Off-line signature verification using directional PDF and neural networks

/in , , /by
Off-line signature verification using directional PDF and neural networks

Sabourin, Robert and Drouhard, Jean Pierre

Proceedings – International Conference on Pattern Recognition 1992

Abstract : The first stage of a complete Automatic Handwritten Signature Verification System (AHSVS) is described in this paper. Since only random forgeries are taken into account in this first stage of decision, the directional Probability Density Function (PDF) which is related to the overall shape of the handwritten signature has been taken into account as feature vector. Experimental results show that using both directional PDFs and the completely connected feed-forward neural network classifier are valuable to bild the first stage of a complete AHSVS.

You might also like
Rapid blockwise multi-resolution clustering of facial images for intelligent watermarking
Deep Active Learning for Joint Classification & Segmentation with Weak Annotator
Native language detection using the i-vector framework
Automated, portable, and low-cost system for home screening of peripheral arterial disease
A comparative study of the k nearest neighbour, threshold and neural network classifiers for handwritten signature verification using an enhanced directional PDF
An engineering approach to forecast volatility of financial indices
Rapport Technique
Deep high-order supervised hashing