Automated inspection of engineering ceramic grinding surface damage based on image recognition

As the engineering ceramic ground workpieces usually contain machining damage such as breaks and cracks, the traditional test methods cannot accurately reflect the real surface. Therefore, this paper describes an automatic damage detection system of the engineering ceramic machined surface using image processing techniques, pattern recognition, and machine vision. First, it has great influence on the exact identification of surface damage if engineering ceramic machined surfaces contain grinding texture, so Fourier transform is skillfully adopted to remove grinding texture. Second, through image noise reduction, contrast enhancement, and image segmentation, an optimal combination of image preprocessing is obtained. Then, by comprehensive extraction of surface feature parameters, decision tree classifier based on the C4.5 algorithm is built according to shape features and texture features. Finally, the paper achieves automatic extraction and classification of engineering ceramic grinding surface damage, and the recognition accuracy of breakage reaches over 93 %. Experimental results show that this method is effective in defect detection of the engineering ceramic surface, and it also can provide some analytical basis for the post-function hierarchy partition of engineering ceramic workpieces.     

Differentiating the extent of cartilage repair in rabbit ears using nonlinear optical microscopy

Nonlinear optical microscopy (NLOM) was used as a noninvasive and label‐free tool to detect and quantify the extent of the cartilage recovery. Two cartilage injury models were established in the outer ears of rabbits that created a different extent of cartilage recovery based on the presence or absence of the perichondrium. High‐resolution NLOM images were used to measure cartilage repair, specifically through spectral analysis and image texture. In contrast to a wound lacking a perichondrium, wounds with intact perichondria demonstrated significantly larger TPEF signals from cells and matrix, coarser texture indicating the more deposition of type I collagen. Spectral analysis of cells and matrix can reveal the matrix properties and cell growth. In addition, texture analysis of NLOM images showed significant differences in the distribution of cells and matrix of repaired tissues with or without perichondrium. Specifically, the decay length of autocorrelation coefficient based on TPEF images is 11.2 ± 1.1 in Wound 2 (with perichondrium) and 7.5 ± 2.0 in Wound 1 (without perichondrium), indicating coarser image texture and faster growth of cells in repaired tissues with perichondrium (p < 0.05). Moreover, the decay length of autocorrelation coefficient based on collagen SHG images also showed significant difference between Wound 2 and 1 (16.2 ± 1.2 vs. 12.2 ± 2.1, p < 0.05), indicating coarser image texture and faster deposition of collagen in repaired tissues with perichondrium (Wound 2). These findings suggest that NLOM is an ideal tool for studying cartilage repair, with potential applications in clinical medicine. NLOM can capture macromolecular details and distinguish between different extents of cartilage repair without the need for labelling agents.     

Feature enhancement framework for brain tumor segmentation and classification

Automatic medical image analysis is one of the key tasks being used by the medical community for disease diagnosis and treatment planning. Statistical methods are the major algorithms used and consist of few steps including preprocessing, feature extraction, segmentation, and classification. Performance of such statistical methods is an important factor for their successful adaptation. The results of these algorithms depend on the quality of images fed to the processing pipeline: better the images, higher the results. Preprocessing is the pipeline phase that attempts to improve the quality of images before applying the chosen statistical method. In this work, popular preprocessing techniques are investigated from different perspectives where these preprocessing techniques are grouped into three main categories: noise removal, contrast enhancement, and edge detection. All possible combinations of these techniques are formed and applied on different image sets which are then passed to a predefined pipeline of feature extraction, segmentation, and classification. Classification results are calculated using three different measures: accuracy, sensitivity, and specificity while segmentation results are calculated using dice similarity score. Statistics of five high scoring combinations are reported for each data set. Experimental results show that application of proper preprocessing techniques could improve the classification and segmentation results to a greater extent. However, the combinations of these techniques depend on the characteristics and type of data set used.     

