基于深度神经网络的多聚焦红外图像非线性增强

Nonlinear enhancement of multi-focus infrared image based on depth neural network

当红外图像中含有多个聚焦目标主体时,会导致红外图像质量下降,部分区域出现模糊,因此,提出基于深度神经网络的多聚焦红外图像非线性增强方法。在引导滤波的作用下,从红外图像中获取细节层图像和背景层图像,在细节层图像中建立局部清晰度评价函数,得到清晰的细节层和背景层并融合二者。利用构建的深度神经网络结构,建立非线性增益函数,通过设定阈值和调整子带系数,实现对多聚焦红外图像的非线性增强。测试结果表明,所提方法在增强图像过程中,并没有改变原始图像的亮度和纹理波动;增强后的图像信息熵比原图像提高了57%左右,图像抗噪性能值更高,平均为7.4 dB,图像更清晰,SSIM值更趋近于1,平均为0.98,增强后的图片与原图片图像相似度更高,更接近于真实图像。

When there are multiple focused target subjects in the infrared image,it will lead to a decrease in the quality of the infrared image and blurring in some areas.Therefore,a deep neural network-based nonlinear enhancement method for multifocal infrared images is proposed.Under the guidance of guided filtering,detail layer images and background layer images are obtained from infrared images,and a local clarity evaluation function is established in the detail layer image to obtain clear detail layer and background layer,and the two are fused.Using the constructed deep neural network structure,establish a nonlinear gain function,and achieve nonlinear enhancement of multi focus infrared images by setting thresholds and adjusting subband coefficients.The test results show that the proposed method did not change the brightness and texture fluctuations of the original image during the enhancement process;The information entropy of the enhanced image is about 57% higher than that of the original image.The image anti noise performance value is higher,with an average of 7.4 dB.The image is clearer,and the SSIM value is closer to 1,with an average of 0.98.The enhanced image has a higher similarity with the original image,which is closer to the real image.