基于多小波的胃癌病理细胞图像边缘检测与分析

对胃癌细胞图像的多尺度小波变换边缘检测进行了研究,为医生运用现代信息理论的方法进行相关疾病诊断提供了一种新的思路和途径。提出了多尺度小波边缘检测的新方法,归纳了改善小波边缘检测效果的一些策略。实验结果表明,对于具有复杂纹理的医学病理细胞图像,采用传统的边缘检测方法会产生伪边缘和方向性误差,它影响了图像边缘检测的可信度;而运用小波变换的时频尺度特性和对奇异变化的优良检测性能,可得到无噪声污染的图像实际边缘。     

基于微血栓运动分析的微血管特征结构自动提取

提出了一种基于微血栓运动分析的微血管特征结构自动提取策略。提出用灰度梯度直方图统计来自动选阈的快速阈值值化算法,检测形态复杂的微血管图像边缘,抑制次要的微血管,采用低阈值双窗二次角点选择策略选取边缘曲线角点。通过微血管显微图像及其二值化图像分析,建立反映含微血栓的微血管特征结构模型,利用微血管的先验知识,给出提取微血管特征结构的算法,最后给出微血管显微图像结构的提取结果,实验证明该算法是十分有效的。含微血栓的微血管的特征结构建立,复杂的微血栓的匹配和识别问题将得到简化,微血管及微血栓的形态变化及运动估算任务得以减轻。该研究对于脑微循环障碍和老年病的基础医学研究和临床实践具有十分重要的意义。     

基于多尺度植物种子图像边缘检测算法的设计与实现

小波变换,由于其具有时频局部化的特性及多尺度特性,能敏感地反映突变信号,是一种理想的边缘提取方法．本文系统地介绍了作者在图像边缘检测方面所做的理论探讨、算法及应用研究工作．目前的边缘提取方法有多种,本文将重点集中于基于小波变换的图像边缘检测方法的理论推导和算法实现．     

基于PET医学图像边缘检测算法的研究

目的:边缘检测在图像处理中至关重要,可被广泛应用于目标区域识别、区域形状检测、图像分割等图像分析领域。边缘是图像中不平稳现象和不规则结构的重要表现,往往携带着图像中的大量信息,并给出图像轮廓。在医学图像三维显示技术中,为了更精确的临床判别需要得到单像素的清晰轮廓,因此我们提出一种新的边缘检测算法。方法:在传统的小波边缘检测的基础上,提出了一种新的边缘算法,即基于小波极大值边缘检测算法,应用模糊算法构造相应的隶属函数,再对得到的极大值进一步筛选。结果:将该算法应用到医学图像中,最终可以得到较清楚的单像素边缘轮廓,实验结果证明了该算法的可行性。结论:运用这种算法处理过的医学图像边缘锐化更好,更清晰,能够为肿瘤的早期识别提供依据,满足医学影像识别的需要。     

基于空间小波变换的生态地理界线识别与定位

为了提高生态地理分界线识别和定位的客观性,探讨了通过空间小波变换获取多尺度模极大值定位过渡带的方法.以NDVI和降水作为小波多尺度分解的对象,应用db3小波核函数分别对49条样带的模极大值进行了多尺度检测,并在GIS中确定其地理坐标.研究结果表明:识别半干旱半湿润生态地理分界线的最佳空间尺度为20～40 km,小于这一尺度定位过程容易受到局部地表覆被因素如城市区域或地形的影响,大于这一尺度由于要素被过度平滑,造成定位不准;从定位点的聚集度分析,NDVI的定位效果好于降水,特别是在较大空间尺度上.而与综合自然地理区划方案中的半干旱半湿润分界线比较,从定位点的方向性、平均最短距离以及均衡度三项指标综合判断,小波变换对于降水过渡带的定位优于对NDVI的定位.研究证实,空间小变换与GIS结合是提高生态地理分界线识别与定位科学性的重要途径,是对专家系统划分界线方法的有力补充和完善.     

