期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
基于图像增强技术的水利工程隐患识别 被引量:2
1
作者 徐志立 《计算机仿真》 CSCD 北大核心 2012年第2期263-265,327,共4页
研究水利工程隐患准确检测问题,提高监测的准确性受到监测手段限制,而传统水力工程隐患检测是通过雷达成像获取隐患区域图像与正常区域图像的像素特征差异转化后的特征差异信号进行检测,当隐患区域与正常区域差异不明显的时候,转化后的... 研究水利工程隐患准确检测问题,提高监测的准确性受到监测手段限制,而传统水力工程隐患检测是通过雷达成像获取隐患区域图像与正常区域图像的像素特征差异转化后的特征差异信号进行检测,当隐患区域与正常区域差异不明显的时候,转化后的特征差异信号很弱,会发生漏检测,造成检测的准确性不高。为了解决上述问题,提出根据像素差异补偿的水利工程安全隐患检测算法,通过增加隐患区域与正常区域的像素差异的强度,补偿由于外界环境因素造成的像素差异过小的弊端,增强转化后的像素差异信号强度,进而增加检测的准确性。实验表明,改进方法能够很好地补偿像素差异信号的衰减,准确检测水利工程中的安全隐患。 展开更多
关键词 水利工程隐患 像素差异 像素增强
下载PDF
基于图像增强技术的水利工程隐患识别
2
作者 王浩 王磊 付德奎 《中国水运(下半月)》 2014年第5期214-215,共2页
水利工程中的安全隐患检测是一项难题,传统的检测方法主要借助探地雷达进行影像识别,然而传统方法受到影像采集条件的影响会有一定的局限性。文中通过补偿隐患区域影像像素差异,使得转化后的差异信号强度增强,从而提高了隐患识别的准确... 水利工程中的安全隐患检测是一项难题,传统的检测方法主要借助探地雷达进行影像识别,然而传统方法受到影像采集条件的影响会有一定的局限性。文中通过补偿隐患区域影像像素差异,使得转化后的差异信号强度增强,从而提高了隐患识别的准确性,具有重要的生产实际意义。 展开更多
关键词 水利工程 隐患识别 像素增强
下载PDF
基于全连接神经网络和边缘感知视差传播的立体匹配算法研究 被引量:3
3
作者 严邓涛 霍智勇 +1 位作者 戴伟达 陈钊 《南京邮电大学学报(自然科学版)》 北大核心 2018年第3期83-88,共6页
提出一种基于全连接神经网络和边缘感知视差传播(Edge-aware Disparity Propagation,EDP)的立体匹配算法。首先通过全连接网络获得初始的匹配代价,并利用胜者为王(Winner Takes All,WTA)算法生成初始视差图;然后进行一致性检测,对不一... 提出一种基于全连接神经网络和边缘感知视差传播(Edge-aware Disparity Propagation,EDP)的立体匹配算法。首先通过全连接网络获得初始的匹配代价,并利用胜者为王(Winner Takes All,WTA)算法生成初始视差图;然后进行一致性检测,对不一致视差点采用EDP和测地距滤波算法计算得到新的匹配代价和视差值,并填充初始视差图;最后,对填充后的视差图进行亚像素增强优化。实验数值表明,该算法能有效降低立体匹配的误匹配率,提高视差图精度,特别是在非闭塞区域有较低的误匹配率。 展开更多
关键词 立体匹配 全连接神经网络 视差传播 测地距滤波 边缘感知 像素增强
下载PDF
Multivariate Analysis of Recurrence in Meningioma
4
作者 吴涛 吴志敏 +1 位作者 袁先厚 陈卫国 《The Chinese-German Journal of Clinical Oncology》 CAS 2005年第1期26-29,66,共5页
Objective: To evaluate the clinical and radiological factors that affect therecurrence of the meningioma patient so as to effectively prevent and cure recurrence of meningiomapatients more earlier. Methods: The clinic... Objective: To evaluate the clinical and radiological factors that affect therecurrence of the meningioma patient so as to effectively prevent and cure recurrence of meningiomapatients more earlier. Methods: The clinical features and radiological aspects in 145 cases ofmeningiomas undergoing operation during 1993-1997 were retrospectively studied. The data of only 83cases of all 145 cases were available. The factors were evaluated with univariate and multivariateanalysis. Results: With univariate analysis, 7 factors showed highly significance to recurrence ofmeningiomas: tumor size, tumor location, tumor shape, edema, extent of resection, pathologicalgrade, CT enhancement. With multivariate analysis, 4 factors showed significant danger to recurrenceof meningiomas: pathological grade, extent of resection, tumor shape and CT enhancement.Conclusion: The main factors that affect the recurrence of meningioma patients are pathologicalgrade, extent of resection, tumor shape and CT enhancement. 展开更多
关键词 MENINGIOMA clinical factors radiological features RECURRENCE
下载PDF
Distance Transform Based Enhancement for Linear Interpolated Images
5
作者 唐莉萍 曾培峰 《Journal of Donghua University(English Edition)》 EI CAS 2003年第1期43-48,共6页
An approach of distane map based imageenhancement (DMIE) is proposed. It is applied toconventional interpolations to get sharp images. Edgedetection is performed after images are interpolatedby linear interpolations. ... An approach of distane map based imageenhancement (DMIE) is proposed. It is applied toconventional interpolations to get sharp images. Edgedetection is performed after images are interpolatedby linear interpolations. To meet the two conditionsset for DMIE, i. e., no abrupt changes and no over-boosting, different boosting rate should be used inadjusting pixel intensities. When the boosting rate isdetermined by using the distance from enhancedpixels to nearest edges, edge-oriented imageenhancement is obtained. By using Erosion technique,the range for pixel intensity adiustment is set.Over-enhancement is avoided by limiting the pixel iutensities in enhancement within the range. A unifled linear-time algoritiml for disance transform is adopted to deal with the calculation of Euelidean distance of the images.Its computation complexity is 0(N).After the preparation,i.e.,distance transforming and erosion,the images get more and more sharpened while no over.boosting.Occurs by repeating the enhancement procedure ,The simplicity of the enhancement operation makes DMIE suitable for enhancement rate adjusting 展开更多
关键词 INTERPOLATION edge detection Euclidean distance transform B-spline。image enhancement
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部