基于MAP的自适应图像配准及超分辨率重建

图像超分辨率重建是一种将多幅低分辨率图像合成为高分辨率图像的技术.当前的超分辨重建技术主要分为图像配准和超分辨率重建2个步骤,提出一种基于最大后验概率的图像超分辨率重建算法,将这2个步骤合二为一;与此同时,为了解决配准参数以及点扩展函数估计值的不精确性问题,在每一幅低分辨率图像代价函数的残差项引入了自适应加权系数并随之...     

Alignment with sub‐pixel accuracy for images of multi‐modality microscopes using automatic calibration

A biological specimen is often imaged with various imaging modalities, and it is crucial that such images are well aligned to best reveal physiological structures and functions of the specimen for in‐depth analyses. In this paper, we present a methodology for automatic calibration of multiple optical imaging modalities within the x–y detector plane using a custom chrome‐on‐glass target and an automatic and accurate registration algorithm. The target contains lines crossing at random angles, and our method of registration is based on the alignment of salient features extracted from the lines within the individual images. Once spatial relationships are found between the various detectors and applied to the resultant images, no further registration is required for all static samples, and the registered images serve as the starting point for registration of dynamic samples, where the remaining misalignment is caused by sample movement. We have validated our algorithm with 40 inter‐modal and 30 intra‐modal image pairs, and the success rates are 95 and 100%, respectively, with sub‐pixel accuracy. This methodology is widely applicable to any multi‐modal microscope that combines a number of imaging modalities on a common platform assuming images of the target can be obtained.     

基于字典描述向量的实时图像配准

针对传统的特征向量计算方法复杂度高、耗时长、占用内存多等缺点,提出了一种基于字典描述向量的图像配准方法。该算法采用K-奇异值分解（K-SVD）方法生成字典,通过比较特征点临近区域图像与字典中基底图像的相似性得到特征描述向量,从而降低了描述向量的计算复杂度,提高了算法的实时性。实施该算法时,首先通过随机KD树算法对参考图像和待配准图像的特征点进行匹配,然后使用经典随机抽样一致性（RANSAC）算法剔除误匹配点对,最后应用最小二乘法对得到的匹配点对进行参数估计,从而得到两幅待配准图像的空间几何变换关系。实验表明结果,本文提出的描述向量计算方法降低了描述向量的存储空间,加快了特征匹配的速度,可在保证配准准确度的前提下实现配准过程。     

Fusion of mis‐registered GFP and phase contrast images with convolutional sparse representation and adaptive region energy rule

Biomedical image fusion is the process of combining the information from different imaging modalities to get a synthetic image. Fusion of phase contrast and green fluorescent protein (GFP) images is significant to predict the role of unknown proteins, analyze the function of proteins, locate the subcellular structure, and so forth. Generally, the fusion performance largely depends on the registration of GFP and phase contrast images. However, accurate registration of multi‐modal images is a very challenging task. Hence, we propose a novel fusion method based on convolutional sparse representation (CSR) to fuse the mis‐registered GFP and phase contrast images. At first, the GFP and phase contrast images are decomposed by CSR to get the coefficients of base layers and detail layers. Secondly, the coefficients of detail layers are fused by the sum modified Laplacian (SML) rule while the coefficients of base layers are fused by the proposed adaptive region energy (ARE) rule. ARE rule is calculated by discussion mechanism based brain storm optimization (DMBSO) algorithm. Finally, the fused image is achieved by carrying out the inverse CSR. The proposed fusion method is tested on 100 pairs of mis‐registered GFP and phase contrast images. The experimental results reveal that our proposed fusion method exhibits better fusion results and superior robustness than several existing fusion methods.     

Segmentation of confocal microscope images of cell nuclei in thick tissue sections

Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525), a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.     

基于单目视觉的视网膜三维重建技术研究

为了在视网膜疾病诊断中获得精度高、可视化好的视网膜,提出一种基于单目视觉的视网膜三维重建算法。该算法通过对两幅预处理图像的特征点提取确定匹配点对之间的对应关系,采用RANSAC算法去除误匹配点对,准确率高,用链匹配的方法使得多幅图像间的特征点匹配从而得到整体最优化结果。根据不同图像间特征点的对应关系,使用4通光束平差法确定空间中摄像机相对位置关系,使用PMVS算法实现视网膜的三维重建。实验结果表明,该算法具有很好的鲁棒性和稳定性,能较好地实现视网膜的三维重建。     

