抽样切分卷积实现跨尺度特征融合及内镜图像去模糊  

Sampling slice convolution for cross-scale feature fusion and endoscopic image deblurring

作　　者：严靖易 李小霞[1,2] 秦佳敏 文黎明[3] 周颖玥[1,2] Yan Jingyi;Li Xiaoxia;Qin Jiamin;Wen Liming;Zhou Yingyue(School of Information Engineering,Southwest University of Science&Technology,Mianyang Sichuan 621010,China;Robot Technology Used for Special Environment Key Laboratory of Sichuan Province,Mianyang Sichuan 621010,China;Sichuan Mianyang 404 Hospital,Mianyang Sichuan 621010,China)

机构地区：[1]西南科技大学信息与工程学院,四川绵阳621010 [2]特殊环境机器人技术四川省重点实验室,四川绵阳621010 [3]四川绵阳四〇四医院,四川绵阳621010

出　　处：《计算机应用研究》2023年第4期1233-1238,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(62071399);四川省科技计划重点研发项目(2021YFG0383)。

摘　　要：针对内镜图像去模糊过程中语义信息难以提取和细节纹理重建困难的问题,设计了一种新的抽样切分卷积,并将其应用于跨尺度特征融合过程中:通过等间隔抽样将大尺度特征无损切分成小尺度特征块,再与小尺度特征进行卷积融合。过程中大尺度特征的所有值都参与了特征融合,避免了细节信息的丢失;未对小尺度特征进行插值,避免了语义信息的模糊。为进一步实现特征互补,设计了特征交互融合模块,先用语义特征激活细节特征,再将两者融合。针对内镜图像亮通道、中间通道和暗通道的特征差异性设计了梯度重建和频域重建损失函数,提升了重建图像的锐度。在EAD和Kvasir-SEG数据集上,该算法的PSNR分别达到32.88 dB和33.01 dB,SSIM分别达到0.972和0.973。实验结果表明,该算法的性能优于主流去模糊算法,视觉上重建图像的纹理更清晰,且未产生伪影。To solve the challenges of semantic information extraction and texture reconstruction in the process of endoscopic image deblurring,this paper designed a new sampling slice convolution(SSC)and applied it to the cross-scale feature fusion process.It divided the large-scale features into small-scale feature blocks losslessly by sampling at equal intervals,and then fused these feature blocks with small-scale features through convolution.All values of large-scale features participate in the feature fusion process,which could avoid the loss of detailed information.There was no interpolation operation on small-scale features,which could avoid the blurring of their semantic information.This paper proposed a feature interaction fusion(FIF)mo-dule,which used semantic features to activate detailed features,and then fused the two to achieve feature complementarity.This paper designed gradient reconstruction and frequency domain reconstruction loss functions for the feature differences of the bright channel,middle channel,and dark channel of endoscopic images to improve the sharpness of reconstructed images.Experiments on EAD and Kvasir-SEG datasets show that the PSNR of the algorithm reaches 32.88 dB and 33.01 dB,respectively,and the SSIM reaches 0.972 and 0.973,respectively.The experimental results show that the performance of the proposed algorithm is better than that of the mainstream deblurring algorithms,and the texture of the reconstructed image is visually clearer and does not produce artifacts.

关 键 词：内镜图像重建 抽样切分卷积 去模糊 跨尺度特征融合 损失函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]