Abstract
We present an optical implementation of an improved version of the Kohonen map neural network applied to the recognition of handwritten digits taken from a postal code database. Improvements result from the introduction of supervision during the learning stage, a technique that also simplifies the map layer labeling. The experimental implementation is based on a frequency-multiplexed raster computer-generated hologram used to realize the required N 4 interconnection. The setup is shown to be equivalent to a 64-channel correlator. Computer simulations are used to study various detection and classification procedures. The results of the optical experiments, obtained with binary phase computer-generated holograms, are presented and shown to be in excellent agreement with the simulations.
© 1996 Optical Society of America
Full Article | PDF ArticleMore Like This
Wesley E. Foor and Mark A. Neifeld
Appl. Opt. 34(32) 7545-7555 (1995)
Yann Frauel, Gilles Pauliat, André Villing, and Gérald Roosen
Appl. Opt. 40(29) 5162-5169 (2001)
Bahram Javidi, Jian Li, and Qing Tang
Appl. Opt. 34(20) 3950-3962 (1995)