偏振探测系统的图像配准

分振幅式偏振探测成像系统的各分光路图像之间存在位置误差,率先完成各分光路图像之间的图像配准是进行偏振探测的前提条件。针对探测过程中,目标特征不明显、图像特征难以提取、各分光路图像间灰度变化较大的问题,提出适用于分振幅式偏振探测成像系统各分光路图像的相似性度量函数,并在此基础上,完成各分光路图像间的配准工作。首先,根据图像间的位置误差会造成偏振信息图像中出现信息异常区域的原理,研究了相似性度量函数的提取算法;接着,根据探测系统的各分光路的成像特点,确定图像间的几何变换参数;以遗传算法作为参数优化搜索算法,搜索得到最优的几何变换参数,完成整个图像配准算法的设计;最后,分别利用构造图像和实际采集图像,对配准算法进行了验证,并以图像间互信息值(MI)衡量图像配准的精度。实验结果表明:配准后的构造图像的MI为2.692 5,高于特征配准方法的实现精度;实际采集图像配准后的MI达1.849 3,同样高于特征配准方法的实现精度。基本满足偏振探测系统的图像配准需求。     

Surface imaging microscopy using an ultramiller for large volume 3D reconstruction of wax- and resin-embedded tissues

Three-dimensional reconstruction of large tissue volumes using histological thin sections poses difficulties because of registration of sections, section distortion, and the possibility of incomplete data set collection due to section loss. We have constructed an integrated surface imaging system that successfully addresses these problems. Embedded tissue is mounted on a high precision XYZ stage and the upper surface is iteratively: (i) stained to provide an effective optical section, (ii) imaged using a digital camera, and (iii) removed with an ultramiller. This approach provides for the reconstruction of high-quality 3D images by inherently preserving image registration, eliminates section distortion, thus removing the need for complex realignment and correction, and also ensures full capture of all image planes. The system has the capacity to acquire images of tissue structure with voxel sizes from 0.5 to 50 mum over dimensions ranging from micrometers to tens of millimeters. The ultramiller enables large samples to be imaged by reliably removing tissue over their full extent. The ability to visualize key features of 3D tissue structure across such a range of scale and resolution will facilitate the development of a greater understanding of the relationship between structure and function. This understanding is essential for better analyses of the structural changes associated with different disease states, and the development of structure-based computer models of biological function.     

A new approach for image stitching technique using Dynamic Time Warping (DTW) algorithm towards scoliosis X-ray diagnosis

Consider a set of images of a single object, or scenery, taken from different viewpoints and time. Panorama image creation is the process of stitching such images into a single coordinate system to generate a wider viewing panoramic image. Image stitching consists of two processes which are image registration and image blending. In image registration, parts of two overlapping or consecutive images are considered to find an appropriate merging position and transformation to combine the images. In image blending, the intensities of pixels along the stitching line are modified so that they flow naturally without any noticeable break. In this paper, we propose a novel method that utilizes the Dynamic Time Warping (DTW) algorithm to match pairs of images for image stitching. We also perform a dimension reduction scheme that significantly reduces the computational complexity of the standard DTW without affecting its performance. The effectiveness of the proposed method is demonstrated in stitching 50 pairs of medical X-ray images and its performance is compared to those of normalized cross correlation (NCC), Minimum Average Correlation Energy (MACE) filters, sum-of-square-differences (SSD) and sum-of-absolute-differences (SAD). For the database used, the dimensionally reduced DTW outperforms the NCC, MACE, SSD and SAD methods in accuracy and average execution time. The method also outperforms two widely used stitching programs available on the internet called Hugin and Autostitch.     

改进的视角鲁棒KAZE特征匹配算法

针对KAZE特征匹配算法对视角变化敏感,在大视角场景下不能实现正确匹配的问题,提出了一种视角鲁棒的PKAZE(Perspective-KAZE)算法。该算法在原KAZE描述符的基础上,计算特征点邻域内的二阶梯度均值,形成新的扩展的80维描述符;然后利用透视变换模型对待匹配影像进行多视角模拟,在模拟影像上提取改进的KAZE描述符,再进行特征匹配。最后,选取5对含有最多正确匹配数量的影像上的匹配对作为初始结果,利用随机抽样一致算法对初始结果提纯。对多组图像进行了匹配实验,结果表明:与KAZE、尺度不变特征变换(SIFT)和加速鲁棒特征(SURF)算法相比,所提算法对视角变化具有更强的鲁棒性;与透视尺度不变特征(PSIFT)和仿射尺度不变特征(ASIFT)算法相比,本算法匹配正确率更高,分别为PSIFT的2~10倍,ASIFT的2~7倍。提出的算法对视角变化具有很好的鲁棒性,不仅对模拟影像的视角变化很稳健,而且适用于真实三维复杂场景拍摄的大视角影像,具有一定的实用价值。     

