In this paper, we present an efficient approach for unsupervised segmentation of natural and textural images based on the extraction of image features and a fast active contour segmentation model. We address the probl...In this paper, we present an efficient approach for unsupervised segmentation of natural and textural images based on the extraction of image features and a fast active contour segmentation model. We address the problem of textures where neither the gray-level information nor the boundary information is adequate for object extraction. This is often the case of natural images composed of both homogeneous and textured regions. Because these images cannot be in general directly processed by the gray-level information, we propose a new texture descriptor which intrinsically defines the geometry of textures using semi-local image information and tools from differential geometry. Then, we use the popular Kullback-Leibler distance to design an active contour model which distinguishes the background and textures of interest. The existence of a minimizing solution to the proposed segmentation model is proven. Finally, a texture segmentation algorithm based on the Split-Bregrnan method is introduced to extract meaningful objects in a fast way. Promising synthetic and real-world results for gray-scale and color images are presented.展开更多
Identifying critical nodes is a pivotal research topic in network science,yet the efficient and accurate detection of highly influential nodes remains a challenge.Existing centrality measures predominantly rely on loc...Identifying critical nodes is a pivotal research topic in network science,yet the efficient and accurate detection of highly influential nodes remains a challenge.Existing centrality measures predominantly rely on local or global topological structures,often overlooking indirect connections and their interaction strengths.This leads to imprecise assessments of node importance,limiting practical applications.To address this,we propose a novel node centrality measure,termed six-degree gravity centrality(SDGC),grounded in the six degrees of separation theory,for the precise identification of influential nodes in networks.Specifically,we introduce a set of node influence parameters—node mass,dynamic interaction distance,and attraction coefficient—to enhance the gravity model.Node mass is calculated by integrating K-shell and closeness centrality measures.The dynamic interaction distance,informed by the six-degrees of separation theory,is determined through path searches within six hops between node pairs.The attraction coefficient is derived from the difference in K-shell values between nodes.By integrating these parameters,we develop an improved gravity model to quantify node influence.Experiments conducted on nine real-world networks demonstrate that SDGC significantly outperforms nine existing classical and state-of-the-art methods in identifying the influential nodes.展开更多
针对视觉结构类似导致的文种相似性问题,基于局部三值模式的相邻共生矩阵(co-occurrence of adjacent local ternary patterns,CoALTP)提出一种具有判别性和鲁棒性的局部三值模式的相邻共生矩阵(discriminant and robust co-occurrence ...针对视觉结构类似导致的文种相似性问题,基于局部三值模式的相邻共生矩阵(co-occurrence of adjacent local ternary patterns,CoALTP)提出一种具有判别性和鲁棒性的局部三值模式的相邻共生矩阵(discriminant and robust co-occurrence of adjacent local ternary patterns,DRCoALTP)方法,用于获取图像纹理。计算文档图像的相邻稀疏局部三值模式(adjacent sparse local ternary patterns,ASLTP),将采样点数量设定为8,以便获得详细的局部纹理,设计出一种基于自适应中值滤波思想的半自适应阈值方法,用于提取灰度图像中心像素周边对角邻域像素的编码值。ASLTP在邻域像素位置存放稀疏局部三值模式(local ternary patterns,LTP)的值,提取灰度共生矩阵(gray-level co-occurrence matrix,GLCM),从4个方向统计使用ASLTP后灰度图像像素之间的频率关系。该算法在阿拉伯文、俄文、简体中文、哈萨克文、藏文、蒙古文、土耳其文、维吾尔文、英文、吉尔吉斯斯坦文和塔吉克斯坦文11个文种的自建印刷体文档图像数据集中验证。试验结果表明,相较于基线和先进的纹理方法,改进后的方法更具判别性,平均识别准确率为99.14%。为改善CoALTP方法可能产生低效分类特征的问题,提出半自适应阈值方法,有效提高识别率并抑制噪声。此外,针对算法产生的高维特征,采用基于均方差的特征选择方法,通过支持向量机(support vector machine,SVM)分类器特征选择后,识别速度提高284%,对11个文种的平均识别准确率达99.44%。展开更多
