Design of Generative Adversarial Network Super‐Resolution Reconstruction Algorithm for Intelligent Security Images

ABSTRACT In the reconstruction of security images, the current generative adversarial network super‐resolution reconstruction algorithm is prone to generate unrealistic artifacts under high noise and low contrast, and the details of small targets are blurred. This paper adopts an improved Real‐ESRGAN (Real‐Enhanced Super‐Resolution Generative Adversarial Network) and CBAM (Convolutional Block Attention Module) algorithm to perform super‐resolution reconstruction of security images and improve the quality of reconstructed images. The study applies multi‐scale convolution kernels in the RRDB (residual in residual dense block) module of the model and uses convolution kernels of different sizes to extract and fuse image features to comprehensively capture local and overall detail information in the image. Then, based on Real‐ESRGAN, the CBAM module is applied in the generator, and the channel attention and spatial attention mechanisms are used to adaptively focus on multi‐scale features to enhance the modeling ability of texture details in the target area. Finally, a multi‐loss fusion optimization strategy is adopted, and color consistency loss and total variation loss are applied to effectively suppress artifacts and color drift problems in the reconstruction process. The experiment takes the security image in the license plate recognition task as an example to perform super‐resolution reconstruction. The results show that the PSNR (Peak Signal‐to‐Noise Ratio) and SSIM (Structural Similarity) of the improved Real‐ESRGAN‐CBAM are the best, reaching 20.1 dB and 0.635, respectively, under extremely high noise of 5 dB, and still reaching 26.1 dB and SSIM of 0.765 under extremely low contrast of 0.2. The experimental results show that the improved Real‐ESRGAN and CBAM combined algorithm in this paper greatly improves the reconstruction quality of security images, effectively suppresses the generation of artifacts, and can better meet the dual needs of intelligent security systems in image quality and practicality.