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

نویسندگان

  • Stanislaw Osowski
  • Do Dinh Nghia
چکیده

This paper presents the application of three di1erent 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 di1erent neural network structures associated with di1erent preprocessing of the data results in di1erent accuracy of recognition and classi9cation. 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 classi9ers based on the weighted summation of the signals from the neural networks has been proposed and checked in numerical experiments. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Wavelet descriptors for multiresolution recognition of handprinted characters

-We present a novel set of shape descriptors that represents a digitized pattern in a concise way and that is particularly well-suited for the recognition ofhandprinted characters. The descriptor set is derived from the wavelet transform of a pattern's contour. The approach is closely related to feature extraction methods by Fourier series expansion. The motivation to use an orthonormal wavelet...

متن کامل

Recognizing shipbuilding parts using artificial neural networks and Fourier descriptors

A pattern recognition system is described for recognizing shipbuilding parts using artificial neural networks and Fourier descriptors. The system uses shape contour information that is invariant of size, translation, and rotation. Fourier descriptors provide information, and the neural networks make decisions about the shapes. A brief review of the current state of the art is included, and resu...

متن کامل

A hybrid EEG-based emotion recognition approach using Wavelet Convolutional Neural Networks (WCNN) and support vector machine

Nowadays, deep learning and convolutional neural networks (CNNs) have become widespread tools in many biomedical engineering studies. CNN is an end-to-end tool which makes processing procedure integrated, but in some situations, this processing tool requires to be fused with machine learning methods to be more accurate. In this paper, a hybrid approach based on deep features extracted from Wave...

متن کامل

Indian Sign Language Recognition System Using New Fusion Based Edge Operator

The objective is to generate a basis for sign language recognizer under simple backgrounds. Complications arise in extracting shapes of hands and head using traditional segmentation models due to non-uniform lighting. This paper proposes a wavelet based fusion of two weak edge detection models. One is morphological subtraction model and the other is gradient based canny edge operator. Elliptica...

متن کامل

Analog design of a new neural network for optical character recognition

An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Pattern Recognition

دوره 35  شماره 

صفحات  -

تاریخ انتشار 2002