景观生态学中的尺度分析方法

多尺度空间分析法是发现和识别景观特征尺度的主要方法.当前这类方法很多,缺乏归类和对比分析评价.基于空间类型变量和数值变量,对多尺度空间分析方法进行了重新梳理.同时对当前常用的尺度分析方法:半方差分析、尺度方差分析、小波分析和孔隙度指数分析,以中国三北防护林为例,对比了各种尺度分析方法的特点和优劣.结果表明,在特征尺度的识别上:小波方差方法清晰明了;半方差分析法灵活简捷,结果明显;尺度方差分析法和孔隙度指数法在本研究中的判识结果不甚明显.在计算速度上:半方差分析法计算量最大、耗时最长,尺度方差次之,小波方差速度最快,孔隙度指数法计算速度快于前两种,慢于小波方差分析方法.半方差分析方法简单灵活,而且相关理论方法成熟,但缺乏对大尺度格局的整体把握,而小波分析恰恰能很好的弥补这一不足.最后提出,半方差分析和小波变换相结合将会是最优的尺度分析方法.     

一种基于小波变换的心电去噪算法

目的:去除心电信号采集过程中混入的工频干扰、肌电干扰和基线漂移等噪声信号,并能有效的保留心电特征信息.方法:通过小波变换将含噪的心电信号分解并重构得到不同尺度下的细节信号,在中小尺度上选取不同的门限值,并在QRS波群信息多的尺度上计算获得信息窗,对该尺度的信息窗内外采用不同的门限处理方式,在大尺度上直接重构出要去除的基线信息.结果:采用MIT/BIH Arrhythmia Database中的数据对算法进行了仿真验证,实现了三种主要干扰的去除,较好的保留了心电特征信息.结论:本方法效果较好,为后续的特征点识别奠定了基础.     

基于变动窗口和移动序列的基因识别算法

采用信号处理技术来识别DNA碱基序列中的基因片段的方法,已经成为一种重要的基因识别途径,重新编码的DNA序列存在大量噪声信息,使得目前很多识别算法无法准确的识别外显子片段的起始位置。本研究通过对"固定长度滑动窗口-频谱曲线法"和"移动序列-信噪比法"的实现与改进,提出了一种基于变动窗口和移动序列的基因识别算法。首先,对已有基因识别算法进行编程实现;采用小波分析对识别结果进行消噪处理;探讨识别最优固定长度M的选择,提出基于变动窗口和移动序列的基因预测模型,并编程实现。最后使用该模型对已有基因序列进行识别,其识别准确度达到77.57%。     

初级视觉的小波表征及其图象压缩效果

初级视觉的Ｇａｂｏｒ函数模型和变换尺度为３是初级视觉处理外界信息的主要特征,在此基础上,由于小波所具有的多分辨特性与视觉处理由粗到细的过程相一致,因而,希望存在一类能够表征这两个初高觉特征的小波亦换。从这点出发,本文先给出了具有变换尺度为３的正交Ｈａａｒ基,而后给出了具有以上两个特征的小波基和小波滤波器。     

1959—2006年长白山地区降水序列的多时间尺度分析

基于长白山地区松江、东岗、长白、和龙、临江和天池6个气象站1959—2006年的月均降水量和年降水量数据,采用Morlet小波分析方法,对1959—2006年长白山地区植被生长季(5—9月)降水量、降雪季(11月至次年4月)降水量和年降水量序列进行多尺度特征分析,并运用Daubechies小波系中的db5小波对各降水序列进行不同层次的分解和低频重构,对重构序列进行了趋势识别和分析.结果表明:研究期间,长白山地区植被生长季降水量存在3～6a、10～13a和24～30a的特征周期;降雪季降水量存在1～2a、5～7a和17～20a的特征周期;年降水存在8～10a、16～20a、25～30a的特征周期;研究区年降水量序列呈现整体下降的趋势.     

