中国科学院机构知识库网格系统: 检索

A novel methodology for series arc fault detection by temporal domain visualization and convolutional neural network 期刊论文 OAI收割
SENSORS, 2020, 卷号: 20, 期号: 1, 页码: 1-13
作者: Yang K(杨凯); Chu, Ruobo; Zhang RC(张认成); Xiao JC(肖金超); Tu R(涂然)

|

收藏 | 浏览/下载：20/0 | 提交时间：2020/01/18

series arc fault convolutional neural network temporal domain visualization gray image

Multi-source Remote Sensing Image Registration Based on Contourlet Transform and Multiple Feature Fusion 期刊论文 OAI收割
International Journal of Automation and Computing, 2019, 卷号: 16, 期号: 5, 页码: 575-588
作者: Huan Liu; Gen-Fu Xiao; Yun-Lan Tan; Chun-Juan Ouyang

|

收藏 | 浏览/下载：7/0 | 提交时间：2021/02/22

Feature fusion multi-scale circle Gaussian combined invariant moment multi-direction gray level co-occurrence matrix multi-source remote sensing image registration contourlet transform.

An algorithm of non-continuous gray-scale histogram enhancement based on the visual characteristics 会议论文 OAI收割
作者: Li Y; Li Z; Tang XY

|

收藏 | 浏览/下载：27/0 | 提交时间：2018/11/20

Non-continuous gray-scale histogram Visual characteristics curve Central segment histogram enhancement Gray-scale compression Image enhancement Infrared

A porosity calculation method based on CT images and its application 期刊论文 OAI收割
JOURNAL OF HYDRAULIC ENGINEERING, 2015, 卷号: 46, 期号: 46, 页码: 357-365
作者: Wang Y(王宇); Wang; Yu; Que JM(阙介民); Li

收藏 | 浏览/下载：61/0 | 提交时间：2016/04/18

Conventional methods CT Image Deformation and failures Gray-level Porosity calculations Segmentation methods Threshold segmentation X-ray computed tomography

Centroid localization algorithm based on bicubic interpolation gray square weighted (EI CONFERENCE) 会议论文 OAI收割
2012 3rd International Conference on Advances in Materials and Manufacturing Processes, ICAMMP 2012, December 22, 2012 - December 23, 2012, Beihai, China
作者: Zhou J.

收藏 | 浏览/下载：152/0 | 提交时间：2013/03/25

The 3D coordinates of measured point is embodied in 2D image coordinate of the optical characteristic point via the visual measurement system. Based on the gray square weighted centroid localization algorithm the paper presents bicubic interpolation gray square weighted centroid localization algorithm increases the number of effective pixels around the optical characteristic point imaging center and reduces noise error via the gray square weighted improves the imaging center location accuracy of optical characteristic point realizes the accurate location of the optical characteristic points. Results indicate application of the proposed algorithm to location the standard tolerance along the direction of x is 0.0022 Pixel the standard tolerance along the direction of y is 0.0023 Pixel compared with the others the standard tolerance is minimum and discrete to a lesser degree distancing ideal image point that is the proposed algorithm has higher location accuracy. The maximum tolerance along the direction of x is 0.008 Pixel the one along the direction of y is 0.007 Pixel compared with the other two algorithms the maximum tolerance is minimum.Results indicate that the stability of the proposed algorithm is better. (2013) Trans Tech Publications Switzerland.

基于灰度共生矩阵的彩色遥感图像纹理特征提取 期刊论文 OAI收割
国土资源遥感, 2013, 卷号: 25, 期号: 04, 页码: 26-32
侯群群; 王飞; 严丽

收藏 | 浏览/下载：76/0 | 提交时间：2014/10/21

彩色图像 color image 图像检索和分类 image retrieval and image classification 纹理 texture 灰度共生矩阵(GLCM) gray level co － occurrence matrix ( GLCM) 特征值

A line mapping based automatic registration algorithm of infrared and visible images 会议论文 OAI收割
5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013
作者: Ai R(艾锐); Shi ZL(史泽林); Xu DJ(徐德江); Zhang CS(张程硕)

