Fuzzy operator infrared image deblurring algorithm for image blurring in dragon boat races

Abstract

To address the issues of poor robustness and weak generalization in existing infrared image deblurring methods, a fuzzy operator-based algorithm is proposed to solve the fuzzy imaging in dragon boat races. The experiment showed that the models trained utilizing original and synthesized datasets had very small differences in peak signal-to-noise ratio and structural similarity performance indicators, and the evaluation results were close. For a blurry image with 19 pixels, the number of blurry pixels extracted by the research algorithm was 22, with a difference of 3 pixels. For a blurry image with 35 pixels, the algorithm extracted 34 blurry pixels, with a difference of 1 pixel. This indicated that the deblurring result of the algorithm was accurate. In terms of peak signal-to-noise ratio and structural similarity, the peak signal-to-noise ratio and structure similarity were 30.98 dB and 0.921, respectively, both of which were the optimal values in all algorithms. In terms of the change of pixel gray value, the simulated blur length of the research method was 19 pixels, and the actual blur length was 20 pixels far less than 30 pixels. The results verified the effectiveness and significance of the algorithm for deblurring of dragon boat competition infrared images.

Keywords

• Dragon boat competition
• Fuzzy operators
• Infrared images
• Deblurring
• Attention mechanism