Abstract
New spatial feature descriptor based on Gabor wavelet function is proposed. The proposed method is compared to Fourier descriptor. The experimental results with Advanced Earth Observing Satellite: ADEOS / Advanced Visible and Near-Infrared Radiometer: AVNIR image show an effectiveness of the proposed method. It is found that the restored image quality, in terms of root mean square error between the original and the restored images depends on the support length of the mother wavelet and is much better than that with the conventional Fourier descriptor method for spatial feature description.
Highlights
There are various examples of applying wavelet analysis to the processing analysis of earth observation satellite images
Through experiments with actual remote sensing satellite imagery data, it is found that the proposed description of geometric features of images based on the wavelet transform based on the Daubechies basis is more reproducible than that by existing Fourier descriptors under the condition of the same bandwidth
This is because, when the image space domain is transformed into the Fourier frequency domain and the wavelet frequency domain by the Fourier transform and the wavelet transform, respectively, if the band is halved to the maximum image frequency, the high frequency component disappears in the former case
Summary
There are various examples of applying wavelet analysis to the processing analysis of earth observation satellite images. As far as the authors are aware, there is no example of applying wavelet analysis to the method of describing the geometrical features of an image. The Fourier descriptor is well known as a method of describing the geometrical features of an image [29] – [31]. Some proposals have already been made for the method of applying the Fourier descriptor to open curves. The author considered that the Gabor descriptor enables the description of geometrical features with less information than the Fourier descriptor with less deterioration [32] – [34]. The section describes theoretical background and the proposed method for spatial feature descriptor based on Gabor wavelet function. Some experiments are described followed by conclusion together with some discussions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have