最近邻域与无邻域算法结合空间滤波实现显微光切片

运用最近邻域与无邻域算法,并结合空间滤波方法,可去除显微切层图像的离焦模糊成份,可获得高成像速度、高质量的显微光切片。对各种显微图像进行了光切片处理,并与由现有去卷积处理、结构光照明等方法获得的光切片图像进行了对比,验证了该算法在去除模糊信息方面有更好的效果,提高了图像处理效率,获得了令人满意的光切片图像。在此基础上研制出了显微光切片图像处理系统。运用最近邻与无最近邻算法,结合空间滤波方法,采用简便可调的卷积模糊算子代替点扩散函数的估计过程,图像处理方便快捷,可较好地去除离焦平面的模糊信息。     

零件的角点提取及匹配定位

本文基于三坐标测量机(CMM)设计了一套视觉检测系统,该系统能够对零件实际空间特征信息进行比较全面地提取。针对位于CMM平台上带有角点的零件,利用Harris算子提取从CMM三个不同方位获取的零件图像的角点。对于Harris算子提取到的角点,本文提出一种八链码搜索法和SUSAN区域法相结合的伪角点剔除方法,最后基于立体视觉的原理,提出"距离空间图"匹配算法,将以上3幅图像一一建立匹配关系。实验中多次改变零件在CMM中姿态时,多次实验数据表明本文的角点提取精度与真实角点间仅存在1~2像素的偏差,零件的定位误差为1~3 mm。通过实验验证,角点匹配和定位的稳定性和精度满足要求,具有一定的抗干扰性和实用性。     

Noninvasive determination of spectral depth of light penetration into skin

A noninvasive method for determining the spectral depth of light penetration into the skin has been developed. It is based on measuring fluxes of radiation reflected from the skin in N _Λ ≥ 3 narrow or wide spectral parts and spectral analysis thereof using the regression approach to solving ill-posed inverse problems. The possibility of estimating the spectral depth of light penetration into skin by skin images in three wide spectral parts (red, green, and blue) is demonstrated. Errors of the method are estimated under conditions of general variability of structural-morphological skin parameters, and its resistance to errors of optical measurements is analyzed.     

中药黄连饮片活性成分分布的检测研究

为了实现中药饮片的活性成分空间分布检测,有效地对药用部位进行质量评价,以中药黄连饮片为研究对象,运用光谱成像分析技术进行检测.首先获取检品的荧光光谱立方体,根据中药鉴定学知识,人工提取3个不同组织结构处的光谱曲线;进而运用主成分分析法重构光谱图像,将3个不同组织结构的特征差异集中于前几个主成分图中;最后采用阈值法对第一主成分图像进行分割,获得了不同组织结构的空间分布情况及各组织结构有效成分的相对含量.实验结果显示光谱成像技术可以提供中药饮片有效成分的空间分布状态,为人药部位的选择提供依据,且检测过程无损、快速.     

具有紧支撑正交非张量积小波的图像融合

提出了基于一种新的小波——具有紧支撑、正交性、伸缩矩阵为[^2 0 ^0 2]的非张量积小波的图像融合方法。首先根据非张量积小波理论,利用Daubechies构造的单变量滤波器构造出基于四通道的不可分的小波滤波器组,用此滤波器组对参加融合的图像进行分解,然后对低频部分采用取均值、高频部分采用系数绝对值取大的融合算法对分解子图进行融合,最后重构。并采用熵、交叉熵、互信息、均方根误差和峰值信噪比等指标对该方法进行了客观评价。对可见光图像与红外图像、远红外图像与近红外图像、遥感图像、多聚焦图像和其它多类图像的融合实验结果证明本方法有较好的融合效果,其融合性能与采用同样融合算法的张量积db2小波的融合方法的融合性能相当。     

Image Defogging Framework Using Segmentation and the Dark Channel Prior

Foggy images suffer from low contrast and poor visibility problem along with little color information of the scene. It is imperative to remove fog from images as a pre-processing step in computer vision. The Dark Channel Prior (DCP) technique is a very promising defogging technique due to excellent restoring results for images containing no homogeneous region. However, having a large homogeneous region such as sky region, the restored images suffer from color distortion and block effects. Thus, to overcome the limitation of DCP method, we introduce a framework which is based on sky and non-sky region segmentation and restoring sky and non-sky parts separately. Here, isolation of the sky and non-sky part is done by using a binary mask formulated by floodfill algorithm. The foggy sky part is restored by using Contrast Limited Adaptive Histogram Equalization (CLAHE) and non-sky part by modified DCP. The restored parts are blended together for the resultant image. The proposed method is evaluated using both synthetic and real world foggy images against state of the art techniques. The experimental result shows that our proposed method provides better entropy value than other stated techniques along with have better natural visual effects while consuming much lower processing time.     

