基于残差网络和特征融合的小麦图像修复模型

Wheat Image Inpainting Based on Residual Networks and Feature Fusion

针对基于生成对抗网络的多数图像修复算法所修复的图像纹理细节不清晰,不能充分融合神经网络提取的纹理细节信息和语义信息的问题,本文提出一种基于残差网络和特征融合的双阶段生成网络图像修复模型,通过修复训练集中被遮挡的图像,获取符合训练集整体分布的修复图像。首先,设计一种轻量型多尺度感受野残差模块,通过多个感受野不同的卷积核提取特征信息,提升粗化生成网络保留纹理信息的能力。其次构建一种双边精细修复网络结构,分别处理纹理细节信息和语义信息并进行聚合,实现图像的精细修复。最后基于GWHD数据集进行实验,验证本文算法的有效性。实验结果表明,本文模型较CE、GL、PEN-Net、CA算法,客观评价指标L1-loss降低0.56~3.79个百分点,PSNR和SSIM提升0.2~1.8 dB和0.02~0.08,并在人眼直观感受中实现了纹理结构清晰、语义特征合理的修复效果。相较于原GWHD数据集,在基于本文模型所扩充的小麦数据集中,运用YOLO v5s预测小麦麦穗的mAP提升1.41个百分点,准确率提升3.65个百分点,召回率提升0.36个百分点。

Aiming at the problem that most image inpainting algorithms based on generative adversarial networks restore unclear image texture details and cannot fully integrate texture detail information and semantic information extracted by neural networks,a two-stage algorithm was proposed based on residual network and feature fusion.A network image inpainting model was generated,and inpainted images were obtained which conformed to the overall distribution of the training set by inpainting the occluded images in the training set.Firstly,a lightweight multi-scale receptive field residual module was designed,which extracted feature information through multiple convolution kernels with different receptive fields,and improved the ability of the coarsening generation network to retain texture information.Secondly,a bilateral fine inpainting network structure was constructed,which processed texture detail information and semantic information separately and aggregated them to realize fine inpainting of images.Finally,experiments were carried out on the GWHD dataset to verify the effectiveness of the algorithm.The experimental results showed that compared with the CE,GL,PEN-Net,and CA algorithms,the objective evaluation index L1-loss of this model was reduced by 0.56~3.79 percentage points,PSNR and SSIM were improved by 0.2~1.8 d B and 0.02~0.08,and the restoration effect with clear texture structure and reasonable semantic features was realized in the intuitive perception of human eyes.Compared with the original GWHD data set,in the wheat data set expanded based on the proposed algorithm herein,the average detection accuracy m AP of predicting wheat ears using YOLO v5s was increased by 1.41 percentage points,the accuracy rate was increased by 3.65 percentage points,and the recall rate was increased by 0.36 percentage points.