# Semi-Supervised Seven-Segment LED Display Recognition with an Integrated Data-Acquisition Framework

## TL;DR

This paper introduces a semi-supervised framework combining image processing and deep learning to improve the accuracy of LED display recognition in varying industrial environments.

## Contribution

The novel contribution is an integrated data-acquisition and semi-supervised adversarial learning framework for robust LED display recognition.

## Key findings

- The proposed framework improves classification accuracy and robustness in varying environmental conditions.
- Adversarial training with a modified CNN backbone enhances model performance.
- Stratified sampling via k-means clustering improves training data quality.

## Abstract

In industrial inspection and experimental data-acquisition scenarios, the accuracy and efficiency of digital tubes, which are commonly used display components, directly affect the intelligence of the system. However, models trained on data from specific environments may experience a significant drop in recognition accuracy when applied to different environments derived from impacts of various specific scenarios (e.g., temperature changes, changes in light intensity, changes in rate, and color contrast between equipment displays and environments, among others), which may affect model accuracy. To ensure recognition accuracy, we may need to collect data from specific environments to retrain the model for each specific environment, but manual annotation is often inefficient. To address these issues, this article proposes a solution integrating image processing with deep learning within specific scenarios, encompassing the entire workflow from data acquisition to model training. Employing image processing techniques to provide high-quality training data for models, we construct a semi-supervised adversarial learning framework based on an improved self-training algorithm. The framework employs the k-means clustering algorithm for stratified sampling preparation, adds the Squeeze-and-Excitation B Block to the Convolutional Neural Network backbone, and employs the Adversarial Generative Adversarial Network to generate adversarial examples for adversarial training, thus enhancing both classification accuracy and robustness.