一种基于小波理论的铁谱图像反锐化掩模增强法

介绍了当前常用的图像增强技术,结合铁谱图像预处理研究了基于小波域的反锐化掩模法在图像增强中的运用,并给出了具体算法。实验结果表明,基于小波分析的图像反锐化掩模增强算法能够在控制噪声的同时有效地突出图像细节,改善图像质量。小波变换使得原始图像中不同分辨率的细节特征随尺度的不同而分离开来,避免了传统算法中通过不断调整滤波器窗口大小来选择增强效果的繁琐工作;运用不同尺度下的小波分量分别进行增强,原始图像中无论较粗还是较细的边缘都能同时得到增强,从而既能有效地检测出边缘又能突出图像的表面纹理细节。     

Semi-automated imaging system to quantitate estrogen and progesterone receptor immunoreactivity in human breast cancer

A semi‐automated imaging system is described to quantitate estrogen and progesterone receptor immunoreactivity in human breast cancer. The system works for any conventional method of image acquisition using microscopic slides that have been processed for immunohistochemical analysis of the estrogen receptor and progesterone receptor. Estrogen receptor and progesterone receptor immunohistochemical staining produce colorimetric differences in nuclear staining that conventionally have been interpreted manually by pathologists and expressed as percentage of positive tumoral nuclei. The estrogen receptor and progesterone receptor status of human breast cancer represent important prognostic and predictive markers of human breast cancer that dictate therapeutic decisions but their subjective interpretation result in interobserver, intraobserver and fatigue variability. Subjective measurements are traditionally limited to a determination of percentage of tumoral nuclei that show positive immunoreactivity. To address these limitations, imaging algorithms utilizing both colorimetric (RGB) as well as intensity (gray scale) determinations were used to analyze pixels of the acquired image. Image acquisition utilized either scanner or microscope with attached digital or analogue camera capable of producing images with a resolution of 20 pixels /10 μ. Areas of each image were screened and the area of interest richest in tumour cells manually selected for image processing. Images were processed initially by JPG conversion of SVS scanned virtual slides or direct JPG photomicrograph capture. Following image acquisition, images were screened for quality, enhanced and processed. The algorithm‐based values for estrogen receptor and progesterone receptor percentage nuclear positivity both strongly correlated with the subjective measurements (intraclass correlation: 0.77; 95% confidence interval: 0.59, 0.95) yet exhibited no interobserver, intraobserver or fatigue variability. In addition the algorithms provided measurements of nuclear estrogen receptor and progesterone receptor staining intensity (mean, mode and median staining intensity of positive staining nuclei), parameters that subjective review could not assess. Other semi‐automated image analysis systems have been used to measure estrogen receptor and progesterone receptor immunoreactivity but these either have required proprietary hardware or have been based on luminosity differences alone. By contrast our algorithms were independent of proprietary hardware and were based on not just luminosity and colour but also many other imaging features including epithelial pattern recognition and nuclear morphology. These features provide a more accurate, versatile and robust imaging analysis platform that can be fully automated in the near future. Because of all these properties, our semi‐automated imaging system ‘adds value’ as a means of measuring these important nuclear biomarkers of human breast cancer.     

Scanning electron microscopy combined with image processing technique: Microstructure and texture analysis of legumes and vegetables for instant meal

Development and innovation of new technologies are necessary especially in food quality; due that most instrumental technique for measuring quality properties involves a considerable amount of manual work. Image analysis is a technique that allows to provide objective evaluations from digitalized images that can estimate quality parameters for consumer's acceptance. The aim of the present research was to study the effect of freeze drying on the microstructure and texture of legume and vegetables using scanning electron microscopy at different magnifications' combined with image analysis. Cooked and cooked freeze dried rehydrated legumes and vegetables were analyzed individually by scanning electron microscopy at different magnifications' (250, 500, and 1000×).Texture properties were analyzed by texture analyzer and image analysis. Significant differences (P < 0.05) were obtained for image and instrumental texture parameters. A linear trend with a linear correlation was applied for instrumental and image features. Results showed that image features calculated from Grey level co‐occurrence matrix at 1,000× had high correlations with instrumental features. In rice, homogeneity and contrast can be applied to evaluate texture parameters gumminess and adhesiviness; Lentils: contrast, correlation, energy, homogeneity, and entropy for hardness, adhesiviness, gumminess, and chewiness; Potato and carrots: contrast, energy, homogeneity and entropy for adhesiviness, chewiness, hardness, cohesiviness, and resilence. Results revealed that combing scanning electron microscopy with image analysis can be a useful tool to analyze quality parameters in legumes and vegetables. Microsc. Res. Tech. 79:267–275, 2016. © 2016 Wiley Periodicals, Inc.     

