We examined the performance of linear and nonlinear processors (filters) for image recognition that are l_p-norm optimum in terms of tolerance to input noise and discrimination capabilities. These processors were developed by minimizing the l_p norm of the filter output due to the input scene and the output due to the noise. We tested the performance of the l_p-norm optimum filters by measuring the average peak-to-sidelobe ratio of the output of the filters for different values of p. We also tested the performance of these filters by placing a target in a scene containing additive noise and a realistic background. For the images presented here, the filters detected the target in the presence of additive noise and a realistic background. The tests conducted show that the discrimination capabilities of the l_p-norm filters improve as p decreases (p>1). This is shown by sharper peaks at the target location and higher average peak-to-sidelobe ratios for smaller values of p.

© 1999 Optical Society of America

[Optical Society of America ]

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

Related Journal Articles

• Three-dimensional object recognition by use of digital holography (OL)
• Texture classification based on comparison of second-order statistics. I. Two-point probability density function estimation and distance measure (JOSAA)
• l_p-norm optimum filters for image recognition. Part I. Algorithms (JOSAA)
• Generalized Rayleigh quotient approach to filter optimization (JOSAA)
• Modeling the sensitivity of moment invariants in a recognition system (JOSAA)

Related Conference Papers

• Integrated System Design for Application-Specific Imaging
• Integrated Sensing and Processing for Target Detection in Multi-Spectral data
• Template construction for object and biometric recognition
• Automatic classification of biological specimens: Diatoms
• Quantitative Histo- and Cytopathology