Browsing by Author "Rotinwa-Akinbile, M. O."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A novel palmprint segmentation technique
    (IEEE, 2011-12-12) Rotinwa-Akinbile, M. O.; Aibinu, A. M.; Salami, Momoh-Jimoh E.
    Recent paradigm shift from the conventional contact based palmprint recognition to contactless based systems (CBS) has necessitated the development of a variety of these systems. A major challenge of these systems is it robustness to illumination variation in unconstrained environment, thus making segmentation difficult. In this paper, the acquired image undergoes color space conversion and the output is filtered using coefficients obtained from the training of an artificial neural network (ANN) based model coefficient determination technique. Performance analysis of the proposed technique shows better performance in term of mean square error, true positive rate and accuracy when compared with two other techniques. Furthermore, it has also been observed that the proposed method is illumination invariant hence its suitability for deployment in contactless palmprint recognition systems.
  • Thumbnail Image
    Item
    Palmprint recognition using principal lines characterization
    (IEEE, 2011-12-12) Rotinwa-Akinbile, M. O.; Aibinu, Abiodun M.; Salami, Momoh-Jimoh E.
    In this paper, a novel contactless Palmprint recognition system using palm print principal line-based feature extraction technique has been proposed. The discriminative Palmprint features were extracted from a pre-processed acquired images using easily available and low cost camera. Distances from endpoints to endpoints and point of interception to endpoints were calculated and transformed to frequency domain by the application of Discrete Fourier Transformed (DFT) technique. The extracted K-points DFT coefficients has been used as the discriminating features for recognition and identification purposes using correlation technique, power spectral matching and Euclidean distance measure. The proposed technique has been observed to be rotation, scale and translation invariant and accuracy of 100% was achieved in a 1-to-4 recognition and classification verification.