基于纹理分布特征的虹膜识别算法

二维小波变换方向性差,不能从方向和频率同时描述虹膜纹理.基于此,分析了归一化虹膜纹理的分布特点,提出了基于纹理分布特征的虹膜识别算法.对原始人眼图像进行虹膜定位等预处理操作,得到归一化的虹膜纹理图像;对归一化虹膜图像进行了二维小波多尺度变换,结合虹膜纹理分布特点,选择小波分解水平通道;依据点能量贡献度,消除伪特征点并进行了点能量编码;计算了不同虹膜编码间海明距离,以其为依据进行分类.在给定距离阈值为0.25的前提下,可以达到99.91%的正确识别率.实验证明该算法是有效、可行的,并具有较高的识别率,识别速度也很快.     

Lungs nodule detection framework from computed tomography images using support vector machine

The emergence of cloud infrastructure has the potential to provide significant benefits in a variety of areas in the medical imaging field. The driving force behind the extensive use of cloud infrastructure for medical image processing is the exponential increase in the size of computed tomography (CT) and magnetic resonance imaging (MRI) data. The size of a single CT/MRI image has increased manifold since the inception of these imagery techniques. This demand for the introduction of effective and efficient frameworks for extracting relevant and most suitable information (features) from these sizeable images. As early detection of lungs cancer can significantly increase the chances of survival of a lung scanner patient, an effective and efficient nodule detection system can play a vital role. In this article, we have proposed a novel classification framework for lungs nodule classification with less false positive rates (FPRs), high accuracy, sensitivity rate, less computationally expensive and uses a small set of features while preserving edge and texture information. The proposed framework comprises multiple phases that include image contrast enhancement, segmentation, feature extraction, followed by an employment of these features for training and testing of a selected classifier. Image preprocessing and feature selection being the primary steps—playing their vital role in achieving improved classification accuracy. We have empirically tested the efficacy of our technique by utilizing the well‐known Lungs Image Consortium Database dataset. The results prove that the technique is highly effective for reducing FPRs with an impressive sensitivity rate of 97.45%.     

多图像融合Retinex用于弱光图像增强

为解决弱光图像增强过程中对比度增强和自然度保持问题,本文提出一种基于Retinex的多图像自适应加权最小二乘滤波算法。首先,在图像的每个像素的R,G,B三通道中找到最大亮度值作为该像素的初始照明估计,根据Retinex理论生成反射图像,并通过形态学闭合方式调整反射图;接着,在初始照明图基础上,通过Gamma变换和双对数变换方法分别生成全局对比度增强图和局部自然度保持照明图;随后,设计一种自适应加权最小二乘滤波融合策略将三幅照明图融合成最终照明估计图;最后合成上述的最终照明图和调整反射图以获得弱光增强后的图像。实验结果表明,本文所提出算法的亮度顺序差(LOE)及盲图像质量评价(NIQE)值更低,可同时降低到4.12和3.25,较其他方法表现出更好的增强效果。证明了本文算法能有效地增强弱光图像对比度,同时保持图像自然度。     

利用MATLAB实现遥感图像增强

图像增强是数字图像的预处理。本文采用直方图增强、对比度增强、平滑滤波方法,利用MATLAB软件实现对了遥感图像增强处理,并给出了实验结果图像。结果表明,对利用MATLAB实现遥感图像增强,能够改善图像的质量。     

面向机柜表面缺陷检测的不均匀光照和低亮度图像增强方法

光照条件是大尺寸机柜表面缺陷检测的重要影响因素。当光照分布不均匀或光照强度不足时,采集得到的机柜表面图像质量低,造成缺陷检测误差。为此,提出一种融合卡通纹理分解和最优双曲正切曲线的图像增强方法。首先,采用导向滤波将机柜表面图像分解为卡通图和纹理图,利用高斯尺度空间理论建立光照模型,实现不均匀光照去除;其次,研究图像的双曲正切曲线性质,通过图像加权拉伸实现低亮度图像增强;最后,采用对比度、亮度和灰度方差乘积对图像增强效果进行评价,同时对增强前和增强后的图像进行缺陷检测,进行对比分析验证。实验结果表明,该方法能实现光照不均且低亮度的机柜表面图像增强,机柜表面缺陷检测的准确率显著提升,召回率提高了29%,F值提高了21%。     

