Song Man Hyok, a section head at the Faculty of Earth Science and Technology, has proposed a new method to extract image features and to evaluate fractality based on two-dimensional (2D) continuous wavelet transform (CWT).
Multi-directional 2D CWT coefficients are used to determine the direction and magnitude of image intensity gradients directly unlike other methods using gradient components in horizontal and vertical directions. Image feature points are detected by comparing candidate directional 2D CWT coefficients at candidate points and their neighbors instead of gradient magnitudes or 2D CWT moduli used in traditional methods. It enables extracting multiscale image features including line singularities such as corners which are recognized to be hardly extracted by traditional methods. This offers an advantageous condition to study fractal objects consisting of lots of line singularities.
Assuming that the detected multiscale image features can reflect multiscale fractal measures used to evaluate fractality, that is, self-similarity across scales, he has proposed a method to evaluate fractality and calculate fractal dimensions using multiscale image features.
The application of the proposed method to theoretical fractal models proved that it is convenient and effective in extracting the image features of the models consisting of many line singularities and in calculating their fractal dimensions. It is concluded that the method is useful to deal with fractality evaluation of geoscientific objects such as coastlines and stream networks.
For more information, please refer to his paper “Image feature extraction and fractality evaluation based on two-dimensional continuous wavelet transform: Application to digital elevation model data” published in the SCI Journal “Fractals”.
© 2021 KumChaek University of Technology