心脏分割算法提供精准把握心脏结构的信息,辅助医生进行诊断、制定治疗计划以及进行手术前的评估工作,提高临床治疗的效果并减轻并发症。然而,心脏分割在应用中存在诸多问题。手动分割方法不仅耗时费力,并且具有很强的主观意识。全监督...心脏分割算法提供精准把握心脏结构的信息,辅助医生进行诊断、制定治疗计划以及进行手术前的评估工作,提高临床治疗的效果并减轻并发症。然而,心脏分割在应用中存在诸多问题。手动分割方法不仅耗时费力,并且具有很强的主观意识。全监督的心脏分割方法虽已取得一定成果,但标注数据的依赖性过高。现有的半监督分割方法在处理复杂的心脏结构和病理变化时表现仍不够理想,难以在实际临床环境中稳定应用。为解决这一问题,提出了心脏磁共振成像(MRI)分割方法,结合Linformer and Performer merge V-Net(LPV-Net)和3D Enhanced Discriminator with Attention(3D-EDA)技术,实现了全局-局部信息的有效整合。LPV-Net模块由LinPerBlock和改进的V-Net联袂打造,旨在规范模型训练过程、实现全局与局部信息的有机整合,有效提高分割效果的准确性与鲁棒性。同时引入新鉴别器3D-EDA规范未标记数据,并加入关键模块CARE-Layer,集成自定义注意力模块以增强对特征重要信息的捕捉能力,辅助网络可提高主网络分割指标性能。在左心房数据集上进行综合实验,并将所提方法与MC-Net,V-Net等其他先进的半监督方法进行比较,发现该方法在基准数据集上的表现尤为优异。特别是在使用有限标签数据进行训练时,该方法仍然展示出卓越的性能;当仅使用10%和20%的标记数据进行训练时,该方法的Dice系数分别达到88.50%和90.39%。展开更多
针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样...针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样本中的故障信息,避免了因有标记故障样本不足引起的过学习问题,同时采用正交迭代方式求解最优正交映射矩阵,克服现有方法无法得到正交映射矩阵的不足。正交映射矩阵的基矢量统计不相关,可有效地提高所得低维特征矢量的可辨识性。通过正交映射矩阵对故障样本集和新增样本进行维数约简,并将维数约简的结果输入粗糙优化k最近邻分类器(Coarse to fine k nearest neighbor classifier,CFKNNC)进行学习训练和故障识别。所提方法集成了OSELF在维数约简和CFKNNC在模式识别的优势,有效地提高了故障诊断的精度。通过齿轮箱故障模拟试验验证了该方法的有效性。展开更多
基金supported by Swiss National Science Foundation Grant #205320-101621supported by ONR N00014-03-1-0071
文摘In this paper, we present an efficient approach for unsupervised segmentation of natural and textural images based on the extraction of image features and a fast active contour segmentation model. We address the problem of textures where neither the gray-level information nor the boundary information is adequate for object extraction. This is often the case of natural images composed of both homogeneous and textured regions. Because these images cannot be in general directly processed by the gray-level information, we propose a new texture descriptor which intrinsically defines the geometry of textures using semi-local image information and tools from differential geometry. Then, we use the popular Kullback-Leibler distance to design an active contour model which distinguishes the background and textures of interest. The existence of a minimizing solution to the proposed segmentation model is proven. Finally, a texture segmentation algorithm based on the Split-Bregrnan method is introduced to extract meaningful objects in a fast way. Promising synthetic and real-world results for gray-scale and color images are presented.
基金supported by the National Natural Science Foundation of China(Grant No.62173065)the Natural Science Foundation of Beijing(Grant No.4242040)+1 种基金the Intelligent Policing and National Security Risk Management Laboratory Open Topics for the year 2025(Grant No.ZHKFYB2503)the Intelligent Policing and National Security Risk Management Laboratory Open Topics for the year 2024(Grant No.ZHKFZD2401).
文摘Identifying critical nodes is a pivotal research topic in network science,yet the efficient and accurate detection of highly influential nodes remains a challenge.Existing centrality measures predominantly rely on local or global topological structures,often overlooking indirect connections and their interaction strengths.This leads to imprecise assessments of node importance,limiting practical applications.To address this,we propose a novel node centrality measure,termed six-degree gravity centrality(SDGC),grounded in the six degrees of separation theory,for the precise identification of influential nodes in networks.Specifically,we introduce a set of node influence parameters—node mass,dynamic interaction distance,and attraction coefficient—to enhance the gravity model.Node mass is calculated by integrating K-shell and closeness centrality measures.The dynamic interaction distance,informed by the six-degrees of separation theory,is determined through path searches within six hops between node pairs.The attraction coefficient is derived from the difference in K-shell values between nodes.By integrating these parameters,we develop an improved gravity model to quantify node influence.Experiments conducted on nine real-world networks demonstrate that SDGC significantly outperforms nine existing classical and state-of-the-art methods in identifying the influential nodes.
