共查询到20条相似文献,搜索用时 109 毫秒
1.
2.
《制造技术与机床》2021,(10)
不同磨损状况的刀具在工件表面切削后形成的纹理特征也各不相同,工件表面纹理蕴含着大量表征刀具状况的信息。为有效、高效地提取反映刀具状况的工件表面纹理特征,提出1种结合旋转不变均匀算子的局部二值模式(rotation-invariant uniform local binary pattern, RULBP)与灰度共生矩阵(gray-level co-occurrence matrix, GLCM)的纹理特征提取方法。该方法利用RULBP与GLCM的计算原理分别提取工件表面纹理的微结构特征和宏结构特征,达到全面提取纹理"微宏观"特征的目的。实验结果表明,同常用的工件表面纹理特征提取方法相比,所提方法能显著提高纹理特征的表征度。 相似文献
3.
冠状动脉中易损斑块的破裂是导致心血管疾病死亡的重要原因。掌握易损斑块形态特性、组成成分(主要是脂质)与空间分布信息,有利实现易损斑块的早期预测和干预治疗,则可以极大降低心血管病带来的危害。介绍了一种基于LabVIEW实现数据采集功能的血管内光声成像系统,并利用其实现对血管斑块脂质的成像与定量分析。实验结果表明,血管内光声成像技术应用于临床血管内介入具有巨大潜力。 相似文献
4.
5.
通过对灰度共生矩阵的介绍,提出一种基于灰度共生矩阵提取纹理图像特征.对纹理学原理与其主要研究方法进行了分析,然后结合车削工件表面图像特征,研究了纹理学特征分析的经典方法--灰度共生矩阵法,并结合车削工件表面图像,分析了车削工件表面纹理在归一化灰度共生矩阵中所表现出的特点. 相似文献
6.
7.
本文提出了一种基于Gabor滤波器的水面尾迹纹理的自动提取算法.该方法分为两步第一步,选取等大小的含尾迹纹理的水面子图像和不含尾迹纹理的水面子图像,通过一组GaBOR滤波器得到它们的特征图像,计算每个子图像特征图的均值和方差,将它们作为神经网络的训练样本对BP网络进行训练得到用于识别的网络;第二步,将待提取的整幅图像分成很多与第一步中子图像等大小的子图像,分别计算它们的Gabor特征图像,并得到它们的均值和方差,把它们作为神经网络的输入,得到它们是否是纹理区域,由整幅子图像的识别结果得到一幅二值图像,用Hough变换检测图像中的直线,根据直线的长度是否有尾迹存在.大量的实验结果表明该方法能够准确地提取尾迹纹理. 相似文献
8.
基于Gabor小波的浮选泡沫图像纹理特征提取 总被引:4,自引:1,他引:3
矿物浮选泡沫表面纹理是浮选工艺指标高低的重要指示器,为了获取泡沫图像纹理的细微差别进而对浮选生产状态进行机器识别,提出一种基于Gabor滤波的泡沫图像纹理特征提取方法。首先利用Gabor小波提取了泡沫图像多尺度与多方向上的泡沫纹理幅度谱(GMTR)与相位谱(GPTR);然后根据GMTR与GPTR的分布特征,通过估计GMTR的Gamma分布参数和计算GPTR的熵作为泡沫纹理特征参量;最后,利用所提取的泡沫纹理特征对浮选工业生产状态进行无监督的模糊聚类分析与有监督的生产状态识别。实验结果表明,该纹理特征提取方法能有效地获取各种浮选状态下泡沫表面纹理的细微差别,基于该纹理特征参量的浮选状态识别准确率高于90%。 相似文献
9.
10.
11.
A component‐by‐component characterisation of high‐risk atherosclerotic plaques by multiphoton microscopic imaging
下载免费PDF全文
![点击此处可从《Journal of microscopy》网站下载免费的PDF全文](/ch/ext_images/free.gif)
M. JAIN B. WU D. PISAPIA S. SALVATORE S. MUKHERJEE N. NARULA 《Journal of microscopy》2017,268(1):39-44
Aims: Atherosclerotic plaques vulnerable to rupture are almost always inflamed, and carry a large lipid core covered by a thin fibrous cap. The other components may include neovascularisation, intraplaque haemorrhage and spotty calcification. In contrast, stable plaques are characterised by a predominance of smooth muscle cells and collagen, and lipid core is usually deep seated or absent. This study is a proof of principle experiment to evaluate the feasibility of multiphoton microscopy (MPM) to identify aforementioned plaque components. Methods and Results: MPM is a nonlinear optical technique that allows imaging based on intrinsic tissue signals including autofluorescence and higher‐order scattering. In our study, MPM imaging was performed on morphologically diverse aortic and coronary artery plaques obtained during autopsy. Various histologically verified plaque components including macrophages, cholesterol crystals, haemorrhage, collagen and calcification were recognised by MPM. Conclusions: Recognition of the distinct signatures of various plaque components suggests that MPM has the potential to offer next‐generation characterisation of atherosclerotic plaques. The higher lateral resolution (comparable to histology) images generated by MPM for identifying plaque components might complement larger field of view and greater imaging depth currently available with optical coherence tomography imaging. As the next step MPM would need to be evaluated for intact vessel imaging ex vivo and in vivo. 相似文献
12.
