Image Dehazing Algorithm Based on Deep Transfer Learning and Local Mean Adaptation

Background In recent years, haze has significantly hindered the quality and efficiency of daily tasks, reducing the visual perception range. Various approaches have emerged to address image dehazing, including image enhancement, image restoration, and deep learning-based dehazing methods. While these methods have improved dehazing performance to some extent, they often struggle in bright regions of the image, leading to distortions and suboptimal dehazing results. Moreover, dehazing models generally exhibit weak noise resistance, with the PSNR value of dehazed images typically falling below 30 dB. Residual noise remains in the processed images, leading to degraded visual quality. Currently, it is challenging for dehazing models to simultaneously ensure effective dehazing in bright regions while maintaining strong noise suppression capabilities. Methods To address both issues simultaneously, we propose an image dehazing algorithm based on deep transfer learning and local mean adaptation. The framework consists of several key modules: an atmospheric light estimation module based on deep transfer learning, a transmission map estimation module utilizing local mean adaptation, a haze-free image reconstruction module, an image enhancement module, and a noise reduction module. This design not only ensures the stable and accurate estimation of atmospheric light but also enables the model to effectively process different regions of hazy images, preventing distortion artifacts. Furthermore, to enrich the details of the dehazed images and enhance the dehazing performance while improving the model’s noise resistance, we incorporate an image enhancement module and a noise reduction module into the proposed dehazing framework. Results To validate the effectiveness of the proposed algorithm, we conducted dehazing experiments on a self-constructed hazy dataset, the SOTS (outdoor) dataset, and the NH-HAZE dataset. Experimental results demonstrate that the proposed dehazing model achieves superior performance across all three datasets. The dehazed images exhibit no color distortion, and the PSNR values consistently exceed 30 dB, indicating high-quality dehazed images. The dehazed images also demonstrate a significant advantage in SSIM performance compared to mainstream dehazing algorithms, consistently achieving a similarity of over 85%. This indicates that the proposed dehazing model effectively mitigates distortion while enhancing noise resistance, exhibiting strong generalization capabilities across different datasets. Conclusion The experimental results confirm that the proposed dehazing algorithm effectively handles bright regions such as the sky while significantly improving the model’s noise resistance, reducing residual noise in the dehazed images. Both aspects demonstrate strong performance, validating the effectiveness and superiority of the proposed dehazing model. Furthermore, the algorithm achieves consistently good dehazing performance across all three hazy datasets, demonstrating its generalization capability. This study introduces a novel dehazing method and theoretical framework, which can be effectively applied to scenarios such as autonomous driving and intelligent surveillance systems. The proposed model provides a new approach to image dehazing, contributing to advancements in related fields and fostering further development in haze removal technologies.