基于机器视觉的浮空器囊体材料表面缺陷检测系统

在复杂气象环境下,浮空器囊体作为整机系统的直接受压面,其表面必须平整光滑,无褶皱损伤,以将其与空气的摩擦力降至最小。文中基于机器视觉对浮空器囊体材料表面缺陷检测进行系统设计。首先为了降低背景灰度变化对缺陷检测的影响,研究了一种同时具有噪声滤除与图像增强功能的预处理算法;其次利用图像二值化和中值滤波技术实现特征图像的预处理,并结合纹理特征提取技术（基于灰度共生矩阵）对囊体材料表面不同缺陷图像的特征参数进行仿真提取,通过分析不同特征参数,判断囊体材料的表面缺陷类型。该系统对采集到的200个囊体材料表面缺陷样本的分析表明,所用方法能识别浮空器囊体材料93.6%的表面缺陷,识别内容包括缺陷的类型、位置、大小等,并根据缺陷的类型加盖不同的标记。该系统具有较高的识别率和准确率,可对浮空器囊体材料表面缺陷进行快速检测。     

多尺度区域生长与去粘连模型的乳腺细胞分割

乳腺癌已经成为女性最常见的恶性肿瘤,组织切片显微图像的病理分析是诊断的主要手段,细胞的准确分割是病理分析的重要环节。该文提出了一种新的乳腺细胞显微图像的自动分割算法:首先结合小波分解和多尺度区域生长算法分离细胞和背景,实现对细胞的精确定位;然后采用改进的数学形态学对粘连细胞进行一次细分割;接着再采用基于曲率尺度空间(CSS)的角点检测分割算法对粘连细胞进行二次细分割;两次细分割方法构成了一个双策略去粘连模型,保证了去粘连的准确性和鲁棒性。将算法应用到22幅乳腺细胞显微图像上,可以对不同类型的乳腺细胞图像进行全自动分割,有较高的分割灵敏度(0.944±0.024)和特异度(0.937±0.038),且具有较好的普适性。     

An investigation of segmentation methods and texture analysis applied to tomographic images of human vertebral cancellous bone

The goal of this study is to determine architectural and textural parameters on computed tomographic (CT) images, allowing us to explain the mechanical compressive properties of bone. Although the resolution (150 μm) is of the same order of magnitude as the trabecular thickness, this method enables the possibility of perfecting an in vivo peripheral CT system with an acceptable radiation dose for the patient. This study was performed on L2 vertebrae cancellous bone specimens taken after necropsy in 22 subjects aged 47–95 years (mean: 79 years). The segmentation process is a crucial point in the determination of accurate architectural parameters. In this paper the use of two different segmentation methods is investigated, based on an edge enhancement and a region growing approach. The images are compared and the architectural parameters extracted from the images segmented by both methods lead to a quantitative evaluation. The parameters are found to be globally robust towards the segmentation process, although some of them are much more sensitive to the approach used. Highly significant correlations ( P  < 0.0005) have been obtained between the two segmentation methods for all the parameters, with ρ ranging from 0.70 to 0.93. In order to improve the assessment of bone architecture, texture analysis (run length method) was investigated. New features are obtained from an image reduced to 16 grey-levels. Textural parameters in addition to architectural parameters in a multivariate regression model increase significantly ( P  = 0.01) the prediction of the maximum compressive strength (variation of r ² from 0.75 up to 0.89).     

基于火焰彩色纹理特征的转炉炼钢碳含量预测

连续实时测量碳含量是转炉终点钢水碳含量控制的关键.针对转炉终点炉口火焰图像相似性高导致难以提取具有较强区分性火焰图像特征的问题,提出一种图像彩色纹理特征提取方法——四元数方向统计量(QDS)算法.首先,利用四元数乘法特性对火焰图像进行旋转操作得到火焰图像的四元数旋转图谱;其次,以旋转图谱指定方向和距离上像素差值的四元数...     