13.
14.
Recognition and localization of mechanical parts using machine vision is a common approach in precision assembly systems. However, positional inaccuracy in assembly systems often produces unfocused images. Hence, existing methods of part recognition and localization are vulnerable to failure. In this paper, we present a part recognition and localization method, based on relative entropy, which can be applied to small samples. First, a template image is generated based on the contour of the parts and divided into several regions. The intensity distribution of the regions was sampled to generate template features. Then, the captured image is segmented using the Gaussian mixture model and the expectation maximum algorithm to extract the target part in the image. Part features are also generated by sampling the target part image using the template features. Furthermore, an optimization model is established in which the objective function is the sum of the relative entropy between the image features, the template features, and the region matching error correction term. By solving the optimization model, the location of the part can be obtained. The proposed method is compared with the edge and invariant feature-based methods through experiments. The results show that the proposed method has higher robustness and is suitable for the recognition and localization of parts with unfocused images. By using this method, the flexibility and reliability of precision assembly systems can be improved. 相似文献
15.
基于活动轮廓模型和Contourlet多分辨率分析分割血管内超声图像 总被引:4,自引:5,他引:4
血管内超声斑块图像的分割对动脉粥样硬化疾病的诊断有重要价值。针对传统分割方法初始化和鲁棒性两个问题,提出一种基于活动轮廓模型和Contourlet多分辨率分析分割血管内超声斑块图像的新方法。该方法运用Contourlet变换将原图像分解为多分辨率低通分量和多分辨率带通分量方向性子带。对低通分量进行模板匹配,确定血管内腔边界和中外膜边界的初始轮廓;对带通分量方向性子带进行扩散滤波,抑制噪声的同时尽可能保留有用边缘,并结合边界矢量场使轮廓演化得到最终分割结果,从而提高了分割算法的鲁棒性。对100幅仿真图像和120幅实际图像的分割结果表明,该方法能自动、精确地提取血管的两条边界。相对于传统活动轮廓模型法,该方法分割实际图像的平均距离误差提高了3.04像素,面积差异百分比提高了6.30%。 相似文献
16.
针对磨粒的识别问题,利用数字磨粒图像分析方法,结合D-S证据理论和BP神经网络,建立了基于D-S证据理论的集成神经网络磨粒融合诊断方法。首先对磨粒图像进行处理,并利用统计分析方法和傅立叶分析方法对处理好的磨粒图片进行分析得到磨粒特征;然后基于统计分析方法和傅立叶分析方法建立对应的两个BP分类子神经网络,利用典型的磨粒样本对BP子神经网络进行训练,得到初步的诊断结果;最后用D-S法对子神经网络诊断结果进行融合,得到最终的诊断结果。算例分析结果表明,基于D-S证据法和集成神经网络的磨粒融合诊断方法比单个诊断方法具有更高的准确性。 相似文献
17.
18.
19.
通过对轧制自动厚度控制系统(automated gauge control,简称AGC)伺服缸分别模拟3个阶段的保载和振动加载下所收集到的声发射信号,依托前期研究,探索基于状态热图的AGC伺服缸早期振动的辨识方法。通过在迁安沪久660mm轧机的AGC伺服缸上模拟保载和早期振动状态,采集声发射信号,对所采集信号的累计概率分布进行分析,选取可表征伺服缸加载状态变化的声发射特征。基于对所选特征进行组合并施加一定的值域约束和逻辑运算条件,构建了AGC伺服缸保载和早期振动的声发射热图。对状态热图的分析结果显示,AGC伺服缸在同等加载状态下的振动和保载状态可较好地通过此类状态热图予以呈现,为AGC伺服缸的早期振动状态提供一种快速、便捷的可视化辨识方案。 相似文献
20.
Muhammad A. Khan Ikram U. Lali Amjad Rehman Mubashar Ishaq Muhammad Sharif Tanzila Saba Saliha Zahoor Tallha Akram 《Microscopy research and technique》2019,82(6):909-922
Brain tumor identification using magnetic resonance images (MRI) is an important research domain in the field of medical imaging. Use of computerized techniques helps the doctors for the diagnosis and treatment against brain cancer. In this article, an automated system is developed for tumor extraction and classification from MRI. It is based on marker‐based watershed segmentation and features selection. Five primary steps are involved in the proposed system including tumor contrast, tumor extraction, multimodel features extraction, features selection, and classification. A gamma contrast stretching approach is implemented to improve the contrast of a tumor. Then, segmentation is done using marker‐based watershed algorithm. Shape, texture, and point features are extracted in the next step and high ranked 70% features are only selected through chi‐square max conditional priority features approach. In the later step, selected features are fused using a serial‐based concatenation method before classifying using support vector machine. All the experiments are performed on three data sets including Harvard, BRATS 2013, and privately collected MR images data set. Simulation results clearly reveal that the proposed system outperforms existing methods with greater precision and accuracy. 相似文献