Image enhancement algorithm in digital storage and visual inheritance of intangible cultural heritage

With the widespread application of image enhancement technology in the digital protection of intangible cultural heritage, research on improving low light image enhancement algorithms is receiving increasing attention. Embroidery, as an important component of intangible cultural heritage, has always been highly valued for its image enhancement work in both industry and academia. In recent years, deep learning (DL) has demonstrated outstanding performance in areas such as image classification, object detection, and image enhancement, providing new ideas for enhancing embroidery textures of different types. However, how to improve image illumination while preserving detail clarity and avoiding overfitting remains an urgent challenge that needs to be addressed. This article proposes an embroidery texture image enhancement model based on Generative Adversarial Network (GAN) to meet the demand for digital storage of intangible cultural heritage. This model significantly improves processing efficiency and effectively avoids overfitting by combining attention mechanisms while reducing the number of network parameters. The results indicate that our model not only significantly improves the brightness performance of the image, but also makes the enhanced embroidery texture smoother and more natural, with clearer details.