结合噪声估计的NRLBP铆钉表面缺陷检测

针对铆钉表面缺陷纹理形态复杂多变,传统纹理特征提取方法难以获取准确纹理信息、铆钉缺陷识别率较低的问题,提出一种自适应阈值抗噪LBP的铆钉表面缺陷检测算法AT_NRLBP。首先,将铆钉图像均匀分块后提取铆钉子块;然后,基于PCA分解铆钉子块的协方差矩阵,估计子块图像的噪声水平。根据图像噪声强度计算NRLBP阈值,编码铆钉子块得到NRLBP纹理特征。最后,训练SVM单分类器分类铆钉子块,检测并标记出缺陷子块。实验结果表明,这里算法能有效地检测出铆钉表面缺陷,误检率明显降低;与其他纹理分类算法相比,这里算法在KTH-TIPS数据集上的分类准确率较高。     

Evaluating image reconstruction methods in improving effective parameters on image quality in IRI-microPET

We intend to improve the image reconstruction for RMS contrast, spatial resolution and signal-to-noise (SNR) parameters for the animal positron emission tomograph IRI—microPET (IRI-Islamic Republic of Iran), designed and built at the Gamma scan laboratory of nuclear science and technology research institute. Acquired images quality from this system depends on different algorithms for image reconstruction in addition to its design and construction. In this paper, system features and tomography method are considered, firstly. Then, image reconstruction algorithms (MLEM, SART, and FBP) were performed on sinogarm. Acquired images quality from these reconstructed algorithms was compared with RMS contrast, spatial resolution and SNR characteristics. Also, reconstructed time and speed of process for three algorithms was considered. According to results, obtained RMS contrast, spatial resolution and signal to noise ratio (SNR) from reconstructed images with MLEM algorithm shows superiority of MLEM algorithm against the SART and FBP algorithms but its computation time is high. Thus, SART algorithm can be suitable replacement for MLEM algorithm.     

Enhancing microscopy images of minerals through morphological center operator‐based feature extraction

To well enhance the mineral image and image details obtained by microscopes, an effective mineral image enhancement algorithm through feature extraction using the morphological center operator is proposed in this work. First, mineral image feature extraction based on the morphological center operator is proposed and discussed. Second, the multiscale extension of the mineral image feature extraction is given by using the multiscale structuring elements. Third, the important mineral image features at multiscales of image are extracted and used to construct the final mineral features for mineral image enhancement. Finally, the original mineral image is well enhanced through importing the extracted final mineral image features into the original mineral image. Experimental results on different types of microscopy images of minerals verified the effective performance of the proposed algorithm for microscopy mineral image enhancement. Microsc. Res. Tech., 2013. © 2012 Wiley Periodicals, Inc.     

Extrinsic parameter's adjustment and potential implications in Plasmodium falciparum malaria diagnosis

Malaria is a major public health concern, affecting over 3.2 billion people in 91 countries. The advent of digital microscopy and Machine learning with the aim of automating Plasmodium falciparum diagnosis extensively depends on the extracted image features. The color of the cells, plasma, and stained artifacts influence the topological, geometrical, and statistical parameters being used to extract image features. During microscopic image acquisition, custom adjustments to the condenser and color temperature controls often have an influence on the extracted statistical features. But, our human visual system sub-consciously adjusts the color and retains the originality in a different lighting environment. Despite the use of appropriate image preprocessing, findings from the literature indicate that statistical feature variations exist, allowing the risk of P. falciparum misinterpretation. In order to eliminate this pervasive variation, the current work focuses on preprocessing the extracted statistical features rather than the prepossessing of the source image. It begins with the augmentation of series images for a microscopic field by inducing illumination variations during the microscopic image acquisition stage. A set of such image series is analyzed using a Nonlinear Regression Model to generalize the relationship between microscopic images acquired with variable ambient brightness and a specific feature. The projection point of the centroid feature onto the brightness parameter is identified in the model and it is denoted as the optimum brightness factor (OBF). Using the model, the feature correction factor (CF) is calculated from the rate of change of feature values over the interval OBF, and the brightness of the test image is processed. The present work has investigated OBF for selected image textural features, namely Contrast, Homogeneity, Entropy, Energy, and Correlation individually from its co-occurrence matrices. For performance analysis, the best state-of-the-art method uses selected texture as a subset feature to evaluate the effectiveness of P. falciparum malaria classification. Then, the impact of proposed feature processing is evaluated on 274 blood smear images with and without Feature Correction (FC). As a result, the “p” value is less than .05, which leads to the result that it is highly significant and the classification accuracy and F-score of P. falciparum malaria are increased.