基于抖动补偿技术的印刷品图像配准方法研究

在实际的印刷品缺陷检测过程中,存在因相机支架的颤动而导致标准印刷图像和待检测图像在空间位置上配准不精确的问题。为此,在图像去抖动技术的基础上,提出了一种融合SURF(speeded-up robust features)和ORB(oriented FAST and rotated BRIEF)的运动估计算法。首先,基于SURF算法提取标准印刷图像和待检测图像的特征点;其次,基于ORB算法对提取的特征点进行描述和匹配;再次,将正确匹配的特征点通过仿射模型来求取全局运动矢量;最后,通过求得的全局运动矢量来补偿图像,并完成待检测图像与标准印刷图像的配准。针对待测图像存在的平移、尺度和旋转三种不同变化,分别采用SURF-ORB、ORB和SIFT(scale-invariant feature transform)的运动估计算法进行了性能分析。结果表明,SURFORB的特征点匹配对数量最多,匹配效果最好,SURB-ORB的运动估计时间控制在毫秒级别,满足现代印刷品缺陷检测的实时性要求。因此,融合SURF和ORB的运动估计算法能够对图像进行精确、实时的配准。     

Data-driven, simultaneous blur and image restoration in 3-D fluorescence microscopy

A novel algorithm for simultaneous blur and image restoration (SBIR)* in three-dimensional (3-D) fluorescence microscopy is presented. All the internal parameters including the point spread function essential for the restoration are estimated from the data. Validation of the SBIR algorithm using simulated signals/images and known real world specimens is provided. Both lateral and axial resolution of images are improved by the application of the algorithm. Finally, the results of the application of the algorithm to unknown specimens are shown, demonstrating the potential of the algorithm in practical applications. Furthermore, evidence is provided to show that this algorithm can provide a turn-key system to deblur images in 3-D fluorescence microscopy.     

Attenuation correction in confocal laser microscopes: a novel two-view approach

Confocal microscopy is a three‐dimensional (3D) imaging modality, but the specimen thickness that can be imaged is limited by depth‐dependent signal attenuation. Both software and hardware methods have been used to correct the attenuation in reconstructed images, but previous methods do not increase the image signal‐to‐noise ratio (SNR) using conventional specimen preparation and imaging. We present a practical two‐view method that increases the overall imaging depth, corrects signal attenuation and improves the SNR. This is achieved by a combination of slightly modified but conventional specimen preparation, image registration, montage synthesis and signal reconstruction methods. The specimen is mounted in a symmetrical manner between a pair of cover slips, rather than between a slide and a cover slip. It is imaged sequentially from both sides to generate two 3D image stacks from perspectives separated by approximately 180° with respect to the optical axis. An automated image registration algorithm performs a precise 3D alignment, and a model‐based minimum mean squared algorithm synthesizes a montage, combining the content of both the 3D views. Experiments with images of individual neurones contrasted with a space‐filling fluorescent dye in thick brain tissue slices produced precise 3D montages that are corrected for depth‐dependent signal attenuation. The SNR of the reconstructed image is maximized by the method, and it is significantly higher than in the single views after applying our attenuation model. We also compare our method with simpler two‐view reconstruction methods and quantify the SNR improvement. The reconstructed images are a more faithful qualitative visualization of the specimen's structure and are quantitatively more accurate, providing a more rigorous basis for automated image analysis.     

改进Demons算法的非刚性医学图像配准

非刚性配准是医学图像处理的一个重要的研究方向。基于光流场模型的Demons算法由于仅依赖图像灰度梯度使图像变形,当缺乏梯度信息时图像的变形方向不能确定,因而容易造成误配准,且该算法只适合于单模态图像配准。本文针对最大互信息配准方法在多模态刚性配准中的成功应用,提出了一种可用于多模态图像配准的改进Demons算法。该方法在原有驱动图像变形力的基础上,增加两幅图像间互信息对当前变换的梯度作为附加力作用,使浮动图像向两图像间互信息增大的方向变形,正确地配准图像。为避免陷入局部极值并提高算法的运行速度,该方法在多分辨率策略下实现。使用单模态、多模态图像分别进行实验来验证此算法,并与原始Demons算法进行比较,实验表明,该方法能够快速地产生准确的配准变换。     

