基于Backes Andre Ricardo等人提出的“构造伴生动态演化网络”、生成“高维解释向量”的纹理图片分类法,研究了Kylberg纹理图像库的分类问题。通过将数据集图片样本进行二次分割以减少该算法预处理计算量、提出了构建纹理网络时的“网...基于Backes Andre Ricardo等人提出的“构造伴生动态演化网络”、生成“高维解释向量”的纹理图片分类法,研究了Kylberg纹理图像库的分类问题。通过将数据集图片样本进行二次分割以减少该算法预处理计算量、提出了构建纹理网络时的“网络顶点随机化、抽样采集”策略,该思路可进一步减少算法的时间开销。该类纹理图片数据高维几何数字特征的提取流程易于实现,扩展了原算法的适用范围。数值结果表明算法对旋转操作、噪声干扰具有一定的鲁棒性,具备一定潜在应用前景。展开更多
Three kinds of aggregates were polished by genuine pneumatic rubber tyres.The initial states of surface texture and dynamic friction coefficient were measured and their developments in polishing process were monitored...Three kinds of aggregates were polished by genuine pneumatic rubber tyres.The initial states of surface texture and dynamic friction coefficient were measured and their developments in polishing process were monitored.The characterizations of height distribution and power spectral density of aggregate surface texture were estimated.The changes of micro-texture were also investigated based on a fractal filtering method with sound theoretical backgrounds of rubber friction on rough surfaces.Global height reduction and differential removal of mineral component are observed in polishing process.It is concluded that the tyre-polishing action plays the critical roles in the micro-scale texture,and the evolution of friction of aggregate is governed by the micro-texture changes due to the differential removal of mineral component.展开更多
Co-occurrence matrices have been successfully applied in texture classification and segmentation.However,they have poor computation performance in real-time application.In this paper,the efficient co-occurrence matrix...Co-occurrence matrices have been successfully applied in texture classification and segmentation.However,they have poor computation performance in real-time application.In this paper,the efficient co-occurrence matrix solution for defect detection is focused on,and a method of Fuzzy Label Co-occurrence Matrix (FLCM) set is proposed.In this method,all gray levels are supposed to subject to some fuzzy sets called fuzzy tonal sets and three defective features are defined.Features of FLCM set with various parameters are combined for the final judgment.Unlike many methods,image acquired for learning hasn't to be entirely free of defects.It is shown that the method produces high accuracy and can be a competent candidate for plain colour fabric defect detection.展开更多
In order to solve the problem of complicated fabric texture interference on the pilling segmentation during the objective evaluation of fabric pilling, a new method of pilling image acquisition was proposed. Firstly, ...In order to solve the problem of complicated fabric texture interference on the pilling segmentation during the objective evaluation of fabric pilling, a new method of pilling image acquisition was proposed. Firstly, multi-direction lights were projected on the pilled fabric surface and its pilling images were captured, which mixed with invariant fabric background texture and pilling profile information modulated by the variant light projections. The captured fabric pilling images were analyzed by independent component analysis method. Using the spectrum feature analysis method, the independent components belonging to the complicated fabric background texture were separated and the pilling images are reconstructed with the left components. The experimental results showed that this method can effectively separate the pilling image from complicated fabric texture, which provides one possibility for colored fabric pilling objective evaluation.展开更多
文摘基于Backes Andre Ricardo等人提出的“构造伴生动态演化网络”、生成“高维解释向量”的纹理图片分类法,研究了Kylberg纹理图像库的分类问题。通过将数据集图片样本进行二次分割以减少该算法预处理计算量、提出了构建纹理网络时的“网络顶点随机化、抽样采集”策略,该思路可进一步减少算法的时间开销。该类纹理图片数据高维几何数字特征的提取流程易于实现,扩展了原算法的适用范围。数值结果表明算法对旋转操作、噪声干扰具有一定的鲁棒性,具备一定潜在应用前景。
基金Project(50809053) supported by the National Natural Science Foundation of ChinaProject(FE 04.208/2007/CRB) funded by Federal Highway Research Institute (Bast),Germany
文摘Three kinds of aggregates were polished by genuine pneumatic rubber tyres.The initial states of surface texture and dynamic friction coefficient were measured and their developments in polishing process were monitored.The characterizations of height distribution and power spectral density of aggregate surface texture were estimated.The changes of micro-texture were also investigated based on a fractal filtering method with sound theoretical backgrounds of rubber friction on rough surfaces.Global height reduction and differential removal of mineral component are observed in polishing process.It is concluded that the tyre-polishing action plays the critical roles in the micro-scale texture,and the evolution of friction of aggregate is governed by the micro-texture changes due to the differential removal of mineral component.
基金Open Fund of the Key Lab of the Ministry of Education for Image Information Processing and Intelligent Control,China(No.200702)
文摘Co-occurrence matrices have been successfully applied in texture classification and segmentation.However,they have poor computation performance in real-time application.In this paper,the efficient co-occurrence matrix solution for defect detection is focused on,and a method of Fuzzy Label Co-occurrence Matrix (FLCM) set is proposed.In this method,all gray levels are supposed to subject to some fuzzy sets called fuzzy tonal sets and three defective features are defined.Features of FLCM set with various parameters are combined for the final judgment.Unlike many methods,image acquired for learning hasn't to be entirely free of defects.It is shown that the method produces high accuracy and can be a competent candidate for plain colour fabric defect detection.
文摘In order to solve the problem of complicated fabric texture interference on the pilling segmentation during the objective evaluation of fabric pilling, a new method of pilling image acquisition was proposed. Firstly, multi-direction lights were projected on the pilled fabric surface and its pilling images were captured, which mixed with invariant fabric background texture and pilling profile information modulated by the variant light projections. The captured fabric pilling images were analyzed by independent component analysis method. Using the spectrum feature analysis method, the independent components belonging to the complicated fabric background texture were separated and the pilling images are reconstructed with the left components. The experimental results showed that this method can effectively separate the pilling image from complicated fabric texture, which provides one possibility for colored fabric pilling objective evaluation.
