本文主要讨论了脑eit成像的计算模型和图像重构算法，并对几类典型算法进行了评价。
In this paper, the mathematical model and reconstruction algorithm of the brain EIT have been mainly discussed.
论文研究了基于图像传感器的原始数据压缩及其彩色图像重构算法以及重构后图像的后续处理算法。
This research discusses the raw data compression and color image reconstruction algorithms based on image sensor and proposes some post-processing algorithms after image reconstruction.
目前MRI重构算法只利用MRI图像稀疏性表示或只利用基于其局部光滑性的先验知识，重构效果不理想。
The current MRI reconstruction algorithms simply use either the sparse priors or the local smooth priors of MRI image, and result in the inferior reconstruction.
提出了一种基于对象的二值图像的重构算法。
In this paper, a reconstruction algorithm is presented that is based on the object of the binary image.
对比实验表明，将此算法用于图像的复原和重构可获得良好的效果，而且性能稳定。
Comparative experiments show that this algorithm converges to visually good images with excellent stability for restoration and reconstruction of images.
本文详细介绍了小波变换理论及其在图像处理方面的应用，分别提出了几何角度和灰度角度的两种不同的图像镶嵌算法，并提出两种不同的边界重构方式。
This paper introduces the theory about wavelet and the applications on image processing particularly and gives two image merging ideas and gives two different boundary reconstruction methods.
主要研究内容包括：数据采集系统设计、图像预处理、滤波方法的选择及其算法、点云生成、三维CAD模型重构。
The main content includes the design of original data collecting system, Image preprocessing, selection and algorithm of filtering method, points cloud creating, reconstruction of 3d CAD model.
目前在压缩传感重构算法中利用图像的可稀疏性表示先验知识，从比奈奎斯特采样少得多的观测值中恢复原始图像。
The current image compressed sensing algorithms can reconstruct the original image using the sparse prior of image from far fewer measurements than the Nyquist samples.
重点分析了高斯金字塔、拉普拉斯金字塔、对比度金字塔和小波金字塔在图像分解与重构中的原理及其融合算法。
The principle of image decomposition and reconstruction based on Gauss-pyramid, Laplacian-pyramid, contrast-pyramid and wavelet-pyramid is emphatically analyzed, as well as the fusion algorithm.
实验结果表明，与传统方法相比，该算法重构图像的主观质量得到了明显增强，提高了峰值信噪比。
The experimental results show that the performance of this algorithm is better than the traditional method both in vision effect and peak signal to noise ratio.
利用这种算法，对CCD相机捕获到的基元图像阵列进行重构。
By proposed algorithm, an original object was reconstructed with the elemental image array captured by a CCD camera.
重点研究了形态学重构算法在微弱目标检测和跟踪中的应用，主要体现在对原始图像的背景估计过程和检测后处理过程。
This paper researches the application of morphology reconstruction algorithm in dim point target detection and tracing, mainly in background estimation and post processing stage after detection.
实验结果表明，该算法在有效消除边缘振荡效应的同时，极大地提高了超分辨率图像重构的速度。
Experimental results show that the proposed algorithm has got a significant increase of efficiency while reducing the ringing artifacts effectively.
文章在图像配准的基础之上，采用后向投影迭代算法对图像序列进行了高分辨率重构，并给出了其中详细的算法和实现过程。
In the paper, based on the image registration, iterative back-projection technique is used to construct high resolution from image sequences, in which algorithms and realization are given in detail.
实验结果表明：该算法有较好的重构图像主观质量和较高的峰值信噪比（PSNR）。
The experiment results show the image compression scheme can improve the recovery image quality and peak signal-to-noise ratio(PSNR).
但由于目前在MAP算法中普遍采用的是平滑型图像先验模型，导致重构出来的图像边界不明锐，一些细节不清晰。
However, due to the use of smooth prior image model in MAP, the reconstructed edges and some image details are blurred.
实验结果证明在解码率比较高的情况下，本文方案的图像重构效果较嵌入式零树算法好，无损情况下的压缩比也得到了提高。
The result of experiments shows that the improved algorithm gets a better result in both the quality of recompose image and the compression ratio of lossless.
真实图像序列的重构实验验证了算法的正确性和有效性。
The experiments on real image sequences demonstrate the correctness and effectiveness of the method.
为了克服噪声对超声检测成像质量的影响，利用离散二进制小波变换的分解重构算法来降低脉冲噪声的干扰，提高超声图像的信噪比。
To overcome pulse noise influence to image quality, discrete dyadic wavelet transform (DDWT) is used to reduce the noise influence and improve signal to noise ratio (SNR).
数值实验表明该算法能够更好的匹配图像的几何特征，具有更好的可控性和图像重构效果。
Numerical results show this method is capable of matching the geometrical characteristics of images and has better steerability as well as reconstruction result.
在压缩感知框架下运用正则化正交匹配追踪(ROMP)算法进行图像重构时，迭代次数取值不合适会严重降低重构图像的质量。
The unsuitable iterative number of the Regularized Orthogonal Matching Pursuit (ROMP) algorithm in the framework of Compressive Sensing (CS) may reduce the quality of image reconstruction greatly.
本文在研究分布式视频编码的基础上，研究并改进了其解码端边信息的生成算法以改善边信息的重构质量，从而提高解码图像的PSNR值。
On the basis of studying DVC theory, an improved algorithm is proposed for the side information generating process so as to increase the PSNR at the decoder.
该算法在原有AMLE算法的基础上，保留图像水平集的边界数据，采用逐层处理方法实现图像重构。
On the basis of existing AMLE algorithm, this algorithm saves the bound data of image level sets and uses the method of processing scale by scale to reconstruct image.
在像素层上，结合红外CT模拟与超声CT算法，采用证据理论方法实现了对三维图像的融合重构；
To acquire fused 3-D images pixel level fusion is performed by the evidential theory to integrate infrared CT simulation into ultrasonic CT.
重点是二维医学图像的三维可视化系统的构成原理及技术手段、三维医学图像的重构算法的优化改进。
Focus on two-dimensional medical image visualization system theory and the composition of technical means, 3d medical image reconstruction algorithm optimization improvements.
实验结果表明本文算法在确保重构图像较高质量的前提下，各层图像都实现了较高的压缩比率，对图像的分层压缩与传输的实现具有较高的实用价值。
The experiment result shows that this approach can keep the quality of images , and compress each layer to a good ratio . So it is useful in multi-layered image compressing and transmission.
实验结果表明本文算法在确保重构图像较高质量的前提下，各层图像都实现了较高的压缩比率，对图像的分层压缩与传输的实现具有较高的实用价值。
The experiment result shows that this approach can keep the quality of images , and compress each layer to a good ratio . So it is useful in multi-layered image compressing and transmission.
应用推荐