A novel white blood cell segmentation scheme based on feature space clustering

This paper presents a novel white blood cell (WBC) segmentation scheme based on two feature space clustering techniques: scale-space filtering and watershed clustering. In this scheme, nucleus and cytoplasm, the two components of WBC, are extracted, respectively, using different methods. First, a sub image containing WBC is separated from the original cell image. Then, scale-space filtering is used to extract nucleus region from sub image. Later, a watershed clustering in 3-D HSV histogram is processed to extract cytoplasm region. Finally, morphological operations are performed to obtain the entire connective WBC region. Through feature space clustering techniques, this scheme successfully avoids the variety and complexity in image space, and can effectively extract WBC regions from various cell images of peripheral blood smear. Experiments demonstrate that the proposed scheme performs much better than former methods.     

Blood smear analyzer for white blood cell counting: A hybrid microscopic image analyzing technique

Total count and differential count of leukocytes or white blood cells (WBC) in blood samples are very important pathological factors for diagnosing a disease. There are not enough pathological infrastructures in the remote places of India and other developing countries. The objective of this work is to design a system, compatible with telemedicine, for automatic calculation of the total count and differential count of WBC from the blood smear slides. Hemocytometer based WBC counting provides more accurate result than manual counting, but hemocytometer preparation process needs expertise. As this device is targeted for remote places, blood smear technique is adopted to reduce the overhead of the operator. In the proposed system, microscopic images of blood smear sample are processed to highlight the WBC for segmentation. Region segmentation procedure involves background scaling and redundant region elimination from the region set. After segmentation, the more accurate region boundary is restored by using gradient based region growing with neighbourhood influence. Individual regions are separately classified on the basis of shape, size, color and texture features independently using different fuzzy and non-fuzzy techniques. A final decision is taken by combining these classification results, which is a kind of hybridization. A set of rules has been generated for making final classification decision based on outputs from various classifiers. The sensitivity and specificity of the system are found to be 96.4% and 79.6%, respectively on a database of 150 blood smear slides collected from different health centres of Kolkata Municipal Corporation, Kolkata, India.     

Unsupervised segmentation and classification of cervical cell images

The Pap smear test is a manual screening procedure that is used to detect precancerous changes in cervical cells based on color and shape properties of their nuclei and cytoplasms. Automating this procedure is still an open problem due to the complexities of cell structures. In this paper, we propose an unsupervised approach for the segmentation and classification of cervical cells. The segmentation process involves automatic thresholding to separate the cell regions from the background, a multi-scale hierarchical segmentation algorithm to partition these regions based on homogeneity and circularity, and a binary classifier to finalize the separation of nuclei from cytoplasm within the cell regions. Classification is posed as a grouping problem by ranking the cells based on their feature characteristics modeling abnormality degrees. The proposed procedure constructs a tree using hierarchical clustering, and then arranges the cells in a linear order by using an optimal leaf ordering algorithm that maximizes the similarity of adjacent leaves without any requirement for training examples or parameter adjustment. Performance evaluation using two data sets show the effectiveness of the proposed approach in images having inconsistent staining, poor contrast, and overlapping cells.     

基于自监督学习的病理图像层次分割

在苏木精-伊红(HE)染色病理图像中，细胞染色分布的不均匀和各类组织形态的多样性给病理图像的自动分割带来极大挑战。为解决该问题，提出了一种基于自监督学习的病理图像三步层次分割方法，对病理图像中各类组织进行由粗略到精细的全自动逐层分割。首先，根据互信息的计算结果在RGB色彩空间中进行特征选择；其次，采用K-means聚类将图像初步分割为各类组织结构的色彩稳定区域与模糊区域；然后，以色彩稳定区域为训练集采用朴素贝叶斯分类对模糊区域进行进一步分割，得到完整的细胞核、细胞质和胞外间隙这三类组织结构；最后，对细胞核部分进行结合形状和色彩强度的混合分水岭分割得到细胞核间的精确边界，进而量化计算细胞核个数、核占比、核质比等指标。对脑膜瘤HE染色病理图像的分割实验结果表明，所提方法对于染色和细胞形态差异保持较高的鲁棒性，各类组织区域分割误差在5%以内，在细胞核分割精度的对比实验中平均正确率在96%以上，满足临床自动图像分析的要求，其量化结果可以为定量病理分析提供依据。     

