abstract

The recent discovery of powerful learning algorithms for parallel distributed networks has made it possible to program computation in a new way, by example rather than algorithm. The back propagation algorithm is a gradient descent technique for training such networks. The problem posed to the researcher using such an algorithm is discovering how it did solve the problem if a solution is found. In this paper we apply back propagation to a well understood problem in image analysis, i.e., bandwidth compression, and analyze the internal representation developed by the network. The network used consists of nonlinear units that compute a sigmoidal function of their inputs. It is found that the learning algorithm produces a nearly linear transformation of a Principal Components Analysis of the image, and the units in the network tend to stay in the linear range of the sigmoid function. The particular transform found departs from the standard Principal Components solution in that near-equal variance of the coefficients results, depending on the encoding used. While the solution found is basically linear, such networks can also use the nonlinearity to solve encoding problems where the Principal Components solution is degenerate.

Citation Download Citation

Garrison W. Cottrell and Paul Munro "Principal Components Analysis Of Images Via Back Propagation", Proc. SPIE 1001, Visual Communications and Image Processing '88: Third in a Series, (25 October 1988); https://doi.org/10.1117/12.969060

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available