Bank Notes Recognition Using Statistical Classification

An approach is presented for bank’s note image analysis using geometric shape properties. The proposed approach, which is based on image processing techniques, has applications in banking and ATMs. Several image features, including geometric and moment invariants (regular and Zernike), are derived for recognition. The first-level classification is used to distinguish different kinds of notes and the second-level to recognize the country of the note. Two-dimensional structures, namely cluster-property and cluster-features matrices, have been employed to evaluate different note’s characteristics. Experimental results at the first- level recognition exhibit better performance of the geometric features compared to moment invariants and Zernike moments. On the other hand, Zernike moments showed supremacy in differential diagnosis at the second level to recognize countries.

Keywords:

Image analysis , Pattern recognition , Segmentation , Moment invariants , Geometric features.