To overcome the shortcomings of the Lee image enhancement algorithm and its improvement based on the logarithmic image processing(LIP) model, this paper proposes what we believe to be an effective image enhancement al...To overcome the shortcomings of the Lee image enhancement algorithm and its improvement based on the logarithmic image processing(LIP) model, this paper proposes what we believe to be an effective image enhancement algorithm. This algorithm introduces fuzzy entropy, makes full use of neighborhood information, fuzzy information and human visual characteristics.To enhance an image, this paper first carries out the reasonable fuzzy-3 partition of its histogram into the dark region, intermediate region and bright region. It then extracts the statistical characteristics of the three regions and adaptively selects the parameter αaccording to the statistical characteristics of the image’s gray-scale values. It also adds a useful nonlinear transform, thus increasing the ubiquity of the algorithm. Finally, the causes for the gray-scale value overcorrection that occurs in the traditional image enhancement algorithms are analyzed and their solutions are proposed.The simulation results show that our image enhancement algorithm can effectively suppress the noise of an image, enhance its contrast and visual effect, sharpen its edge and adjust its dynamic range.展开更多
The key to the wavelet based denoising teehniquea is how to manipulate the wavelet coefficients. By referring to the idea of Inclusive-OR in the design of circuits, this paper proposes a new algorithm called wavelet d...The key to the wavelet based denoising teehniquea is how to manipulate the wavelet coefficients. By referring to the idea of Inclusive-OR in the design of circuits, this paper proposes a new algorithm called wavelet domain Inclusive-OR denoising algorithm（WDIDA）, which distinguishes the wavelet coefficients belonging to image or noise by considering their phases and modulus maxima simultaneously. Using this new algorithm, the denoising effects are improved and the computation time is reduced. Furthermore, in order to enhance the edges of the image but not magnify noise, a contrast nonlinear enhancing algorithm is presented according to human visual properties. Compared with traditional enhancing algorithms, the algorithm that we proposed has a better noise reducing performanee , preserving edges and improving the visual quality of images.展开更多
零样本图像分类解决了训练和测试数据类别不相交的问题,人类标注属性是一种常用的实现零样本图像分类的辅助知识.为协助专家设计类属性矩阵,提出了一种交互式构建方法,简化了烦琐且缺乏指导的流程.首先,通过一种基于概念的深度学习可解...零样本图像分类解决了训练和测试数据类别不相交的问题,人类标注属性是一种常用的实现零样本图像分类的辅助知识.为协助专家设计类属性矩阵,提出了一种交互式构建方法,简化了烦琐且缺乏指导的流程.首先,通过一种基于概念的深度学习可解释性方法,在训练集图像数据中提取出可理解的属性信息;然后,采用多视图协作的交互方式,探索和分析已提取属性的重要性.系统提供了全局和局部2种方式,辅助用户设计测试集数据类别的属性值;最后,通过在数据集Animals with Attributes2上进行的案例分析,以及采用李克特量表的用户评估实验,验证了设计方法的有效性和实用性,可以帮助专家用户高效且便捷地完成类属性构建工作.展开更多
为解决现有VSLAM特征提取器在室内环境中对纹理和光照变化敏感、特征点冗余导致的局部依赖性过强以及硬件资源受限时的存储开销问题,提出了一种面向纹理的均匀FAST特征提取器(texture-oriented and homogenized FAST feature extractor,...为解决现有VSLAM特征提取器在室内环境中对纹理和光照变化敏感、特征点冗余导致的局部依赖性过强以及硬件资源受限时的存储开销问题,提出了一种面向纹理的均匀FAST特征提取器(texture-oriented and homogenized FAST feature extractor, TOHF)。结合HVS(human visual system),采用二阶段阈值策略来更敏感地应对纹理的清晰度和复杂度差异。根据特征点密度的变化来动态调整特征点的分布,在兼顾计算效率和存储开销的同时,保证特征点分布结构信息。在资源受限设备录制的数据集和官方Eu Roc数据集上基于ORB-SLAM3框架开展实验,采用匹配率、重投影误差、绝对轨迹误差(ATE)和耗时作为评估指标。实验结果表明:TOHF在视觉加惯导模式下带来更高精度和鲁棒性的同时,仍满足实时性要求。展开更多
提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容...提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容图像的全局特征,增强对屏幕内容图像整体信息的表征能力;然后使用综合局部注意力机制提取屏幕内容图像的局部特征,使局部特征能够聚焦于屏幕内容图像中更吸引人注意的细节部分;最后使用双通道特征映射模块预测屏幕内容图像的质量分数。在SCID和SIQAD数据集上,MTA-SCI的斯皮尔曼秩序相关系数(Spearman's rank order correlation coefficient,SRCC)分别达到0.9602和0.9233,皮尔森线性相关系数(Pearson linear correlation coefficient,PLCC)分别达到0.9609和0.9294。实验结果表明,MTA-SCI在预测屏幕内容图像质量任务中具有较高的准确性。展开更多
基金supported by the National Natural Science Foundation of China(61472324)
文摘To overcome the shortcomings of the Lee image enhancement algorithm and its improvement based on the logarithmic image processing(LIP) model, this paper proposes what we believe to be an effective image enhancement algorithm. This algorithm introduces fuzzy entropy, makes full use of neighborhood information, fuzzy information and human visual characteristics.To enhance an image, this paper first carries out the reasonable fuzzy-3 partition of its histogram into the dark region, intermediate region and bright region. It then extracts the statistical characteristics of the three regions and adaptively selects the parameter αaccording to the statistical characteristics of the image’s gray-scale values. It also adds a useful nonlinear transform, thus increasing the ubiquity of the algorithm. Finally, the causes for the gray-scale value overcorrection that occurs in the traditional image enhancement algorithms are analyzed and their solutions are proposed.The simulation results show that our image enhancement algorithm can effectively suppress the noise of an image, enhance its contrast and visual effect, sharpen its edge and adjust its dynamic range.
