<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Multi-exposure image fusion as a technical means to bridge the dynamic range gap between real scenes and image acquisition devices, which makes the fused images better quality and more realistic and vivid simulation of real scenes, has been widely concerned by scholars from various countries. In order to improve the adaptive fusion effect of multi-exposure images, this paper proposes a fusion algorithm based on multilayer perceptron (MLP) based on the perceptron model and verifies the feasibility of the algorithm by the peak signal-to-noise ratio (PSNR), correlation coefficient (PCC), structural similarity (SSMI) and HDR-VDR-2, an evaluation index of HDR image quality. Comparison with other algorithms revealed that the average PSNR of the MLP algorithm improved by 4.43% over the Ma algorithm, 7.88% over the Vanmail algorithm, 10.30% over the FMMR algorithm, 11.19% over the PMF algorithm, and 11.19% over the PMF algorithm. For PCC, the MLP algorithm improves by 20.14%, 17.46%, 2.31%, 11.24%, and 15.36% over the other algorithms in that order. For SSMI, the MLP algorithm improved by 16.99%, 8.96%, 17.17%, 14.41%, and 4.85% over the other algorithms, in that order. For HDR-VDR-2, the MLP algorithm improved by 3.02%, 2.79%, 6.84%, 4.90%, and 6.55% over the other algorithms, in that order. The results show that the MLP algorithm can avoid image artifacts while retaining more details. The MLP-based adaptive fusion method is a step further in the theoretical study of multi-exposure image fusion, which is of great significance for subsequent research and practical application by related technology vendors.</p>
</abstract>

Multi-exposure image fusion as a technical means to bridge the dynamic range gap between real scenes and image acquisition devices, which makes the fused images better quality and more realistic and vivid simulation of real scenes, has been widely concerned by scholars from various countries. In order to improve the adaptive fusion effect of multi-exposure images, this paper proposes a fusion algorithm based on multilayer perceptron (MLP) based on the perceptron model and verifies the feasibility of the algorithm by the peak signal-to-noise ratio (PSNR), correlation coefficient (PCC), structural similarity (SSMI) and HDR-VDR-2, an evaluation index of HDR image quality. Comparison with other algorithms revealed that the average PSNR of the MLP algorithm improved by 4.43% over the Ma algorithm, 7.88% over the Vanmail algorithm, 10.30% over the FMMR algorithm, 11.19% over the PMF algorithm, and 11.19% over the PMF algorithm. For PCC, the MLP algorithm improves by 20.14%, 17.46%, 2.31%, 11.24%, and 15.36% over the other algorithms in that order. For SSMI, the MLP algorithm improved by 16.99%, 8.96%, 17.17%, 14.41%, and 4.85% over the other algorithms, in that order. For HDR-VDR-2, the MLP algorithm improved by 3.02%, 2.79%, 6.84%, 4.90%, and 6.55% over the other algorithms, in that order. The results show that the MLP algorithm can avoid image artifacts while retaining more details. The MLP-based adaptive fusion method is a step further in the theoretical study of multi-exposure image fusion, which is of great significance for subsequent research and practical application by related technology vendors.

Adaptive fusion of multi-exposure images based on perceptron model

Tianjin University of Technology and Education

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Adaptive fusion of multi-exposure images based on perceptron model"}

Multi-exposure image fusion as a technical means to bridge the dynamic range gap between real scenes and image acquisition devices, which makes the fused...

Adaptive fusion of multi-exposure images based on perceptron model

Data publikacji: 28 kwi 2023

Zakres stron: -

Otrzymano: 24 sty 2022

Przyjęty: 15 lip 2022

DOI: https://doi.org/10.2478/amns.2023.1.00053

Słowa kluczowe
Perceptron model, Multi-exposure images, Image fusion, Multilayer perceptron, Adaptive algorithm

© 2023 Jianqiang Mei et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Adaptive fusion of multi-exposure images based on perceptron model

Data publikacji: 28 kwi 2023

Zakres stron: -

Otrzymano: 24 sty 2022

Przyjęty: 15 lip 2022

DOI: https://doi.org/10.2478/amns.2023.1.00053

Słowa kluczowePerceptron model, Multi-exposure images, Image fusion, Multilayer perceptron, Adaptive algorithm

© 2023 Jianqiang Mei et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Perceptron model, Multi-exposure images, Image fusion, Multilayer perceptron, Adaptive algorithm