Fourier and wavelet descriptors for shape recognition using neural networks—a comparative study

✍ Scribed by Stanislaw Osowski; Do Dinh Nghia

• Publisher: Elsevier Science
• Year: 2002
• Tongue: English
• Weight: 207 KB
• Volume: 35
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/s0031-3203(01)00153-4

✦ Synopsis

This paper presents the application of three di erent types of neural networks to the 2-D pattern recognition on the basis of its shape. They include the multilayer perceptron (MLP), Kohonen self-organizing network and hybrid structure composed of the self-organizing layer and the MLP subnetwork connected in cascade. The recognition is based on the features extracted from the Fourier and wavelet transformations of the data, describing the shape of the pattern. Application of di erent neural network structures associated with di erent preprocessing of the data results in di erent accuracy of recognition and classiÿcation. The numerical experiments performed for the recognition of simulated shapes of the airplanes have shown the superiority of the wavelet preprocessing associated with the self-organizing neural network structure. The integration of the individual classiÿers based on the weighted summation of the signals from the neural networks has been proposed and checked in numerical experiments.