文摘针对视觉结构类似导致的文种相似性问题,基于局部三值模式的相邻共生矩阵(co-occurrence of adjacent local ternary patterns,CoALTP)提出一种具有判别性和鲁棒性的局部三值模式的相邻共生矩阵(discriminant and robust co-occurrence of adjacent local ternary patterns,DRCoALTP)方法,用于获取图像纹理。计算文档图像的相邻稀疏局部三值模式(adjacent sparse local ternary patterns,ASLTP),将采样点数量设定为8,以便获得详细的局部纹理,设计出一种基于自适应中值滤波思想的半自适应阈值方法,用于提取灰度图像中心像素周边对角邻域像素的编码值。ASLTP在邻域像素位置存放稀疏局部三值模式(local ternary patterns,LTP)的值,提取灰度共生矩阵(gray-level co-occurrence matrix,GLCM),从4个方向统计使用ASLTP后灰度图像像素之间的频率关系。该算法在阿拉伯文、俄文、简体中文、哈萨克文、藏文、蒙古文、土耳其文、维吾尔文、英文、吉尔吉斯斯坦文和塔吉克斯坦文11个文种的自建印刷体文档图像数据集中验证。试验结果表明,相较于基线和先进的纹理方法,改进后的方法更具判别性,平均识别准确率为99.14%。为改善CoALTP方法可能产生低效分类特征的问题,提出半自适应阈值方法,有效提高识别率并抑制噪声。此外,针对算法产生的高维特征,采用基于均方差的特征选择方法,通过支持向量机(support vector machine,SVM)分类器特征选择后,识别速度提高284%,对11个文种的平均识别准确率达99.44%。
文摘心脏分割算法提供精准把握心脏结构的信息,辅助医生进行诊断、制定治疗计划以及进行手术前的评估工作,提高临床治疗的效果并减轻并发症。然而,心脏分割在应用中存在诸多问题。手动分割方法不仅耗时费力,并且具有很强的主观意识。全监督的心脏分割方法虽已取得一定成果,但标注数据的依赖性过高。现有的半监督分割方法在处理复杂的心脏结构和病理变化时表现仍不够理想,难以在实际临床环境中稳定应用。为解决这一问题,提出了心脏磁共振成像(MRI)分割方法,结合Linformer and Performer merge V-Net(LPV-Net)和3D Enhanced Discriminator with Attention(3D-EDA)技术,实现了全局-局部信息的有效整合。LPV-Net模块由LinPerBlock和改进的V-Net联袂打造,旨在规范模型训练过程、实现全局与局部信息的有机整合,有效提高分割效果的准确性与鲁棒性。同时引入新鉴别器3D-EDA规范未标记数据,并加入关键模块CARE-Layer,集成自定义注意力模块以增强对特征重要信息的捕捉能力,辅助网络可提高主网络分割指标性能。在左心房数据集上进行综合实验,并将所提方法与MC-Net,V-Net等其他先进的半监督方法进行比较,发现该方法在基准数据集上的表现尤为优异。特别是在使用有限标签数据进行训练时,该方法仍然展示出卓越的性能;当仅使用10%和20%的标记数据进行训练时,该方法的Dice系数分别达到88.50%和90.39%。
文摘针对有标记故障样本不足和故障特征集维数过高的问题,提出基于正交半监督局部Fisher判别分析(Orthogonal semi-supervised local Fisher discriminant analysis,OSELF)的故障诊断方法。所提出的OSELF能够充分地利用蕴含于无标记故障样本中的故障信息,避免了因有标记故障样本不足引起的过学习问题,同时采用正交迭代方式求解最优正交映射矩阵,克服现有方法无法得到正交映射矩阵的不足。正交映射矩阵的基矢量统计不相关,可有效地提高所得低维特征矢量的可辨识性。通过正交映射矩阵对故障样本集和新增样本进行维数约简,并将维数约简的结果输入粗糙优化k最近邻分类器(Coarse to fine k nearest neighbor classifier,CFKNNC)进行学习训练和故障识别。所提方法集成了OSELF在维数约简和CFKNNC在模式识别的优势,有效地提高了故障诊断的精度。通过齿轮箱故障模拟试验验证了该方法的有效性。
