A methodology to evaluate and improve reliability in paper currency neuro-classifiers

In this paper the reliability of the paper currency classifiers is studied and a new method is proposed for improving the reliability based on the local principal components analysis (PCA). At first the data space is partitioned into regions by using self-organizing map (SOM) model and then the PCA is performed in each region. A learning vector quantization (LVQ) network is employed as the main classifier of the system. The reliability of classification is evaluated by using an algorithm, which employs a function of the winning class probability and second maximal probability. By using a set of test data, we estimate the overall reliability of the system. The experimental results taken fro 1,200 samples of US dollar bills show that the reliability is increased up to 100% when the number of regions as well as the number of codebook vectors in the LVQ classifier is taken properly.