基于DCGAN的紫外像增强器视场瑕疵图片的生成  

DCGAN-Based Generation of Ultraviolet Image Intensifier Field-of-View Defect Images

作　　者：丁习文 程宏昌 苏悦 闫磊 杨晔 党小刚 DING Xiwen;CHENG Hongchang;SU Yue;YAN Lei;YANG Ye;DANG Xiaogang(Kunming Institute of Physics,Kunming 650223,China;Key Laboratory of Low-Light-Level Night Vision Technology,Xi'an 710065,China)

机构地区：[1]昆明物理研究所,云南昆明650223 [2]微光夜视技术重点实验室,陕西西安710065

出　　处：《红外技术》2024年第5期608-616,共9页Infrared Technology

摘　　要：传统数据增强方法容易过拟合,为了解决紫外像增强器视场瑕疵图像数据集样本不平衡的问题,提升基于深度学习的条纹状瑕疵识别精度,提出了一种基于深度卷积生成对抗网络(Deep Convolution Generative Adversarial Network,DCGAN)的紫外像增强器视场瑕疵图像生成方法。通过对DCGAN进行损失函数的改进以及添加卷积注意力机制的优化,建立了紫外像增强器视场瑕疵图像生成模型,成功实现了紫外像增强器视场瑕疵图像的生成。随后,利用图像质量评价指标以及瑕疵检测模型来验证生成图像的有效性。实验结果显示,生成的紫外像增强器视场瑕疵图像可以满足使用需求,将生成图像融合到真实图像中再输入瑕疵检测模型可提高其检测精度。这一研究成果为三代微光像增强器和紫外像增强器的基于深度学习的视场瑕疵检测提供了技术支撑。Traditional data enhancement methods are easy to over-fit.To solve the problem of sample imbalance in the field of view defect image dataset of the ultraviolet image intensifier and improve the recognition accuracy of stripe defects based on deep learning,a field of view defect image generation method of the ultraviolet image intensifier based on a deep convolution generative adversarial network(DCGAN)is proposed.Through the improvement of the loss function of the DCGAN and the optimization of the convolution attention mechanism,the generation model of the field-of-view defect image of the UV image intensifier is established,and the generation of the field-of-view defect image of the UV image intensifier is successfully realized.The image quality evaluation index and defect detection models are then used to verify the effectiveness of the generated image.The experimental results show that the generated UV image intensifier field-of-view defect image can meet the application requirements,and the detection accuracy can be improved by fusing the generated image into the real image and then entering the defect detection model.

关 键 词：紫外像增强器 视场瑕疵检测 深度学习 图像生成 对抗网络 

分 类 号：TN23[电子电信—物理电子学] TP391.4[自动化与计算机技术—计算机应用技术]