Abstract
In recent years, with the rapid development of image processing research, the study of nonstandard images has gradually become a research hotspot, for example, fabric images, remote sensing images, and gear images. Some of the remote sensing images have a complex background and low illumination compared with standard images and are easy to be mixed with noise during acquisition; some of the fabric images have rich texture information, which adds difficulty to the related processing, and are also easy to be mixed with noise during acquisition. In this paper, we propose a fractional-order adaptive P -Laplace equation image edge detection algorithm for the problem of image edge detection in which the edge and texture information of the image is lost. The algorithm can apply for the order adaptively to filter the noise according to the noise distribution of the image, and the adaptive diffusion factor is determined by both the fractional-order curvature and fractional-order gradient of the iso-illumination line and combined with the iterative approach to realize the fine-tuning of the noisy image. The experimental results demonstrate that the algorithm can remove the noise while preserving the texture and details of the image. A fractional-order partial differential equation image edge detection model with a fractional-order fidelity term is proposed for Gaussian noise. The model incorporates a fractional-order fidelity term because this fidelity term smoothes out the rougher parts of the image while preserving the texture in the original image in greater detail and eliminating the step effect produced by other models such as the Perona-Malik (PM) and Rudin-Osher-Fatemi (ROF) models. By comparing with other algorithms, the image edge detection effect is measured with the help of evaluation metrics such as peak signal-to-noise ratio and structural similarity, and the optimal value is selected iteratively so that the image with the best edge detection result is retained. A convolutional mask image edge detection model based on adaptive fractional-order calculus is proposed for the scattered noise in medical images. The adaption is mainly reflected in the model algorithm by constructing an exponential parameter relation that is closely related to the image, which can dynamically adjust the parameter values, thus making the model algorithm more practical. The model achieves the scattering noise removal in four steps.
Highlights
Nowadays, access to information is becoming more and more important, and information exists in a variety of forms, not in the form of voice transmission, but in a variety of forms, including information technology data, text, images, and video
This paper mainly introduces the application of fractionalorder calculus theory based on the image edge detection model; for different types of noise, it is applied to different scenarios; for the common Gaussian noise in life, the theory is used in the partial differential equation, to remove the noise while eliminating the step effect and achieve better preservation of the image texture; for the medical scattered noise, the fractional-order calculus function is combined with a model of fuzzy theory to process medical images
The main work accomplished in this paper includes the following aspects: the two noise models dealt with in this paper are introduced, followed by several edge detection algorithms related to the models proposed in this paper and the related theory of fractional-order calculus in this paper, to have a certain understanding of the theoretical basis of this paper, and point out the image
Summary
Access to information is becoming more and more important, and information exists in a variety of forms, not in the form of voice transmission, but in a variety of forms, including information technology data, text, images, and video. A lot of information is extracted from images, but in the process of transmitting or photographing images, we often use devices or transmission media limitations, making the acquired images more or less mixed with different shapes and colors of noise, because the existence of noise which leads to the visual effect of the whole image becomes very poor, which will seriously affect people’s access to information in the image For this reason, we regard noise removal as an important task in image processing, because if the noise can be minimized, it will help to obtain more local information in the image, which is related to the solution of the problems such as the accuracy of image segmentation, the accuracy of target recognition, and the completeness of edge extraction. The noise mainly exists in medical images, and the image is mainly manifested as black and white chaotic distribution of points; this noise will affect the clarity of the image; the image is very destructive, so it will not be conducive to doctor’s access to information in the image; the traditional method can achieve part of the edge detection effect, the overall performance is still very poor, such as Gaussian filter and wavelet transform, with the development of fractional-order definition; the edge detection model based on the mask template can remove this noise well, so further research on this model is very meaningful
Sign-in/Register to view highlights & summary 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.
