# Exposure image correction of electrical equipment nameplate based on the LMPEC algorithm

## TL;DR

A new algorithm improves the correction of overexposed or underexposed images of electrical equipment nameplates, making them easier to recognize.

## Contribution

The paper introduces an optimized LMPEC algorithm with PS-UNet++ and smooth L1 loss for better exposure correction of nameplate images.

## Key findings

- The optimized algorithm outperformed other methods on the electrical equipment nameplate dataset.
- The SSIM, PSNR, and PI metrics improved by 5.6%, 5.1%, and 7.96% compared to the original LMPEC algorithm.

## Abstract

An optimization algorithm based on the LMPEC algorithm is proposed to rectify the nameplate image to address the problem that overexposure and underexposure of the nameplate image of electrical equipment will make subsequent nameplate recognition difficult. In the network structure, the PS-UNet++ network is based on the sub-pixel convolution upsampling module, and the UNet++ network is constructed as the feature extraction sub-network of the optimization algorithm to extract more detailed information from the model. Smooth L1 loss is substituted for L1 loss in the loss function to prevent model oscillation. In addition, to increase the robustness of the model, an improved method built on the multi-scale training method is applied. The experimental results indicate that, among all comparison algorithms, the optimized algorithm performs the best on the data set of electrical equipment nameplate exposure the experimenter generated. Compared to the original LMPEC algorithm, the SSIM, PSNR, and PI image evaluation indices are enhanced by 5.6%, 5.1%, and 7.96%, respectively.