adel tahar | Misurata University (original) (raw)

Uploads

Papers by adel tahar

Research paper thumbnail of Efficient features extraction for fingerprint classification with multi layer perceptron neural network

Signals, Circuits and Systems …, Jan 1, 2011

In this paper, we present a complete A complete fingerprints recognition system should fingerprin... more In this paper, we present a complete A complete fingerprints recognition system should fingerprint recognition system using an Artificial Neural include three stages. The first stage is detecting the location Network (ANN). The ANN is trained by backof the most important features of the fingerprints image, propagation algorithm on a set of fingerprint images. which is difficult and complicated because of the orientation Pseudo Zernike Moments (PZM) will be used as a and scaling of the image. The second stage is the extraction features vector for all images. To detect the region of of the pertinent features from the localized image and third interest on the fingerprint image, we have used shape stage involves classification of the image based on the information which is characterized by elliptical shape extracted features vector obtained in the last step.This PZM of the elliptical shape constitute the input of the classification can be performed using artificial Neural ANN. The data set is divided into two sets, training set Networks (ANN)[3-4] and test set. The ANN is trained using the training set and

Research paper thumbnail of Efficient features extraction for fingerprint classification with multi layer perceptron neural network

Signals, Circuits and Systems …, Jan 1, 2011

In this paper, we present a complete A complete fingerprints recognition system should fingerprin... more In this paper, we present a complete A complete fingerprints recognition system should fingerprint recognition system using an Artificial Neural include three stages. The first stage is detecting the location Network (ANN). The ANN is trained by backof the most important features of the fingerprints image, propagation algorithm on a set of fingerprint images. which is difficult and complicated because of the orientation Pseudo Zernike Moments (PZM) will be used as a and scaling of the image. The second stage is the extraction features vector for all images. To detect the region of of the pertinent features from the localized image and third interest on the fingerprint image, we have used shape stage involves classification of the image based on the information which is characterized by elliptical shape extracted features vector obtained in the last step.This PZM of the elliptical shape constitute the input of the classification can be performed using artificial Neural ANN. The data set is divided into two sets, training set Networks (ANN)[3-4] and test set. The ANN is trained using the training set and

Log In