收藏 | 浏览/下载：36/0 | 提交时间：2013/12/26

There exist complex gray mapping relationships among infrared and visible images because of the different imaging mechanisms. The difficulty of infrared and visible image registration is to find a reasonable similarity definition. In this paper, we develop a novel image similarity called implicit linesegment similarity(ILS) and a registration algorithm of infrared and visible images based on ILS. Essentially, the algorithm achieves image registration by aligning the corresponding line segment features in two images. First, we extract line segment features and record their coordinate positions in one of the images, and map these line segments into the second image based on the geometric transformation model. Then we iteratively maximize the degree of similarity between the line segment features and correspondence regions in the second image to obtain the model parameters. The advantage of doing this is no need directly measuring the gray similarity between the two images. We adopt a multi-resolution analysis method to calculate the model parameters from coarse to fine on Gaussian scale space. The geometric transformation parameters are finally obtained by the improved Powell algorithm. Comparative experiments demonstrate that the proposed algorithm can effectively achieve the automatic registration for infrared and visible images, and under considerable accuracy it makes a more significant improvement on computational efficiency and anti-noise ability than previously proposed algorithms.

A Local Image Enhancement Method Based on Adjacent Pixel Gray Order-preserving Principle 会议论文 OAI收割
5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013
作者: Fan XP(范晓鹏); Cai TF(蔡铁峰); Zhu F(朱枫)

收藏 | 浏览/下载：41/0 | 提交时间：2013/12/26

The paper is committed in local image enhancement. At first, the authors propose an adjacent pixel gray order-preserving principle. Adjacent pixel gray order-preserving principle is the basement of local enhancement method which ensures that there is no distortion in processed image. And then, the authors propose an iterative algorithm, which could stretch gray-scale difference of adjacent pixels in premise of not changing gray magnitude relationship between adjacent pixels. At last, the authors propose a totally reference image quality assessment method based on adjacent pixel gray order-preserving principle. According to this quality assessment method, the authors made a set of comparative experiments with local histogram equalization and method. Experimental results show that the proposed enhancement method can get higher score and provide better visual effects, fully demonstrating its effectiveness. According to this quality assessment method, the proposed method shows a good effectiveness, through experimental results and comparison with local histogram equalization method.

The application of adaptive enhancement algorithm based on gray entropy in mammary gland CR image (EI CONFERENCE) 会议论文 OAI收割
2012 2nd International Conference on Consumer Electronics, Communications and Networks, CECNet 2012, April 21, 2012 - April 23, 2012, Three Gorges, China
Zhang M.-H.; Zhang Y.-Y.

收藏 | 浏览/下载：34/0 | 提交时间：2013/03/25

Mammary gland is composed entirely of soft tissue with approximate density therefore mammary gland CR medicine radiation image presents a low contrast and slight difference changes may be a manifestation of tumor so it is necessary to enhance mammary gland CR image to improve its visual quality in order to meet the demands of doctor's clinical diagnosis. However the general enhancement algorithms over enhance the contrast and noise due to image details lost aiming at the defects a mammary gland CR medicine image adaptive enhancement arithmetic based on image gray entropy is put forward. The arithmetic adapts dizzy image to magnify selected spatial frequency response in order to enhance the edge details of mammary gland CR images. It can adjust weighted factor K according to image gray characteristics namely pixel gray entropy. Experiments results demonstrate that mammary gland CR image enhanced by the algorithm has abundant details and high signal-to-noise ratio moreover CR image enhanced has good visual effect. So the method is effective and fit for enhancing CR medical radiation image edge details. 2012 IEEE.

The research of digltal CR medicine image adapitive enhancement method (EI CONFERENCE) 会议论文 OAI收割
4th International Conference on Mechanical and Electrical Technology, ICMET 2012, July 24, 2012 - July 26, 2012, Kuala Lumpur, Malaysia
Ming-Hui Z.; Yao-Yu Z.

收藏 | 浏览/下载：66/0 | 提交时间：2013/03/25

Digital CR medicine radiation image is in doctor's favor and has became medicine imaging technology new hot spot because of its high gray contrast powerful computer disposal function little radiation dosage non-film diagnosis different area consultation. But degradation of digital X-ray medical image such as low contrast and blurring during radiographic imaging caused by complexity of body tissue and effects of X-ray scattering and electrical noise etc. can worsen the results of analysis and diagnosis. So it is usually needed that CR medicine image is enhanced to improve its vision quality and easy to doctor's more accurate diagnosis. The general enhancement algorithms over enhancing the contrast and lose image details aiming at the defects an enhancement algorithm for CR image is proposed based on the ratio of deviation to mean of domain. The arithmetic enhance CR image edge details by adjusting factor K based on the ratio of deviation to mean of domain of CR image. Experiment results demonstrate that the algorithm enhances CR image detail and CR image enhanced has good visual effect the adaptive enhancement method is fit for CR medicine image. (2012) Trans Tech Publications Switzerland.