Regeneration of elemental images in integral imaging for occluded objects using a plenoptic camera

In this Letter, we propose an elemental image regeneration method of three-dimensional(3D) integral imaging for occluded objects using a plenoptic camera. In conventional occlusion removal techniques, the information of the occlusion layers may be lost. Thus, elemental images have cracked parts, so the visual quality of the reconstructed 3D image is degraded. However, these cracked parts can be interpolated from adjacent elemental images. Therefore, in this Letter, we try to improve the visual quality of reconstructed 3D images by interpolating and regenerating virtual elemental images with adjacent elemental images after removing the occlusion layers. To prove our proposed method, we carry out optical experiments and calculate performance metrics such as the mean square error(MSE) and the peak signal-to-noise ratio(PSNR).     

Human eye localization using the modified Hough transform

The precise localization of parts of a human face such as mouth, nose or eyes is important for their image understanding and recognition. The developed successful computer method of eyes and eyelids localization using the modified Hough transform is presented in this paper. The efficiency of this method was tested on two publicly available face images databases and one private face images database with the location correctness better than 96% for a single eye or eyelid and 92% for eye and eyelid couples.     

基于成像机理的小波包变换多聚焦图像融合

由于可见光成像系统的聚焦范围有限,因而在成像过程中,除聚焦良好的物体能生成清晰的图像外,该物体前后一定距离外的所有物体都将呈现不同程度的模糊.为了获得场景内所有物体均清晰的图像,在分析了多聚焦图像成像机理的基础上,提出了一种基于小波包变换的融合方法.它是将成像系统先聚焦在一部分对象上,得到其清晰的图像;然后再将其聚焦在另一部分对象上,得到另一清晰的图像;最后把这两幅实验图像加以融合,从而获得场景内所有物体均清晰的图像.实验结果表明,基于小波包变换的融合方法能够将信号的频带进行多层次划分,对高频成分也能进一步地分解,可有效综合多聚焦图像.     

基于亚像素区域加权能量特征的多尺度图像融合算法

对矩形和圆形区域中各像素进行亚像素划分,确定各亚像素的权值,得到基于哑像素的综合加权区域能量.融合箅法首先对源图像进行金字塔分解,然后对金字塔的高频细节分量使用基于哑像素加权区域能量特征的融合规则取大,对低频粗糙分量取平均.得到融合图像的塔形分解,最后重构融合图像.仿真结果表明,新算法融合效果较常规的区域能量特征作为融合规则的多分辨率图像融合算法效果更好,从清晰度和熵的评价来看,提高了融合图像的品质.     

Arbitrary initialization for Chan–Vese model

Three problems about initialization of Chan–Vese model impeding its applications of Chan–Vese model, are discussed in this paper first by various experiments. Then, a novel method to solve these badly initialization problems is proposed, which can be divided into three parts: a hypothesis that image boundaries do not contain any feature of the objects; an examination criterion to check whether the current contour is suitable for continuing or not; and a method to revise the unsuitable current contour into a new one. The most important advantage of our proposed method is that it realizes the arbitrary initialization which can release the manual work in essence. Extensive experiments on synthetic and real images demonstrate the advantages of the proposed method.     

潜在低秩表示框架下基于卷积神经网络结合引导滤波的红外与可见光图像融合

为提高融合图像的可视性,解决传统红外与可见光图像融合算法中存在的边缘特征缺失、细节模糊的问题,提出了一种潜在低秩表示框架下基于卷积神经网络结合引导滤波的红外与可见光图像融合算法。该算法首先利用潜在低秩表示对源图像进行分解,得到源图像的低秩分量和显著分量。其次,利用卷积神经网络根据源图像的特征信息,得到权值图。再次,通过引导滤波算法对权值图进行边缘锐化,然后再将优化后的权值图分别与源图像的低秩分量和显著分量融合,得到融合图像的低秩分量和显著分量。最后,将融合图像的低秩分量和显著分量叠加,得到最终的融合图像。实验结果表明,该算法在主观评价和客观指标上均优于传统的红外与可见光图像融合算法。     