基于区域分块与尺度不变特征变换的图像拼接算法

针对图像匹配算法计算量大,实时性差的问题,提出了一种基于区域分块与尺度不变特征变换(SIFT)相结合的图像拼接算法。该算法利用图像能量的归一化互相关系数快速分割出匹配图像与待匹配图像间的相似区域,利用SIFT算法在重叠区域中搜索出能用于匹配的图像特征点并实现快速精确配准。然后,通过对图像进行了几何校正和图像融合来实现图像序列间的无缝拼接。实验结果表明,该算法减少了传统SIFT算法的大量无用搜索,改善了图像的几何失真,降低了算法复杂度,提高了图像匹配的速度,在保证90%以上的匹配准确率的基础上,计算时间较传统SIFT算法减少了近50%。提出的算法可准确、快速地实现有形变和尺度变换图像的无缝拼接。     

Stereo pairs of bright-field micrographs via Wiener-type inverse filtering

In a three-dimensional (3-D) image data set obtained through optical sectioning, each two-dimensional (2-D) segment is blurred by out-of-focus information from neighbouring focal planes superimposed on the in-focus segments from that plane. Instead of attempting to remove this redundant information over the full 3-D data set, we have developed a technique for restoring stereoscopic views. In this paper we describe the implementation of a Wiener-type inverse filtering method for generating stereo pairs of bright-field micrographs. A theoretical optical transfer function valid under certain simplifying approximations has been used in implementing this filtering technique. In developing this method the slice theorem of computed tomography is used. In this way the image reconstruction problem is reduced to one of processing 2-D arrays rather than 3-D arrays and the problem of restoring missing Fourier components within the missing-cone region is circumvented. Limited experimentation with real micrographs shows that the approach provides images that display an effective increased depth of field and 3-D attributes of the specimen, even though some of the underlying assumptions on which this method is based are difficult to verify explicitly. The method can be implemented with a relatively fast execution time on 386-SX computers.     

克服动态问题影响的相机响应函数标定

利用图像之间的亮度映射函数而不是图像本身各像素点信息进行相机响应函数的标定,避免了成像系统的晃动或者拍摄场景的动态问题带来的图像配准之间的误差给后续标定算法带来的影响。采用直方图规则化的方法分析不同曝光量图像之间的各颜色通道不同亮度级的统计特征,获得了不同图像对之间的亮度映射函数。然后,利用图像对之间的亮度映射函数结合各帧图像的直方图建立求解相机响应函数的超定方程模型。最后,利用最小二乘法解算模型获得相机响应函数。验证实验表明,本文相机响应函数标定算法具有克服相机的动态问题的能力;不同输入帧数图像的分组实验显示,最小输入4帧图像能够获得较为理想的响应函数标定结果。     

采用目标区域互信息的星空图像配准

提出了采用目标区域互信息的测度方法对星图进行精确配准以解决星图中存在噪声、伪星点、星点稀疏以及星图间的旋转等问题。首先对星图进行图像分割,检测出星点目标并对星点进行二值化处理;然后基于互信息配准模型,在含星点的目标区域上,利用Powell算法将最大互信息作为目标函数来指导图像间最优变换参数的搜索。分析了适宜于互信息测度配准的星点分割算法,并论证了采用目标区域互信息的星图配准的可行性。对提出的算法与标准的互信息配准算法进行了对比。结果表明:提出算法的时间消耗与图像中星的数量有关,在图像大小为1 000×1 000时,提出算法的加速比为标准算法的3.4倍。该算法在星图中存在噪声、伪星点、星点稀疏和旋转的情况下仍能进行准确配准,50组实拍星图配准误差平均值为0.138 2pixel,满足了星空图像对精确配准的要求。     

基于ORB与RANSAC融合改进的图像拼接方法

针对旋转不变性二进制描述算法（Oriented Fast and Rotated Brief, ORB）的尺度旋转性配准误差大,配准率较低及随机采样一致性（Random Sample Consensus, RANSAC）算法随机性强且不稳定的问题,提出一种ORB与RANSAC结合的快速特征匹配算法。首先,对特征点提取方式进行优化选择,消除特征边缘影响。之后构建简化的金字塔式尺度空间模型,改进分层图像的尺度空间结构,减少生成图像层数和数目;然后采用梯度方向改进传统ORB算法中的主方向提取模式,提高特征角点主方向的准确性。最后,通过构建分块随机取样检测的方式改进RANSAC算法,提高RANSAC算法的稳定性和图像配准的准确性。实验结果表明改进后的ORB和RANSAC融合算法在尺度和旋转配准方面性能有很大提高,并且配准的精度较传统ORB算法高,尺度配准精度提高55.41%,旋转配准精度提高26.66%。满足复杂图像快速精确配准拼接的精度和实时性要求。