Abstract

A pattern recognition and classification system has been studied which computes the inner products of an input pattern with a generalized set of pattern functions. The system utilizes a filter whose impulse response consists of an amplitude superposition of a set of generalized pattern functions in phase-coded form and has a space–bandwidth product the same as that of a matched filter for one pattern function. Each pattern function in the general set may correspond to a different variation (e.g., scale or rotation) of the object to be detected. Because the amplitude superposition of the phase-coded pattern functions takes place in the digital computer, and the filter is created as a computer-generated hologram, the biasing problem of conventional, multiple exposure (intensity superposition) holograms is significantly reduced. This makes it possible to encode many more pattern functions than was previously possible using multiple exposure techniques. Furthermore, the use of computer-generated holograms eliminates the need to generate a transparency for each pattern function and complex phase code. To facilitate real-time operation a hybrid system was constructed consisting of a liquid crystal light valve for incoherent-to-coherent image conversion, a TV camera and image digitizer for image analysis, and a laser scanner to produce the computer-generated holograms. Both the TV camera/digitizer and the laser scanner systems were interfaced to a digital computer for automatic operation. Experimental results using the hybrid system are presented for pattern recognition of rotated and scaled objects and pattern classification. In the second half of the paper we provide an analysis on the SNR of the processor employing the coded-phase technique, on the diffraction efficiencies of computer-generated filters (amplitude superposition) vs conventional filters (intensity superposition), and on the number of pattern functions required for a certain recognition task.

© 1982 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Hybrid optical–digital pattern recognition

Fritz Merkle and Thomas Lörch
Appl. Opt. 23(10) 1509-1516 (1984)

Hybrid pattern recognition by features extracted from object patterns and Fraunhofer diffraction patterns

Takumi Minemoto and Junzo Narano
Appl. Opt. 24(18) 2914-2920 (1985)

Real-time deformation invariant optical pattern recognition using coordinate transformations

David Casasent, Shao-Feng Xia, Andrew J. Lee, and Jian-Zhong Song
Appl. Opt. 26(5) 938-942 (1987)

References

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
Login to access OSA Member Subscription

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 OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription

Figures (9)

You do not have subscription access to this journal. Figure files 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
Login to access OSA Member Subscription

Tables (3)

You do not have subscription access to this journal. Article tables 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
Login to access OSA Member Subscription

Equations (52)

You do not have subscription access to this journal. Equations 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
Login to access OSA Member Subscription

Metrics

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
Login to access OSA Member Subscription