基于折反射原理的层去反求技术研究

为了克服传统层去反求测量中图像衬比度较低的缺陷,提出一种新的基于棱镜反射原理的层去反求图像摄取方法。该方法利用棱镜的全发射和折射作用提高图像衬比度,根据物体反射率的高低可分别采用垂直照明和倾斜照明,分别可获得高衬比度的亮目标暗背景和暗目标亮背景图像,为了校正由于折反射引入的几何变形,推出了相应的数学变换模型。该研究已成功投入实际产品校正的应用中,研究表明这种新的层去法比起传统的层去法不仅在于图像衬比度高,而且物体截面图像的轮廓更清晰可靠、无需填充反差材料,有望在零件及模型的反求测量中发挥较大的作用。     

DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution

This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network. Different from most existing works which rely on the utilization of the coil sensitivities or prior information of predefined transforms, DeepcomplexMRI takes advantage of the availability of a large number of existing multi-channel groudtruth images and uses them as target data to train the deep residual convolutional neural network offline. In particular, a complex convolutional network is proposed to take into account the correlation between the real and imaginary parts of MR images. In addition, the k-space data consistency is further enforced repeatedly in between layers of the network. The evaluations on in vivo datasets show that the proposed method has the capability to recover the desired multi-channel images. Its comparison with state-of-the-art methods also demonstrates that the proposed method can reconstruct the desired MR images more accurately.     

基于三幅子图的干涉合成孔径雷达数据处理方法研究

现有干涉合成孔径雷达(InSAR)数据处理方法需要单视复图像对包含的所有四幅子图信息, 且生成的干涉相位图去相关噪声非常严重。提出了基于三幅子图的InSAR数据处理方法：等值线相关干涉法, 包括图像对配准和干涉相位图生成。首先介绍了条纹方向图和条纹等值线窗口求取的方法, 并对算法进行了改进, 然后采用相关的方法详细推导了在等值线窗口内InSAR图像的配准和干涉相位图生成的公式。模拟和实测数据表明, 等值线相关干涉法(CCI方法)仅需用InSAR复数图像对的4个实虚部子图中任意3个能得到基本无斑点噪声、无模糊效应的干涉相位图, 并且减少了数据的传输和处理量, 是一种InSAR数据处理的全新方法。     

Alterable-capacity fragile watermarking scheme with restoration capability

To take invisibility and restoration quality into account, this paper proposes an alterable-capacity watermarking scheme. For each block of size 8 × 8 pixels, the alterable-length code is generated based on the roughness of it. The alterable-length watermark generated by the alterable-length code is divided into three parts and embedded in other three blocks based on the secret key. The authenticity of each block is determined by comparing the watermark reconstructed by the block content and the corresponding extracted watermark. To improve the quality of recovered images, two copies of the significant-code of each block are embedded in different blocks and the image inpainting method is adopted to recover the tampered blocks whose significant-code embedded in other blocks is destroyed. The alterable-payload watermark preserves adequate information of image blocks especially for texture images with as few bits as possible and takes into account invisibility, security and restoration quality. Experimental results demonstrate that the proposed scheme improves the quality of watermarked and reconstructed images and is resilient to the known forgery attacks.     

23Na TQF NMR imaging for the study of spinal disc tissue

A method for acquiring triple quantum filtered (TQF) (23)Na NMR images is proposed that takes advantage of the differences in transverse relaxation rates of sodium to achieve positive intensity, PI, NMR signal. This PITQF imaging sequence has been used to obtain spatially resolved one-dimensional images as a function of the TQF creation time, tau, for two human spinal disc samples. From the images the different parts of the tissue, nucleus pulposus and annulus fibrosus, can be clearly distinguished based on their signal intensity and creation time profiles. These results establish the feasibility of (23)Na TQF imaging and demonstrate that this method should be applicable for studying human disc tissues as well as spinal disc degeneration.     

Image registration based on matrix perturbation analysis using spectral graph

We present a novel perspective on characterizing the spectral correspondence between nodes of the weighted graph with application to image registration. It is based on matrix perturbation analysis on the spectral graph. The contribution may be divided into three parts. Firstly, the perturbation matrix is obtained by perturbing the matrix of graph model. Secondly, an orthogonal matrix is obtained based on an optimal parameter, which can better capture correspondence features. Thirdly, the optimal matching matrix is proposed by adjusting signs of orthogonal matrix for image registration. Experiments on both synthetic images and real-world images demonstrate the effectiveness and accuracy of the proposed method.