Abstract
The methods used for image contrast enhancement in the wavelet domain have been previously documented. The essence of these methods lies in the manipulation of the image during the reconstruction process, by changing the relationship between the components that require transformation. This paper proposes a new variant based on using undecimated wavelet transform and adapting the Gaussian function for scaling the coefficients of detail wavelet components, so that the role of low coefficients in the reconstructed image is greater. The enhanced image is then created by combining the new components. Applying the Haar wavelet minimises the effects of the relationship disturbance between components, and creates a small buffer around the edge. The proposed method was tested using six images at different scales, collected with handheld photo cameras, and aerial and satellite optical sensors. The results of the tests indicate that the method can achieve comparable, or even better enhancement effects for weak edges, than the well-known unsharp masking and Retinex methods. The proposed method can be applied in order to improve the visual interpretation of remote sensing images taken by various sensors at different scales.
Highlights
The interpretation of image content is performed in a visual and, more and more, in an automatic manner
The aim of the research presented in this paper is to develop a method where the edges are enhanced with low local contrast and the areas with high contrast are left unchanged
There is a conflict between the measurement and the visual assessment, especially in the shadowy area, where wavelet and Multiscale Retinex (MSR)-enhancement methods provide a clearer image
Summary
The interpretation of image content is performed in a visual and, more and more, in an automatic manner. The radiometric quality of the images in both cases is critical for the resulting analyses. Nowadays many optical sensors are used for acquiring images. Imaging sensors for remote sensing are satellite systems based on linear detector array and digital (formerly analogue) large-format aerial cameras. For capturing cultural heritage or industrial objects, various digital photo cameras are being used, much like those for taking photos from unmanned aerial vehicles (UAV). The diversity of image types is the reason for searching for universal image-enhancement methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
