中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共5条，第1-5条

帮助

条数/页：排序方式：
	Characteristic point match algorithm based on the SURF in binocular stereo vision (EI CONFERENCE) 会议论文 OAI收割 5th International Conference on Intelligent Networks and Intelligent Systems, ICINIS 2012, November 1, 2012 - November 3, 2012, Tianjin, China 作者: Wang L.; Wang L.; Wang L.; Yang L.; Yang L. 收藏 \| 浏览/下载：30/0 \| 提交时间：2013/03/25 One of the main components of the computer vision is 3D reconstruction. Extracts and the match based on two-dimensional picture characteristic point is the 3D reconstruction technology core. Taking binocular stereoscopic vision theory as a foundation through extracts the characteristics of SURF based on the multi-scale analysis this feature has specific scale reproducibility put the epipolar constraints and disparity constraints as conditions judgement to specific screening it is greatly reduced the search range. The experiment use the matching method for three different actual scenes the results shows that the method can enhance the image matching speed and precision and can get more precise dense parallax used for reconstruction complete scene. 2012 IEEE.
	Image compression based on contourlet and no lists SPIHT (EI CONFERENCE) 会议论文 OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China 作者: Zhang S. 收藏 \| 浏览/下载：52/0 \| 提交时间：2013/03/25 The volume of raw image data captured by the high resolution camera is extremely huge. Thus the efficient image compression method should be used to decrease the bit rate. The image compression method based on wavelet is used more widely nowadays. However two dimensional wavelet is only the tensor product of the one dimensional wavelet whose support region of basis function is extended from interval to square. Contourlet is an image multiscale geometric analysis tool which could represent image sparsely and has strong capability of nonlinear approximation. The basis function of contourlet is multidirectional and anisotropic. Nevertheless contourlet is redundant. So the non-redundant Wavelet Based Contourlet Transform (WBCT) is used in this paper. The SPIHT algorithm is very efficient way to coding the significant coefficients. And the improved no lists SPIHT is more easy to implemented by hardware. Image compression method based on the combination of both wavelet based contourlet transform and no lists SPIHT coding is proposed in the paper. Experiment shows that compared to wavelet based scheme the contourlet scheme can reserve the texture of the image. For barbara test image when coding at low bit rate the PSNR can improve about 0.2dB. 2010 IEEE.
	Study on color difference estimation method of medicine biochemical analysis (EI CONFERENCE) 会议论文 OAI收割 ICO20: Illumination, Radiation, and Color Technologies, August 21, 2005 - August 26, 2005, Changchun, China 作者: Zhou Y.; Zhou F.; Wang C. 收藏 \| 浏览/下载：42/0 \| 提交时间：2013/03/25 The biochemical analysis in medicine is an important inspection and diagnosis method in hospital clinic. The biochemical analysis of urine is one important item. The Urine test paper shows corresponding color with different detection project or different illness degree. The color difference between the standard threshold and the test paper color of urine can be used to judge the illness degree therefore it can be used in hospital so that further analysis and diagnosis to urine is gotten. The color is a three-dimensional physical variable concerning psychology the estimation method of color difference in urine test can have better precision and facility than the conventional test method with one-dimensional reflectance calibrating organization and family while reflectance is one-dimensional variable it can make an accurate diagnose. The digital camera is easy to take an image of urine test paper and is used to carry out the urine biochemical analysis conveniently. On the experiment so its application prospect is extensive. the color image of urine test paper is taken by popular color digital camera and saved in the computer which installs a simple color space conversion (RGB &rarr XYZ &rarr Lab*) and the calculation software. Test sample is graded according to intelligent detection of quantitative color. The images taken every time were saved in computer and the whole illness process will be monitored. This method can also use in other medicine biochemical analyses that have relation with color. Experiment result shows that this test method is quick and accurate
	A new high-precision measurement system used in the image calibration of large-sized photographic instrument (EI CONFERENCE) 会议论文 OAI收割 Optical Design and Testing II, November 8, 2004 - November 11, 2004, Beijing, United states 作者: Li Y.; Liu Z.; Li Y.; Li Y.; Li Y. 收藏 \| 浏览/下载：23/0 \| 提交时间：2013/03/25 The purpose of characterizing the image of large-sized photographic instrument is to make the directionality of three coordinate axises in the three-dimensional coordinate of the image and the directionality of three axises of coordinate in the frame of axes of the instrument keep the same direction. This problem was solved by a high-precision measurement system composed of double-theodolite and a set of communication system. Two cube prisms will be respectively placed on the image surface and the instrument. Every cube prism will stand for a three-dimensional coordinate from the image surface or the instrument. As a result the interdependence of both coordinates from the image surface and the instrument can be obtained by measuring the interdependence of the both cube prisms with autocollimation survey axiom. In the survey system two high-precision stations TDA5005 from Leica Company will be selected as double-theodolite and the interdependence of both coordinates can be achieved by moving the station only at one time. Therefore this measurement system is a high efficient and high-precision surveying method to the image calibration of the large-sized photographic instrument. Based on the experiment its measuring accuracy can reach arc-second level.
	The united adaptive learning algorithm for the link weights and shape parameter in RBFN for pattern recognition 期刊论文 OAI收割 INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 1997, 卷号: 11, 期号: 6, 页码: 873-888 作者: Huang, DS \| 收藏 \| 浏览/下载：30/0 \| 提交时间：2018/10/10 Neural Networks Recognition Radial Basis Function Network Gaussian Kernel Function Shape Parameter Forgotten Factor Recursive Least Squares Adaptive Gradient Descending One-dimensional Image