电子测量与仪器学报

刘正男,王凤随,付林军.改进的联合型图像超分辨率重建算法[J].电子测量与仪器学报,2020,34(1):111-120

改进的联合型图像超分辨率重建算法

Improved joint image super resolution reconstruction algorithm

DOI：

英文关键词:image reconstruction super resolution anchored neighborhood regression convolutional neural network image correlation coefficient

基金项目:安徽省自然科学基金(1708085MF154)、安徽高校省级自然科学研究基金（KJ2019A0162，KJ2015A071）资助项目

作者	单位
刘正男	1.高端装备先进感知与智能控制教育部重点实验室,2.安徽工程大学电气工程学院
王凤随	1.高端装备先进感知与智能控制教育部重点实验室,2.安徽工程大学电气工程学院
付林军	1.高端装备先进感知与智能控制教育部重点实验室,2.安徽工程大学电气工程学院

Author	Institution
Liu Zhengnan	1.Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education,2.Anhui Polytechnic University college of Electrical Engineering
Wang Fengsui	1.Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education,2.Anhui Polytechnic University college of Electrical Engineering
Fu Linjun	1.Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education,2.Anhui Polytechnic University college of Electrical Engineering

摘要点击次数: 391

全文下载次数: 0

中文摘要:

针对传统锚定邻域回归(anchored neighborhood regression, ANR)的图像超分辨率方法缺乏灵活性、且对图像的细节没有很好的恢复能力的缺点，提出一种锚定邻域回归和卷积神经网络(convolution neural network, CNN)相结合的图像重建方法。首先，在ANR中提出使用弹性网络回归模型，使算法具有特征选择的特点。其次，在CNN的图像预处理部分使用lanczos3插值方法，加快了运算速度，在特征提取中提出使用具有自门控特性的Swish函数作为激活函数，用于提高测试准确度。最后，在重建图像的评价方面提出了图像的相关系数，并用于对重建图像做进一步的有效性评估。实验结果证明，所提方法平均峰值信噪比（PSNR）达到了3268，平均结构相似性（SSIM）达到0938 0，平均相关系数达到0982 8。算法有效地恢复了图像的细节部分，图像质量得到了进一步提升。

英文摘要:

This paper presents an image reconstruction method combining convolution neural networks (CNN) with anchored neighborhood regression (ANR), aiming at the shortcomings of the conventional anchored neighborhood regression (ANR) image super resolution method, which is inflexible and incapable to restore image details. Firstly, the elastic network regression model is proposed in ANR to give the algorithm with the characteristics of feature selection. Secondly, the lanczos3 interpolation method is used in the part of image preprocessing of CNN to accelerate the operation speed. In the feature extraction, the Swish function with self gating characteristics is proposed as the activation function to improve the test accuracy. Finally, the correlation coefficient of the image is proposed in the evaluation of the reconstructed image and used for further evaluation of the reconstructed image. The experimental results show that the average PSNR, average SSIM and average correlation coefficient of the proposed method reach 0.982 8, 0.968 and 0.938 0 respectively. The algorithm effectively restores the details of the image and the image quality is further improved.

查看全文查看/发表评论下载PDF阅读器