基于区域搜索与矩特征分类的文本精确定位

提出一种基于特定颜色分布区域搜索的文本定位方法,利用文字通常呈现为单一的颜色被不同的背景颜色包围的特点,以单一的颜色作为依据,搜索被包围的文本候选区域;然后,在区域合并与分离算法的基础上,利用不变矩特征和支持向量机（SVM）分类器实现候选区域的进一步筛选。与一般基于形状和纹理的方法相比,由于采用了文字颜色的空间分布特征,避开了文本与其他元素的形状和纹理特征交错问题,保证了算法适应性。基于精确区域搜索的不变矩特征提取,降低了分类器的训练难度,使分类器能很好地适应背景和文字尺寸变化以及部分遮挡等复杂情形。实验表明,该方法具有较好的复杂环境适应性和非常高的准确性。     

A novel segmentation algorithm for nucleus in white blood cells based on low-rank representation

White blood cells (WBCs) segmentation is a challenging problem in the study of automated morphological systems, due to both the complex nature of the cells and the uncertainty that is present in video microscopy. This paper investigates how to boost the effects of region-based nucleus segmentation in WBCs by means of optimal thresholding and low-rank representation. The main idea is firstly using optimal thresholding to obtain the possible uniform WBC regions in the input image. After that, a manifold-based low-rank representation technique is employed to infer a unified affinity matrix that implicitly encodes the segmentation of the pixels of possible WBC regions. This is achieved by separating the low-rank affinities from the feature matrix into a pair of sparse and low-rank matrices. The experiments show that the proposed method is possible to produce better segmentation results compared with existing approaches.

     

基于Faster R-CNN的疟疾血涂片检测改进算法

根据WHO发布的报告,每年疟疾的新发病例超过2亿,死亡人数仍居高不下.疟疾血涂片镜检法是疟疾检测的金标准,但由于人工评估所需的步骤繁琐,即使在经验丰富的医师手中,这种诊断方法也很耗时并且容易发生漏检和误检.此外疟原虫细胞形状、密度和颜色的变化以及某些细胞类的不确定性等因素,对疟原虫检测提出了重大挑战.基于深度学习的神经...     

高效的白细胞分割算法

白细胞分割是细胞形态学研究中一个重要、富有挑战性的课题。提出一种基于目标检测的白细胞分割算法。具体地讲,首先根据目标检测方法检测出白细胞,并由白细胞的位置信息得到包含白细胞的子图,然后运用多项式拟合的方法得到子图的灰度直方图的波谷值,再在子图上运用直方图阈值算法分割出细胞核。该算法在分割细胞核的过程中,既可以有效地避免血小板和红细胞等干扰,又能较容易地估计出阈值。对于白细胞的细胞质分割,将白细胞位置信息作为GrabCut算法中人工交互部分,通过迭代法分割出白细胞的细胞质。实验结果表明,该算法能准确地定位白细胞,并根据白细胞的位置信息可以降低白细胞分割的难度,提高其分割的精度和分割效率。特别地,在Cellavision的白细胞图片数据库的实验结果表明,所提的白细胞分割算法对不同类别、不同染色剂和不同拍摄环境下得到的白细胞都能得到较好的分割效果,同时算法又还具有很好的泛化性。     

MayGAN: Mayfly Optimization with Generative Adversarial Network-Based Deep Learning Method to Classify Leukemia Form Blood Smear Images

