The three-dimensional architecture of the mitotic spindle,analyzed by confocal fluorescence and electron microscopy

Fluorescence microscopy techniques have become important tools in mitosis research. The well-known disadvantages of fluorescence microscopy, rapid bleaching, phototoxicity and out-of-focus contributions blurring the in-focus image are obstacles which still need to be overcome. Confocal fluorescence microscopy has the potential to improve our capabilities of analyzing cells, because of its excellent depth-discrimination and image processing power. We have been using a confocal fluorescence microscope for the study of the mechanism of poleward chromosome movement, and report here (1) a cell preparation technique, which allows labeling of fixation sensitive spindle antigens with acceptable microtubule preservation; (2) the use of image processing methods to represent the spatial distribution of various labeled elements in pseudocolour; (3) a novel immunoelectron microscopic labeling method for microtubules, which allows the visualization of their distribution in semithin sections at low magnification; and (4) a first attempt to study microtubule dynamics with a confocal fluorescence microscope in living cells, microinjected with rhodamine labeled tubulin. Our experience indicates that confocal fluorescence microscopy provides real advantages for the study of spatial colocalization of antigens in the mitotic spindle. It does not, however, overcome the basic limits of resolution of the light microscope. Therefore, it has been necessary to use an electron microscopic method. Our preliminary results with living cells show that it is possible to visualize the entire microtubule network in stereo, but that the sensitivity of the instrument is still too low to perform dynamic time studies. It will be worthwhile to further develop this new type of optical instrumentation and explore its usefulness on both fixed and living cells.     

基于模糊度测度和改进遗传算法的图像分割

为了利用模糊集理论进行图像分割,本文提出了一种模糊度测度函数,它衡量了背景模糊集和某一个二值图像的相似性:模糊度越小,这种相似程度越大;并且对模糊度的计算只需要进行简单的比较运算和加法运算,便于硬件实现。本文利用遗传算法求取最佳阈值,针对遗传算法的某些不足之处.我们利用精英策略和模拟退火的思想,对其做了一些修正。实验结果表明:相对于Shannon熵方法和模糊熵方法,本文方法取得了较好的分割结果,并且具有较强的抗噪声能力。     

基于复合顺序形态变换的车牌边缘检测

边缘检测是图像分割的重要环节,边缘提取的好坏直接影响了整个图像处理的效果。数学形态学用具有一定形态结构的“结构元素”去度量图像的形态,以解决图像处理和分析问题。文章通过对多种边缘检测方法的分析比较,结合高速公路路口汽车图像噪声大的特点,提出了基于复合顺序形态变换的车牌边缘检测。该方法不但能有效地改善有噪图像边缘检测的效果,鲁棒性好,而且并行快速,便于硬件实现。     

基于二维直方图分析的二元子图微光图像增强处理

提出了基于二维直方图分析的二元子图微光图像增强处理算法，根据原始图像的二维直方图分布特征，依据相邻像素的相关性数据，将图像分割成二元子图像，对每个子图像分别进行直方图均衡增强处理，最后合成得到完整的处理图像，通过用信息容量等图像评价参数对实验结果进行分析，表明此算法克服了对整幅图像进行直方图均衡时难以把握局部细节的缺点，得到了具有较好视觉质量的处理后微光图像。     

Pedestrian detection and tracking in infrared imagery using shape and appearance

In this paper, we present an approach toward pedestrian detection and tracking from infrared imagery using joint shape and appearance cues. A layered representation is first introduced and a generalized expectation-maximization (EM) algorithm is developed to separate infrared images into background (still) and foreground (moving) layers regardless of camera panning. In the two-pass scheme of detecting pedestrians from the foreground layer: shape cue is first used to eliminate non-pedestrian moving objects and then appearance cue helps to locate the exact position of pedestrians. Templates with varying sizes are sequentially applied to detect pedestrians at multiple scales to accommodate different camera distances. To facilitate the task of pedestrian tracking, we formulate the problem of shot segmentation and present a graph matching-based tracking algorithm that jointly exploits the shape, appearance and distance information. Experimental results with both OSU Infrared Image Database and WVU Infrared Video Database are reported to demonstrate the accuracy and robustness of our algorithm.     