Image Quality Assessment Based on Inter-Patch and Intra-Patch Similarity

In this paper, we propose a full-reference (FR) image quality assessment (IQA) scheme, which evaluates image fidelity from two aspects: the inter-patch similarity and the intra-patch similarity. The scheme is performed in a patch-wise fashion so that a quality map can be obtained. On one hand, we investigate the disparity between one image patch and its adjacent ones. This disparity is visually described by an inter-patch feature, where the hybrid effect of luminance masking and contrast masking is taken into account. The inter-patch similarity is further measured by modifying the normalized correlation coefficient (NCC). On the other hand, we also attach importance to the impact of image contents within one patch on the IQA problem. For the intra-patch feature, we consider image curvature as an important complement of image gradient. According to local image contents, the intra-patch similarity is measured by adaptively comparing image curvature and gradient. Besides, a nonlinear integration of the inter-patch and intra-patch similarity is presented to obtain an overall score of image quality. The experiments conducted on six publicly available image databases show that our scheme achieves better performance in comparison with several state-of-the-art schemes.     

A multiresolution approach to orientation assignment in 3D electron microscopy of single particles

Three-dimensional (3D) electron microscopy (3DEM) aims at the determination of the spatial distribution of the Coulomb potential of macromolecular complexes. The 3D reconstruction of a macromolecule using single-particle techniques involves thousands of 2D projections. One of the key parameters required to perform such a 3D reconstruction is the orientation of each projection image as well as its in-plane orientation. This information is unknown experimentally and must be determined using image-processing techniques. We propose the use of wavelets to match the experimental projections with those obtained from a reference 3D model. The wavelet decomposition of the projection images provides a framework for a multiscale matching algorithm in which speed and robustness to noise are gained. Furthermore, this multiresolution approach is combined with a novel orientation selection strategy. Results obtained from computer simulations as well as experimental data encourage the use of this approach.     

Generic properties of edges and “corners” on smooth greyvalue surfaces

The edge line on a smooth greyvalue surface, defined as locus of maximal slope, is a curve embedded in the negatively curved part of the greyvalue surface. For an open and dense set of greyvalue functions the edge line has transverse double points as its only singular points, meets the parabolic curve tangentially at isolated points, and intersects the zero crossings of the Laplacean of the greyvalue function transversely. Defining a greyvalue corner as a curvature extremum of the edge line one can show that, again for an open and dense set of greyvalue functions, these corners are isolated points in the image corresponding to ordinary curvature extrema of the edge. Detecting such corners in greyvalue images requires differential operators containing partial derivatives of order five, which raises some doubts about the existence of numerically robust algorithms for detecting these features in digital images.     

Computational methods for quantifying in vivo muscle fascicle curvature from ultrasound images

Muscle fascicles curve during contraction, and this has been seen using B-mode ultrasound. Curvature can vary along a fascicle, and amongst the fascicles within a muscle. The purpose of this study was to develop an automated method for quantifying curvature across the entirety of an imaged muscle, to test the accuracy of the method against synthetic images of known curvature and noise, and to test the sensitivity of the method to ultrasound probe placement. Both synthetic and ultrasound images were processed using multiscale vessel enhancement filtering to accentuate the muscle fascicles, wavelet-based methods were used to quantify fascicle orientations and curvature distribution grids were produced by quantifying local curvatures for each point within the image. Ultrasound images of ramped isometric contractions of the human medial gastrocnemius were acquired in a test–retest study.The methods enabled distinct curvatures to be determined in different regions of the muscle. The methods were sensitive to kernel sizes during image processing, noise within the image and the variability of probe placements during retesting. Across the physiological range of curvatures and noise, curvatures calculated from validation grids were quantified with a typical standard error of less than 0.026 m^?1, and this is about 1% of the maximum curvatures observed in fascicles of contracting muscle.     

