Human eye sclera detection and tracking using a modified time-adaptive self-organizing map

This paper investigates the use of time-adaptive self-organizing map (TASOM)-based active contour models (ACMs) for detecting the boundaries of the human eye sclera and tracking its movements in a sequence of images. The task begins with extracting the head boundary based on a skin-color model. Then the eye strip is located with an acceptable accuracy using a morphological method. Eye features such as the iris center or eye corners are detected through the iris edge information. TASOM-based ACM is used to extract the inner boundary of the eye. Finally, by tracking the changes in the neighborhood characteristics of the eye-boundary estimating neurons, the eyes are tracked effectively. The original TASOM algorithm is found to have some weaknesses in this application. These include formation of undesired twists in the neuron chain and holes in the boundary, lengthy chain of neurons, and low speed of the algorithm. These weaknesses are overcome by introducing a new method for finding the winning neuron, a new definition for unused neurons, and a new method of feature selection and application to the network. Experimental results show a very good performance for the proposed method in general and a better performance than that of the gradient vector field (GVF) snake-based method.     

基于二进小波变换的主动轮廓模型

针对传统的主动轮廓模型对噪声敏感的缺陷,在推广梯度矢量流的基础上,提出了基于二进小波变换的改进外力场的计算方法.通过综合利用图像小波分解的高频信息,迭代计算获得其外力场,使蛇在图像的多尺度空间中搜索目标轮廓.针对蛇模型对初始轮廓的依赖性问题,给出了在一维最大熵阈值分割后的图像上获取初始轮廓点的方法,减少了人工的干预,加快了蛇的收敛速度和效果.实验结果表明该模型能有效地排除噪声的干扰,搜索凹陷轮廓,而且对脆弱轮廓有很好的逼近能力.     

基于GVF的骨架snake模型

提出了一种基于梯度矢量流(GVF)的快速收敛骨架snake算法。首先利用GVF变换后凹腔内外力的特点检测出物体的骨架，然后以骨架作为指引修改其外力的方向和大小，以达到快速收敛。该算法不但能解决GVF不能解决的深凹腔问题，而且在速度上也远远超过GVF。     

GVF Snake模型时间复杂度的研究

对使用GVF Snake动态轮廓模型算法中两次迭代的时间复杂度进行了统计计算,并进行了力场分析,在此基础上对初始轮廓线设定位置进行了研究。实验结果表明,初始轮廓线的设置应避免跨越能量极小值,此时可以得到比较好的提取效果。GVF力场迭代的次数和轮廓逼近次数与时间成正比。     

一种基于光流的GVF主动轮廓线模型在颈动脉超声动态图像序列边缘提取中的运用

颈动脉超声图像边缘的提取对冠状动脉疾病的诊断和治疗有着重要的意义。本文提出了一种针对颈动脉超声动态图像序列的边缘跟踪方法。根据前一帧图像的边界轮廓,通过计算当前帧与前一帧之间的光流场来预测当前帧图像的初始轮廓,再使用GVF主动轮廓线方法进行分割。然后依次处理图像序列的每一帧图像。实验证明,这种方法相对与独立的分割每帧图像更有效率,并且由于使用了光流来进行预测,具有很好的动态跟踪能力。     

基于梯度向量流的医学图像自动分割

提出了一种基于梯度向量流的自动图像分割算法，该算法首先将梯度向量流场转化为一个标量场，该标量场能够显著简化种子点选取和区域增长的步骤。在得到图像的初始分割后，再使用基于区域邻接图的算法来将相似区域合并得到最终分割结果。试验结果表明，该算法能够有效地解决医学图像中多目标区域的自动分割问题。     

一种新型的视盘分割方法

视盘的检测对于眼底图像分析和计算机辅助诊断视网膜神经疾病有重要意义。论文提出了一种新型的视盘分割方法,新方法的思想是在去除血管的背景图像应用梯度向量场 GVF 活动轮廓模型。首先,从原始图像获取部分背景图像的像素,即获得在去除图像中血管像素之后的部分像素,然后利用取得部分背景的像素重塑整个背景图像,最后在恢复的背景图像中应用 GVF 活动轮廓模型分割出视盘,GVF Snake 模型的初始曲线为 Hough circle 。选取了不同的眼底医学图像进行了大量的实验,结果表明论文算法的分割结果十分准确,具有较好的分割效果。     

基于熵和GVF的血管内超声图像边缘检测

血管内超声(intravascular ultrasound,IVUS)图像属于复杂度高的图像,只使用传统的Snake模型、GVF模型不易得到确切的血管壁内、外膜边缘轮廓。本文采用先对IVUS原图像进行预处理的方法来降低IVUS图像的复杂度。在预处理中,提出了采用极坐标变换、基于熵的阈值分割和二值化处理的方法。之后再采取改进的GVF变换与图像迭加等处理方法。实验结果验证了该方法的有效性。     

Automatic segmentation on multiple starch granules from microscopic images

Starch is the most important carbohydrate in the human diet and contained in many staple foods such as rice, wheat, corn, potatoes and cassava, etc. Currently, microscopic imaging technology is one of the most effective ways to investigate and analyze the structure of starches. Segmentation of starch granules is a necessary step for starch granule structure analysis such as starch granules detection, shape recognition, and size computation. This article investigates a new method based on GVF (gradient vector flow) snake deformable model for starch granules segmentation. The proposed method focuses on full automatic segmentation on granules, especially on separation of adjacent and contacted starch granules, which occur widely in microscopic images. A novel energy function based on position and intensity is introduced into the directional gradient computation, thus the directional gradient is used to obtain the directional GVF snake, which drives the deforming contours to the real contours of multiple granules. To demonstrate the good ability of the proposed method, we segment 30 starch granule images and compare it with the level set method, experimental results show that the new method can separate multiple starch granules successfully; especially it works much better on overlapping objects segmentation than the level set method.     

基于改进CV模型的多尺度图像分割方法*

在结合多尺度图像分析和水平集图像分割模型的基础上提出了一种新的多尺度图像分割方法.首先使用引入梯度向量流的全变差方法对图像进行多尺度空间分析,然后使用一种改进的CV模型进行分割.采用变分水平集方法作数值计算,因此该方法能够处理曲线的拓扑变化.实验结果表明该方法是有效的.