AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Multimedia tools and applications11/8/2022 ![]() Second, we introduce a parameter-free teaching-learning-based optimization method with strong exploitation operator into MPA, called MMPA-TLBO, which effectively trade-off between the exploitation and exploration procedures. Specifically, first, we propose a modified MPA (MMPA) that leverages chaotic map and opposition-based learning strategy in the initialization stage to generate high-quality individuals. To solve this issue, we advise an enhanced version of MPA based on teaching-learning-based optimization (MMPA-TLBO) which can concurrently improve the solution accuracy and the convergence speed. As a result, MPA could be misled to a local minima or even did not converge. However, corresponding to specific optimization tasks (e.g., visual tracking), it is usually hard to select correct multiple parameters in MPA, which will greatly limit the exploitation and exploration performance. Marine predators algorithm (MPA) has solved many challenging optimization problems since proposed. In addition, the method can handle the enhancement of images across different dynamic ranges, especially images with narrow a dynamic range, thus improving the amount of detailed information in the output image and maximizing the visual effect for human observers. An experiment was conducted that shows that the proposed method performs very well in terms of the amount of detailed information captured when compared to an existing improved method based on histogram equalization. After this, the processed low-frequency and three high-frequency sub-images are reconstructed to output a single high-information enhanced image. Then, the low-frequency sub-image is subjected to a histogram-limitation technique to acquire the wavelet integer coefficients. First, a single-layer wavelet transform is performed on the input image to obtain a low-frequency sub-image and three high-frequency sub-images. To resolve this issue, this paper presents an approach to image enhancement that uses a limited wavelet integer coefficient histogram to maintain high information entropy. This can lead to a loss of detail and make the target image look unnatural. ![]() However, traditional histogram equalization tends to have technical defects such as over-enhancement and artifacts. Histogram equalization plays an important role in digital image preprocessing. The results show that the calculation speed of this method is faster, and it can effectively enhance the information in the reflection image, and simultaneously effectively improve the clarity of the image. Finally, we compare the algorithm in this paper with the existing algorithms in subjective vision and objective evaluation. Then, it uses an improved guided image filtering algorithm to enhance the image, introduces adjustment parameters based on local variance information in the cost function of the guided filtering algorithm, and introduces an adaptive magnification factor in the detail layer. This method uses the dark channel prior algorithm to process the specular image, in which the moving window minimum filter is used to estimate the global illumination component of the specular image, and a weighting function based on local pixel chromatic aberration is introduced under the boundary constraints. Of 55 papers submitted, 10 were accepted for this issue after a stringent peer review process.Aiming at the problems of image quality degradation and information loss in images affected by reflections in real scenes, this paper proposes a fast and effective specular reflection image enhancement algorithm. ![]() Of 55 papers submitted, 10 were accepted for this issue after a stringent peer review process.ĪB - Data science on multimedia data: Challenges and applications EDITORIAL NOTE Data science on multimedia data: Challenges and applications © Springer Science+Business Media, LLC, part of Springer Nature 2022 Multimedia Tools and Applications gratefully acknowledges the editorial work of the scholars listed below on the special issue entitled “Data Science on Multimedia Data: Challenges and Applications” (SI 1167). N2 - Data science on multimedia data: Challenges and applications EDITORIAL NOTE Data science on multimedia data: Challenges and applications © Springer Science+Business Media, LLC, part of Springer Nature 2022 Multimedia Tools and Applications gratefully acknowledges the editorial work of the scholars listed below on the special issue entitled “Data Science on Multimedia Data: Challenges and Applications” (SI 1167). T1 - Data science on multimedia data: Challenges and applications ![]()
0 Comments
Read More
Leave a Reply. |