单幅图像超分辨率(Single Image Super Resolution,SISR)在计算机视觉领域占有重要地位,该技术旨在从低分辨率图像中重建出高分辨率图像。近年来,深度神经网络在SISR领域起到了至关重要的作用,然而,目前利用卷积神经网络平等地对待高频...单幅图像超分辨率(Single Image Super Resolution,SISR)在计算机视觉领域占有重要地位,该技术旨在从低分辨率图像中重建出高分辨率图像。近年来,深度神经网络在SISR领域起到了至关重要的作用,然而,目前利用卷积神经网络平等地对待高频与低频特征,使得高频细节的重建表现不佳,输出过于平滑,缺少纹理信息。另一方面,过于深的网络不容易收敛,并且随着神经网络的深度增长,来自前一层的长期信息很容易在后期层中减弱或丢失,使得重建收益不能正比于网络的深度与计算复杂度。针对以上问题,对用于SISR的卷积神经网络的基本块提出了空间注意力模块与通道注意力模块,在同一通道中,不同位置的信息被空间注意力模块赋予不同的权重,不同通道间的权重由通道注意力模块决定,这使得高频信息在重建任务中获得更高的地位,提高了重建指标。进一步地提出了长期特征调制模块将网络的层深度转化为块深度,大大缩小了网络深度,以解决前层长期信息的丢失问题。在Set5等多个基准数据集上的峰值信噪比(PSNR)均比目前其他基于深度卷积神经网络的方法有所提升,这证明了提出的方法的有效性与先进性。展开更多
Image technology is applied more and more to help doctors to improve the accuracy of tumor diagnosis as well as researchers to study tumor characteristics. Image segmentation technology is an important part of image t...Image technology is applied more and more to help doctors to improve the accuracy of tumor diagnosis as well as researchers to study tumor characteristics. Image segmentation technology is an important part of image treatment. This paper summarizes the advances of image segmentation by using artificial neural network including mainly the BP network and convolutional neural network (CNN). Many CNN models with different structures have been built and successfully used in segmentation of tumor images such as supervised and unsupervised learning CNN. It is shown that the application of artificial network can improve the efficiency and accuracy of segmentation of tumor image. However, some deficiencies of image segmentation by using artificial neural network still exist. For example, new methods should be found to reduce the cost of building the marked data set. New artificial networks with higher efficiency should be built.展开更多
针对医学特征对患者病情发展的时间顺序无法有效表达,医学特征构建工作耗费大量人工成本,以及皮肤病数据样本数量较少等问题,提出了融合迁移学习和神经网络的皮肤病辅助诊断方法。该方法将TextLSTM(long short term memory neural netwo...针对医学特征对患者病情发展的时间顺序无法有效表达,医学特征构建工作耗费大量人工成本,以及皮肤病数据样本数量较少等问题,提出了融合迁移学习和神经网络的皮肤病辅助诊断方法。该方法将TextLSTM(long short term memory neural network for text)、TextCNN(convolutional neural network for text)以及RCNN(recurrent convolutional neural networks for text classification)等3种基于神经网络的文本分类模型应用于皮肤病辅助诊断,同时融入迁移学习技术,能够在一定程度上将皮肤病专业书籍中的理论知识迁移到诊断模型中。在皮肤病多分类实验中,本文方法的正确率优于对比方法;在皮肤病二分类实验中,本文方法的召回率优于对比方法。迁移学习对实验结果的积极影响率高于75%。展开更多
Aiming at the problem that the average recognition degree of the moving target line is low with the traditional motion target behaviour recognition method, a motion recognition method based on deep convolutional neura...Aiming at the problem that the average recognition degree of the moving target line is low with the traditional motion target behaviour recognition method, a motion recognition method based on deep convolutional neural network is proposed in this paper. A target model of deep convolutional neural network is constructed and the basic unit of the network is designed by using the model. By setting the unit, the returned unit is calculated into the standard density diagram, and the position of the moving target is determined by the local maximum method to realize the behavior identification of the moving target. The experimental results show that the multi-parameter SICNN256 model is slightly better than other model structures. The average recognition rate and recognition rate of the moving target behavior recognition method based on deep convolutional neural network are higher than those of the traditional method, which proves its effectiveness. Since the frequency of single target is higher than that of multiple recognition and there is no target similarity recognition, similar target error detection cannot be excluded.展开更多
