Abstract
An optical–digital approach to the classification of rough surfaces that uses a Fourier-transform feature space is described. The sampling of the two-dimensional Fourier spectrum is achieved with a charge-coupled device detector array, which has a polar-sampling geometry and reduces an infinitely dimensioned spectrum image into a set of 72 measurements. To discriminate among three plastic samples in this reduced subspace, we use the Karhunen–Loève transformation. Then the classification procedure automatically selects the best subspace from the Karhunen–Loève vectors.
© 1991 Optical Society of America
Full Article |
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Figures (7)
You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Tables (1)
You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Equations (15)
You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription