面向计算机显微视觉系统的白细胞识别

为了解决人工镜检白细胞识别效率低下的问题, 采用计算机显微视觉平台进行了白细胞自动识别研究。白细胞图像分割方面, 筛选图像颜色模型之后采用区域生长算法实现白细胞与图像背景的精确剥离; 并利用大津法(即灰度直方图波谷阈值分割方法)实现了白细胞细胞核和细胞浆的提取; 根据细胞的形态、颜色及纹理特征用人工神经网络分类器对大样本量的白细胞进行了识别分类。结果表明, 采用白细胞图像分割和智能辨识算法具有较高的精度和效率, 最终准确度能够达到95.6%。该系统满足临床医学显微视觉白细胞自动检测的需求。     

Design and Clinical Results of Hematrak: An Automated Differential Counter

A differential white blood cell classifier is described. The system, which is based upon a three-color flying spot-scanner approach, utilizes recognition parameters based on the principle of geometrical probability functions which are generated at high speed in a dedicated computer. The result is a pattern recognition system capable of performing a routine clinical differential cell count at the rate of 100 cells/40s on a traditionally prepared specimen. The Hematrak system was evaluated in a routine clinical laboratory which reported that reproducibility, normal cell recognition accuracy, and the detection of abnormality were at least comparable to the manual technique.     

Edge Detection in Digital Images Using Guided L0 Smoothen Filter and Fuzzy Logic

Image segmentation is an important process in computer vision. Recently fuzzy logic based edge detection is heavily investigated as by changing the number of rules edge detection can be improved. However, due to large colour variations in the images false edges are detected and even using fuzzy rules they cannot be reduced significantly. These falsely detected edges can be controlled by using smoothen filter while controlling the degree of smoothness. This paper, presents fuzzy logic based edge detection mechanism while using Guided L₀ smoothen filter for the smoothening of image under various degree of smoothens. Simulation results for edge detection is presented for Canny, Sobel, Fuzzy logic based edge detection and finally fuzzy logic edge detection with inclusion of L₀ smoothen filter. The results are compared with classical and modern methods. Simulation is performed on Berkley Segmentation Database (BSD) and USC-SIPI Image Database while considering more than 100 images. The obtained F-measure is as high as 0.848.

     

Automated cell nuclei segmentation for breast fine needle aspiration cytology

Breast cancer detection and segmentation of cytological images is the standard clinical practice for the diagnosis and prognosis of breast cancer. This paper presents a fully automated method for cell nuclei detection and segmentation in breast cytological images. The images are enhanced with histogram stretching and contrast-limited adaptive histogram equalization (CLAHE). The locations of the cell nuclei in the image are detected with circular Hough transform (CHT) and local maximum filtering. The elimination of false positive findings (noisy circles and blood cells) is achieved using Otsu’s thresholding method and fuzzy C-means clustering technique. The segmentation of the nuclei boundaries is accomplished with the application of the marker controlled watershed transform in the gradient image, using the nuclei markers extracted in the detection step. The proposed method is evaluated using 92 breast cytological images containing 11,502 cell nuclei. Experimental evidence shows that the proposed method has very effective results even in the case of images with high degree of blood cells, noisy circles.     

基于RGB和C-Y颜色空间的白细胞分割

为了解决血细胞图像中白细胞与其它细胞色彩接近、亮度不均匀等问题,采用了一种基于 C - Y 颜色空间的白细胞分割方法,将原来的 RGB 图像转化为 C - Y 图像,分离 C - Y 图像获得包含全部信息的 B - Y 颜色分量图像,再根据连通域面积筛选、开运算、像素点操作得到完整的白细胞图像;提取对比度拉伸后的 G 图像,阈值分割得到细胞核的大概位置,再用连通域面积筛选、开运算方法分割出完整的细胞核图像。结果表明,本文中的算法对嗜酸性粒细胞、淋巴细胞、单核细胞和嗜中性粒细胞图像都具有较好的分割精度,分别取得了94.33%,91.60%,97.72%,98.66%的准确率。本文中的算法能较完整地分割出白细胞,为后续分类研究奠定了基础。     

基于路面约束的行人检测感兴趣区域提取

针对行人检测存在识别精度不高,实时性较差等问题进行相关研究.分析了基于多尺度滑动窗口法提取行人检测窗口的缺点,为解决行人检测中检测窗口数量过多的问题,提出在图像分割和路面提取的基础上实现对行人检测窗口的提取.先利用FCM聚类算法训练得到分割阈值,其次提取路面区域,根据路面区域筛选可能存在的行人位置,进而提取感兴趣区域,并对相应的感兴趣区域提取HOG特征进行进一步精确分类.实验结果表明,采用基于路面约束的图像分割方法来提取感兴趣区域,有效减少了遍历窗口的数量,从而提高了行人检测速度和检测精度.     

Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging

Intracranial hemorrhage (ICH) detection is the primary task for the patients suffering from neurological disturbances and head injury. This paper presents a segmentation technique that combines the features of fuzzy c-mean (FCM) clustering and region-based active contour method. In the suggested method, the fuzzy membership degree from FCM clustering is first used to initialize the active contour, which propagates for the detection of the desired object. In addition to active contour initialization, the fuzzy clustering is also used to estimate the contour propagation controlling parameters. The level set function as used by active contour in the proposed method does not need re-initialization process; thus, it fastens the convergent speed of the contour propagation. The efficacy of the suggested method is demonstrated on a dataset of 20 brain computed tomography (CT) images suffered with ICH. Experimental results show that the proposed method has advantages in accuracy in comparison with standard region growing method and FCM for the detection of hemorrhage from brain CT images.     

基于内容的敏感图像检测方法研究

随着网络和多媒体技术的发展,互联网中色情图像的传播越来越泛滥,为有效地过滤敏感图像,文章提出一种基于Otsu自适应阈值分割的人体面积比例计算方法。整个检测系统利用人体肤色模型和面部识别模型,并结合面积比例识别算法等图像特征识别技术,实现对网络敏感图像的检测。实验结果表明,该方法具有较高的准确率和较快的实时在线检测速度,具有良好的实用性和应用价值。     

基于多尺度重叠滑动池化的SSD果冻杂质检测方法

提出一种基于SSD的杂质检测方法,用于检测生产线中果冻内部的杂质,并标注出杂质的类型和位置。在预处理阶段,提出滑动图像块分割方法,将整张果冻图像分割成若干图像块,避免杂质占比过小,造成准确率低的现象。使用迁移学习的方法,将神经网络在ImageNet数据库上学习到的特征迁移到果冻数据库中,加快网络收敛速度,同时,在一定程度上避免了过拟合现象。提出多尺度重叠滑动池化(SOSP)方法,取代第五层池化以取得更加鲁棒的特征池化。最后,将一幅图下的所有分割块上的检测结果进行整合,得到整张图像的检测结果。实验结果表明,本文提出的方法有效可行,对多种缺陷平均准确率达到0.7271。相比其他方法,本文的算法更具鲁棒性,可应用到果冻生产线中。      

An efficient deep sclera recognition framework with novel sclera segmentation,vessel extraction and gaze detection

Sclera recognition is a promising ocular biometric modality because of contact-less, gaze-independent image acquisition in visible light. Moreover, it is unaffected even if the subjects are wearing contact lenses in eyes. However, it is a difficult task because several steps are required, each of which must be performed accurately and efficiently. In this work, sclera recognition is performed in the following steps, namely, segmentation of sclera region, extraction of sclera vasculature pattern, detection of gaze direction and finally comparison of two vasculature patterns for matching and recognition. The proposed segmentation model DSeg is based on well-known deep learning model UNet and reduces model complexity by creating a Knowledge Base of sclera and non-sclera colors. DSeg is a lightweight and environment-friendly model, which outperforms UNet in terms of speed, efficiency and accuracy. Two rule-based unsupervised vessel extraction methods require prior sclera segmentation and exhibit competing recognition performance to a supervised deep model for vessel extraction, which does not require prior sclera segmentation. A novel deep recognition model is proposed which compares two vessel structures taking into account their affine-transformation, and produces a single Boolean output to decide whether the structures match or not. The model does not require post logic in the matching process. The model is further improved to detect errors in prediction. We achieve best recognition rates with low false-acceptance-rates for two sets of training and validation, using the publicly available dataset SBVPI and the best achieved AUC score is 0.98.     

一种基于激光视觉的焊缝实时检测技术研究

提出了一种基于激光视觉的焊缝实时检测技术,旨在提高焊缝检测的速度和精度。在实际的焊接过程中,由于大量噪声的干扰,焊接图像的采集一直是一个复杂的过程。 本文首先建立基于激光视觉的检测系统,以获得激光条纹的原始图像。在此基础上,将原始激光条纹图像灰度化,并提出一种改进的快速中值滤波算法,在去除图像中椒盐噪声的同时,缩短了程序运行时间。并通过Otsu阈值分割获得激光条纹的二值图像,提取感兴趣的激光条纹区域。接着结合方向模板法和脊线跟踪法提取激光条纹中心线,最后采用亚像素级角点法提取焊缝的特征点。 实验证明,本文提出的方法有效地克服了焊接环境的影响,不仅缩短了焊缝特征点检测的时间,而且具有较高的检测精度,符合实际焊接要求。     

基于LSDANet的手机芯片屏蔽壳表面缺陷检测方法

为了解决手机芯片屏蔽壳表面白印缺陷微小、尺度各异等因素影响检测快速性和准确性的问题,本文提出一种基于长短连接通路和双注意力网络(long short link and double attention network, LSDANet)的手机芯片屏蔽壳表面缺陷检测方法。首先,通过构建基于编码和解码的语义分割模型和利用长短距离连接通路,提高网络模型对尺度各异缺陷的特征提取能力。其次,分别设计基于通道和空间的注意力机制,增大5—10 pixel尺寸的白印缺陷在空间和通道上的特征权重。最后,融合双注意力机制和长短距离连接通路分割模型,构建LSDANet缺陷检测网络,应用于手机芯片屏蔽壳表面缺陷检测。实验数据表明,LSDANet网络能够达到96.21%的平均像素精度、66.13%的平均交并比和39.03的每秒检测帧数,相比多种语义分割算法均具有更高的检测精度和速度。     

基于图像式传感器的铁路轨距检测系统研究

传感器在铁路安全维护方面应用广泛。为了实现实时在线轨距测量,将激光技术与CCD图像式传感器相结合,建立车载轨距机器视觉检测系统。首先介绍系统的构成与工作原理,并提出基于去噪前置与距离变换算法的快速轨道轮廓中心线提取方法。然后采用强对比度拉伸和指数变换的方法进行图像增强,并结合高斯平滑与动态感兴趣区域对图像进行快速去噪前置处理。最后对图像进行精确阈值分割处理,采用距离变换的方法得到轨道轮廓中心线并定位轨距测量点。结果表明,该系统检测精度满足-1mm~+1mm,图像帧处理速率为14.35m/s。轨距机器视觉检测系统满足实时在线轨距检测对系统鲁棒性、检测速度和精度的要求。     

基于相位一致性改进的活动轮廓分割模型

为了实现甲状腺超声图像中结节组织的快速准确分割,克服图像灰度分布不均匀和边缘模糊对分割结果造成的影响,采用了基于相位一致性改进的活动轮廓分割模型。首先,利用相位一致性边缘检测原理构造一种新的速度函数,不仅弥补了梯度算子边缘检测中由于滤波处理造成边缘损坏的缺陷,而且可以灵活地控制曲线演化速率;然后,将该速度函数乘入到无边缘主动轮廓模型的能量项中,避免了线性组合中的权重分配问题,同时具有全局分割能力。通过理论分析和实验验证,改进模型的相对差异度均小于1%,运行时间均低于对比模型。结果表明,新模型实现了灰度分布不均匀图像的精确分割,同时分割效率也有所提高。     

基于超像素与图卷积神经网络的白细胞分割

白细胞分割是医学图像处理领域的一项富有挑战性的任务,针对目前白细胞分割存在的准确度不高、粘连情况不易分割等问题,将图像的分割转化为区域节点的分类问题,提出基于图卷积神经网络的白细胞分割算法.首先将训练图像经超像素分割得到若干超像素区域,把每个超像素区域作为图的一个节点,并充分利用超像素区域的彩色特征以及空间邻域关系构造稀疏加权图来训练图卷积网络,然后利用训练好的网络对测试图像进行白细胞核、质、背景的三域一次性分类.实验数据表明,本文算法对不同类白细胞均具有较好的分割效果.     

基于Hough变换的倾斜文本图像的检测

在OCR图像扫描输入的过程中,扫描图像经常会出现某种程度的倾斜,这种倾斜会给下一个字符的切割造成困难,影响字符识别的精度。正是出于检测倾斜文本图像角度的目的,提出了一种基于Hough变换的检测图像倾斜度的方法,可以有效地克服几何失真对文字识别系统的影响,为了克服Hough变换计算量大的缺点,该方法采用了提取图像特征点的方法。实验结果表明,该方法能快速准确地测出各类文本图像的倾斜角度,并且具有很好的适应性。     

用于自动识别遥感图像路网信息的改进模糊连接度方法

针对遥感图像中路网信息的自动识别问题,该文将小波模极大值边缘检测方法和模糊连接度方法结合,提出一种改进的模糊连接度方法。采用小波模极大值边缘检测方法进行模糊连接度种子点的自动选择,解决传统模糊连接度理论中种子点难以自动选择的问题。在此基础上,对传统的模糊相似度计算公式进行简化,在保证路网识别准确性的同时,大大减少了计算量。采用来自Quickbird高分辨商业遥感卫星的3组影像进行实验,验证了该文提出的路网识别方法具有较高的准确性和计算速度。