Application of the projection-onto-constraint-sets algorithm for optical pattern recognition Academic Article uri icon

abstract

  • Received January 23, 1991 Projection-onto-constraint sets is an efficient algorithm for constructing synthetic discriminant functions to be employed in pattern-recognition systems. The algorithm is implemented by a digital procedure based on a simulated joint-transform correlator … Projection-onto-constraint sets (POCS) has been used for many years in several areas of signal processing. Recently the use of the POCS was extended to new fields, such as computer-generaid hclegramn- and neural networks.2 In this Letter we show that it is also possible to employ the POCS for th" generation of synthetic discriminant functions3 (SDF's) for pattern recognition. Many algorithms3 used in computing a SDF consider only the value at one point, usually the origin of the correlation plane. Other algorithms4'5 are made more global by using a cost function that contains information about the whole correlation plane, but they still do not control the …

publication date

  • January 1, 1991