Multichannel optical correlator for texture classification

Joaquim Barbe; Juan Campos; Josep Nicolas; Claudio C. Iemmi

doi:10.1117/1.1580156

1 July 2003 Multichannel optical correlator for texture classification

Joaquim Barbe, Juan Campos, Josep Nicolas, Claudio C. Iemmi

Optical Engineering, Vol. 42, Issue 7, (July 2003). https://doi.org/10.1117/1.1580156

We propose the use of a multichannel optical correlator working with two spatial light modulators for texture classification. The architecture may implement any method based on frequency filtering in the Fourier domain. The addition of linear phases in each filter shifts the filtered image in the correlation plane and permits the implementation of several filters in parallel. To show the capacity of the system, we implement a particular case of texture classification method. The features used for the classification are the energy that falls in different frequency subbands. Six wedges and four rings in 24 frequency subbands divide the Fourier domain. By adding linear phases in different regions, it is possible to implement eight subbands simultaneously in the filter spatial light modulator. Then only three filters are necessary.

©(2003) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Joaquim Barbe, Juan Campos, Josep Nicolas, and Claudio C. Iemmi "Multichannel optical correlator for texture classification," Optical Engineering 42(7), (1 July 2003). https://doi.org/10.1117/1.1580156

Published: 1 July 2003

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