文摘单幅图像超分辨率(Single Image Super Resolution,SISR)在计算机视觉领域占有重要地位,该技术旨在从低分辨率图像中重建出高分辨率图像。近年来,深度神经网络在SISR领域起到了至关重要的作用,然而,目前利用卷积神经网络平等地对待高频与低频特征,使得高频细节的重建表现不佳,输出过于平滑,缺少纹理信息。另一方面,过于深的网络不容易收敛,并且随着神经网络的深度增长,来自前一层的长期信息很容易在后期层中减弱或丢失,使得重建收益不能正比于网络的深度与计算复杂度。针对以上问题,对用于SISR的卷积神经网络的基本块提出了空间注意力模块与通道注意力模块,在同一通道中,不同位置的信息被空间注意力模块赋予不同的权重,不同通道间的权重由通道注意力模块决定,这使得高频信息在重建任务中获得更高的地位,提高了重建指标。进一步地提出了长期特征调制模块将网络的层深度转化为块深度,大大缩小了网络深度,以解决前层长期信息的丢失问题。在Set5等多个基准数据集上的峰值信噪比(PSNR)均比目前其他基于深度卷积神经网络的方法有所提升,这证明了提出的方法的有效性与先进性。
文摘Image technology is applied more and more to help doctors to improve the accuracy of tumor diagnosis as well as researchers to study tumor characteristics. Image segmentation technology is an important part of image treatment. This paper summarizes the advances of image segmentation by using artificial neural network including mainly the BP network and convolutional neural network (CNN). Many CNN models with different structures have been built and successfully used in segmentation of tumor images such as supervised and unsupervised learning CNN. It is shown that the application of artificial network can improve the efficiency and accuracy of segmentation of tumor image. However, some deficiencies of image segmentation by using artificial neural network still exist. For example, new methods should be found to reduce the cost of building the marked data set. New artificial networks with higher efficiency should be built.
文摘针对医学特征对患者病情发展的时间顺序无法有效表达,医学特征构建工作耗费大量人工成本,以及皮肤病数据样本数量较少等问题,提出了融合迁移学习和神经网络的皮肤病辅助诊断方法。该方法将TextLSTM(long short term memory neural network for text)、TextCNN(convolutional neural network for text)以及RCNN(recurrent convolutional neural networks for text classification)等3种基于神经网络的文本分类模型应用于皮肤病辅助诊断,同时融入迁移学习技术,能够在一定程度上将皮肤病专业书籍中的理论知识迁移到诊断模型中。在皮肤病多分类实验中,本文方法的正确率优于对比方法;在皮肤病二分类实验中,本文方法的召回率优于对比方法。迁移学习对实验结果的积极影响率高于75%。
文摘Aiming at the problem that the average recognition degree of the moving target line is low with the traditional motion target behaviour recognition method, a motion recognition method based on deep convolutional neural network is proposed in this paper. A target model of deep convolutional neural network is constructed and the basic unit of the network is designed by using the model. By setting the unit, the returned unit is calculated into the standard density diagram, and the position of the moving target is determined by the local maximum method to realize the behavior identification of the moving target. The experimental results show that the multi-parameter SICNN256 model is slightly better than other model structures. The average recognition rate and recognition rate of the moving target behavior recognition method based on deep convolutional neural network are higher than those of the traditional method, which proves its effectiveness. Since the frequency of single target is higher than that of multiple recognition and there is no target similarity recognition, similar target error detection cannot be excluded.