An improved watershed algorithm based on efficient computation of shortest paths

The present paper describes a new algorithm to calculate the watershed transform through rain simulation of greyscale digital images by means of pixel arrowing. The efficiency of this method is based on limiting the necessary neighbouring operations to compute the transform to the outmost, and in the total number of scannings performed over the whole image. The experiments demonstrate that the proposed algorithm is able to significantly reduce the running time of the fastest known algorithm without involving any loss of efficiency.     

Image segmentation towards new image representation methods

Very low bit-rate video coding has recently become one of the most important areas of image communication and a large variety of applications have already been identified. Since conventional approaches are reaching a saturation point, in terms of coding efficiency, a new generation of video coding techniques, aiming at a deeper “understanding” of the image, is being studied. In this context, image analysis, particularly the identification of objects or regions in images (segmentation), is a very important step. This paper describes a segmentation algorithm based on split and merge. Images are first simplified using mathematical morphology operators, which eliminate perceptually less relevant details. The simplified image is then split according to a quad tree structure and the resulting regions are finally merged in three steps: merge, elimination of small regions and control of the number of regions.     

几种常用CT图像分割算法分析和探讨

图像分割是数字图像处理的一个经典难题。其分割质量的好坏直接影响到图像处理的后续工作。因而在理论研究和实际应用中受到研究人员的广泛重视。本文在总结了过去的分割方法基础上,就目前常用几种分割方法进行实验研究。主要包括阈值分割、LOG算子分割、FCM聚类分割、分水岭分割,并结合CT图像进行图像分割。文章阐述了各种分割方法的概念及原理,并在此基础上对分割结果进行了分析和探讨,得出各种方法的优点和不足。这些实验结论将为后续研究提供科学依据。     

基于二维Otsu阈值修正的图像分割新方法

首先采用对二维直方图斜分割和查表的方法,解决了传统二维Otsu方法分割图像计算耗时,难以实时实现的缺点。其次基于灰度统计的思想,针对二维Otsu法处理小目标图像难以实现正确分割的缺点,提出了一种在实现过程中采用迭代的阈值修正新方法。最后设计了一种新型滤波器对分割后的图像进行滤波降噪处理。实验结果表明,阈值修正后的二维Otsu改进算法对小目标图像分割效果明显,而且新型滤波器对滤除散布在目标与背景中的噪声非常有效。将阈值修正法和新型滤波器结合使用,不仅快速,而且准确,取得了良好的分割效果。     

一种基于数据竞争的高分辨率图像的聚类分割算法

近些年,机器人技术得到了迅猛的发展,应用越来越广泛.随着机器人技术的推广和普及,对机器人使用的要求也越来越高,其中对智能机器人的要求尤显迫切.机器视觉是智能机器人研究领域的一个重要研究方向.在机器人视觉系统中,核心问题是目标提取,对目标实时、准确、快速提取的关键技术是图像分割.由于机器人感知的环境的复杂性及目标的多样性,往往导致机器人感知获得的图像数据量较大且图像本身存在不可预知的复杂性,这就对准确的目标分割和提取处理提出了挑战性问题.本文针对高分辨率图像数据集的分割处理,提出一种新的聚类算法,即根据数据点能量和的大小识别类代表点和类成员点,通过数据点间的竞争识别出最有能力成为簇成员的数据点,并将其与mean shift聚类算法有效地结合应用于彩色图像分割问题中,能够快速高效地实现高分辨率图像的目标分割,并得到较好的图像分割效果.实验结果表明,本文算法在分割效果和分割效率上明显优于传统聚类算法.