文摘The key to the wavelet based denoising teehniquea is how to manipulate the wavelet coefficients. By referring to the idea of Inclusive-OR in the design of circuits, this paper proposes a new algorithm called wavelet domain Inclusive-OR denoising algorithm（WDIDA）, which distinguishes the wavelet coefficients belonging to image or noise by considering their phases and modulus maxima simultaneously. Using this new algorithm, the denoising effects are improved and the computation time is reduced. Furthermore, in order to enhance the edges of the image but not magnify noise, a contrast nonlinear enhancing algorithm is presented according to human visual properties. Compared with traditional enhancing algorithms, the algorithm that we proposed has a better noise reducing performanee , preserving edges and improving the visual quality of images.
文摘零样本图像分类解决了训练和测试数据类别不相交的问题,人类标注属性是一种常用的实现零样本图像分类的辅助知识.为协助专家设计类属性矩阵,提出了一种交互式构建方法,简化了烦琐且缺乏指导的流程.首先,通过一种基于概念的深度学习可解释性方法,在训练集图像数据中提取出可理解的属性信息;然后,采用多视图协作的交互方式,探索和分析已提取属性的重要性.系统提供了全局和局部2种方式,辅助用户设计测试集数据类别的属性值;最后,通过在数据集Animals with Attributes2上进行的案例分析,以及采用李克特量表的用户评估实验,验证了设计方法的有效性和实用性,可以帮助专家用户高效且便捷地完成类属性构建工作.
文摘为解决现有VSLAM特征提取器在室内环境中对纹理和光照变化敏感、特征点冗余导致的局部依赖性过强以及硬件资源受限时的存储开销问题,提出了一种面向纹理的均匀FAST特征提取器(texture-oriented and homogenized FAST feature extractor, TOHF)。结合HVS(human visual system),采用二阶段阈值策略来更敏感地应对纹理的清晰度和复杂度差异。根据特征点密度的变化来动态调整特征点的分布,在兼顾计算效率和存储开销的同时,保证特征点分布结构信息。在资源受限设备录制的数据集和官方Eu Roc数据集上基于ORB-SLAM3框架开展实验,采用匹配率、重投影误差、绝对轨迹误差(ATE)和耗时作为评估指标。实验结果表明:TOHF在视觉加惯导模式下带来更高精度和鲁棒性的同时,仍满足实时性要求。
文摘提出一种基于多任务注意力机制的无参考屏幕内容图像质量评价算法(multi-task attention mechanism based no reference quality assessment algorithm for screen content images,MTA-SCI)。MTA-SCI首先使用自注意力机制提取屏幕内容图像的全局特征,增强对屏幕内容图像整体信息的表征能力;然后使用综合局部注意力机制提取屏幕内容图像的局部特征,使局部特征能够聚焦于屏幕内容图像中更吸引人注意的细节部分;最后使用双通道特征映射模块预测屏幕内容图像的质量分数。在SCID和SIQAD数据集上,MTA-SCI的斯皮尔曼秩序相关系数(Spearman's rank order correlation coefficient,SRCC)分别达到0.9602和0.9233,皮尔森线性相关系数(Pearson linear correlation coefficient,PLCC)分别达到0.9609和0.9294。实验结果表明,MTA-SCI在预测屏幕内容图像质量任务中具有较高的准确性。