Efficient Video Panoramic Image Stitching Based on an Improved Selection of Harris Corners and a Multiple-Constraint Corner Matching

Video panoramic image stitching is extremely time-consuming among other challenges. We present a new algorithm: (i) Improved, self-adaptive selection of Harris corners. The successful stitching relies heavily on the accuracy of corner selection. We fragment each image into numerous regions and select corners within each region according to the normalized variance of region grayscales. Such a selection is self-adaptive and guarantees that corners are distributed proportional to region texture information. The possible clustering of corners is also avoided. (ii) Multiple-constraint corner matching. The traditional Random Sample Consensus (RANSAC) algorithm is inefficient, especially when handling a large number of images with similar features. We filter out many inappropriate corners according to their position information, and then generate candidate matching pairs based on grayscales of adjacent regions around corners. Finally we apply multiple constraints on every two pairs to remove incorrectly matched pairs. By a significantly reduced number of iterations needed in RANSAC, the stitching can be performed in a much more efficient manner. Experiments demonstrate that (i) our corner matching is four times faster than normalized cross-correlation function (NCC) rough match in RANSAC and (ii) generated panoramas feature a smooth transition in overlapping image areas and satisfy real-time human visual requirements.     

Automated tracking of muscle fascicle orientation in B-mode ultrasound images

B-mode ultrasound can be used to non-invasively image muscle fascicles during both static and dynamic contractions. Digitizing these muscle fascicles can be a timely and subjective process, and usually studies have used the images to determine the linear fascicle lengths. However, fascicle orientations can vary along each fascicle (curvature) and between fascicles. The purpose of this study was to develop and test two methods for automatically tracking fascicle orientation. Images were initially filtered using a multiscale vessel enhancement (a technique used to enhance tube-like structures), and then fascicle orientations quantified using either the Radon transform or wavelet analysis. Tests on synthetic images showed that these methods could identify fascicular orientation with errors of less than 0.06°. Manual digitization of muscle fascicles during a dynamic contraction resulted in a standard deviation of angle estimates of 1.41° across ten researchers. The Radon transform predicted fascicle orientations that were not significantly different from the manually digitized values, whilst the wavelet analysis resulted in angles that were 1.35° less, and reasons for these differences are discussed. The Radon transform can be used to identify the dominant fascicular orientation within an image, and thus used to estimate muscle fascicle lengths. The wavelet analysis additionally provides information on the local fascicle orientations and can be used to quantify fascicle curvatures and regional differences with fascicle orientation across an image.     

Certain Investigations on Melanoma Detection Using Non-Subsampled Bendlet Transform with Different Classifiers

Skin is the largest organ and outer enclosure of the integumentary system that protects the human body from pathogens. Among various cancers in the world, skin cancer is one of the most commonly diagnosed cancer which can be either melanoma or non-melanoma. Melanoma cancers are very fatal compared with non-melanoma cancers but the chances of survival rate are high when diagnosed and treated earlier. The main aim of this work is to analyze and investigate the performance of Non-Subsampled Bendlet Transform (NSBT) on various classifiers for detecting melanoma from dermoscopic images. NSBT is a multiscale and multidirectional transform based on second order shearlet system which precisely classifies the curvature over other directional representation systems. Here two-phase classification is employed using k-Nearest Neighbour (kNN), Naive Bayes (NB), Decision Trees (DT) and Support Vector Machines (SVM). The first phase classification is used to classify the images of PH2 database into normal and abnormal images and the second phase classification classifies the abnormal images into benign and malignant. Experimental result shows the improvement in classification accuracy, sensitivity and specificity compared with the state of art methods.     

A Novel Method of Automatic Plant Species Identification Using Sparse Representation of Leaf Tooth Features

Automatic species identification has many advantages over traditional species identification. Currently, most plant automatic identification methods focus on the features of leaf shape, venation and texture, which are promising for the identification of some plant species. However, leaf tooth, a feature commonly used in traditional species identification, is ignored. In this paper, a novel automatic species identification method using sparse representation of leaf tooth features is proposed. In this method, image corners are detected first, and the abnormal image corner is removed by the PauTa criteria. Next, the top and bottom leaf tooth edges are discriminated to effectively correspond to the extracted image corners; then, four leaf tooth features (Leaf-num, Leaf-rate, Leaf-sharpness and Leaf-obliqueness) are extracted and concatenated into a feature vector. Finally, a sparse representation-based classifier is used to identify a plant species sample. Tests on a real-world leaf image dataset show that our proposed method is feasible for species identification.