A transfer learning method of collaborating random walk and adaptive instance normalization for inscription image denoising
Year: 2025
Type: article
Abstract: Mess noise hinders reading and understanding of inscriptions in images. For image restoration from noise-corrupted images, existing network-learning-based methods can construct an excellent model to generate noise patterns. However, the performance of such models is degraded owing to the lack of high-quality training data and the complex noise pattern in inscription images, e.g., mixed noise with multiple levels. Herein, we first propose a novel noise generation model that can produce more realistic synthetic noise images using the random walk algorithm. Then, we propose an explainable inscription image denoising network using a variational inference model, where the joint distribution of clean-noise image pairs is approximated in a dual adversarial manner. The proposed network exhibits improved generalizability and adaptability to different noise characteristics using an estimated noise map and adaptive instance normalization. Finally, we introduce a transfer learning scheme to migrate the network learned from the synthetic noise image domain to a real-inscription image domain with a limited number of real-inscription images. The proposed method outperforms state-of-the-art methods.
Authors: Erhu Zhang, Yunjing Liu, Guangfeng Lin, Jinghong Duan
Institution: Xi'an University of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,200
OpenAlex ID: W7083577009