Yazar "Nooraliei, Amir" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    ARTIFICIAL NEURAL NETWORKS BASED RECOGNITION OF SELECTED PALMPRINT FEATURES
    (AMER SOC MECHANICAL ENGINEERS, 2009) Altun, Adem Alpaslan; Nooraliei, Amir
    Biometric recognition suggests a reliable solution to the problem of user authentication in our networked society. Among all biometrics, palmprint-based recognition is one of the most reliable personal identification methods. In this study, a new approach to the palmprint recognition phase is presented. 2D Gabor filters are used for feature extraction of palmprints. After Gabor filtering, standard deviations are computed in order to generate the palmprint feature vector. In addition, Genetic algorithm based feature selection is used to select the best feature subset from the palmprint feature set. Four different algorithms of Artificial Neural Networks are then applied to the feature vectors for recognition of the people. Recognition rate equal to 98 percent are obtained by using conjugate gradient algorithms.
  • Küçük Resim Yok
    Öğe
    Edge Detection by Using IJA Automaton
    (IEEE COMPUTER SOC, 2009) Nooraliei, Amir; Altun, Adem Alpaslan
    In this paper, a fixed structure learning automaton (FSSA), called IJA, while study its steady state behavior in stationary environments is presented to extract the edge of the images. In this model, the gray scale matrix of the image is used. IJA Cellular learning automata edge detection model can extract the edge of the image without people participating in the course. Meanwhile, it is rather than the other cellular learning automata and achieves the edges with little evolution generations.
  • Küçük Resim
    Öğe
    Temperature Determination in Simulated Annealing Using Learning Automata
    (2009) Nooraliei, Amir; Altun, Adem Alpaslan
    This paper presents a new method for temperature parameter determination in simulated annealing for escaping local minimum in artificial potential fields. Learning automata for determine parameter is used. Temperature parameter determination cause improving to escape local minimum, high temperature cause robot farther as obstacles and long path. Furthermore, choice low temperature cause robot can't escape local minimum. The simulation results reflects that how the work has improved path and determine temperature.