Publicado en International Journal on Document Analysis and Recognition (IJDAR) One fundamental step in off-line handwritten signature verification is the detection of the signature position within the document image. This paper introduces an original approach for signature position detection. The method is based on an accumulative evidence technique, searching the region that maximizes some measure of correspondence with a given reference signature. This measure is based on the similarity of the slope marked out by each of the strokes in the signature. Experiments have shown that the method can be used on real documents, such as bank checks, where images have a high noise level due to background interferences (i.e. machine or handwritten texts, stamps, and lines). The proposed method is robust to variability in the size of the signatures and has the advantage of using only one reference signature per person.

Publicado en Fuzzy Sets and Systems This paper introduces an adapted fuzzy snake approach for efficiently solving some of the practical constraints in the off-line signature verification problem. Our method is called fuzzy shape-memory snakes due to its resemblance to shape-memory alloys, which are metals that in high-temperature conditions can remember their original shape. In our approach, the snake also “remembers” its geometry during its iterative adjustment to a test signature. Off-line signature verification aims to establish the degree of genuineness of a given test signature when compared to a reference signature. Due to the shape and size variability in signatures of the same subject, a system with tolerance to imprecision and also with some “memory” of its initial configured shape, would be very useful for this complex verification problem. To our knowledge, snakes and other active contour models have not been previosly applied to the offline signature verifica...

Publicado en 2003 IEEE XIII Workshop on Neural Networks for Signal Processing A novel robust technique for the off-line signature verification problem in practical real conditions is presented. The technique is based on the use of compression neural networks, and in the automatic generation of the training set from only one signature for each writer. Our proposal incorporates a new kind of acceptance/rejection rule, which is based on the similarity between subimages or positional cuttings of a test signature and the corresponding representation stored in the class compression network. Experimental results show that the proposed technique reduces significantly the false acceptation rate (FAR).