Leukemia, often called blood cancer, is a disease that primarily affects white blood cells (WBCs), which harms a person’s tissues and plasma. This condition may be fatal when if it is not diagnosed and recognized at an early stage. The physical technique and lab procedures for Leukaemia identification are considered time-consuming. It is crucial to use a quick and unexpected way to identify different forms of Leukaemia. Timely screening of the morphologies of immature cells is essential for reducing the severity of the disease and reducing the number of people who require treatment. Various deep-learning (DL) model-based segmentation and categorization techniques have already been introduced, although they still have certain drawbacks. In order to enhance feature extraction and classification in such a practical way, Mayfly optimization with Generative Adversarial Network (MayGAN) is introduced in this research. Furthermore, Generative Adversarial System (GAS) is integrated with Principal Component Analysis (PCA) in the feature-extracted model to classify the type of blood cancer in the data. The semantic technique and morphological procedures using geometric features are used to segment the cells that makeup Leukaemia. Acute lymphocytic Leukaemia (ALL), acute myelogenous Leukaemia (AML), chronic lymphocytic Leukaemia (CLL), chronic myelogenous Leukaemia (CML), and aberrant White Blood Cancers (WBCs) are all successfully classified by the proposed MayGAN model. The proposed MayGAN identifies the abnormal activity in the WBC, considering the geometric features. Compared with the state-of-the-art methods, the proposed MayGAN achieves 99.8% accuracy, 98.5% precision, 99.7% recall, 97.4% F1-score, and 98.5% Dice similarity coefficient (DSC).     

逐级细化的交通标志识别算法

针对交通标志识别中存在的识别精度和实时应用之间的矛盾,根据中国交通标志的特点,提出一种逐级细化的交通标志识别算法。首先进行粗分类,构建颜色属性-梯度直方图（Color name-histogram of gradient,CN-HOG）描述子表示每类标志的形状和颜色特征,采用线性支持向量机（Support vector machine,SVM）将交通标分为禁令标志、警告标志、指示标志、解除禁令标志和其他标志5大类;然后进行细分类,采用词袋模型中颜色和形状特征早融合的方式将颜色属性（Color name,CN）和尺度不变特征变换（Scale-invariant feature transform,SIFT）描述子相结合、利用高斯核SVM得到交通标志区域的最终类别标记。在公开数据集上的实验表明本文算法在满足实时应用的同时取得了99.15%的识别精度。     

基于局部特征的图像快速分类算法

基于内容的图像快速分类是Web图像实时搜索和过滤的基础。通过分析图像特征分布特点,提出一个基于局部特征的图像快速分类算法。与目前算法相比,该算法仅需对图像的局部区域扫描分析,即可得到其颜色、纹理、形状等特征,并利用Bayesian分类器来实现图像的快速自动分类。相关对比实验证实,该算法能够快速、准确地实现图像分类。     

Combining shape, texture and intensity features for cell nuclei extraction in Pap smear images

In this work, we present an automated method for the detection and boundary determination of cells nuclei in conventional Pap stained cervical smear images. The detection of the candidate nuclei areas is based on a morphological image reconstruction process and the segmentation of the nuclei boundaries is accomplished with the application of the watershed transform in the morphological color gradient image, using the nuclei markers extracted in the detection step. For the elimination of false positive findings, salient features characterizing the shape, the texture and the image intensity are extracted from the candidate nuclei regions and a classification step is performed to determine the true nuclei. We have examined the performance of two unsupervised (K-means, spectral clustering) and a supervised (Support Vector Machines, SVM) classification technique, employing discriminative features which were selected with a feature selection scheme based on the minimal-Redundancy-Maximal-Relevance criterion. The proposed method was evaluated on a data set of 90 Pap smear images containing 10,248 recognized cell nuclei. Comparisons with the segmentation results of a gradient vector flow deformable (GVF) model and a region based active contour model (ACM) are performed, which indicate that the proposed method produces more accurate nuclei boundaries that are closer to the ground truth.     

Latent Space Representational Learning of Deep Features for Acute Lymphoblastic Leukemia Diagnosis

Acute Lymphoblastic Leukemia (ALL) is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow. Early prognosis of ALL is indispensable for the effectual remediation of this disease. Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images, a process which is time-consuming and prone to errors. Therefore, many deep learning-based computer-aided diagnosis (CAD) systems have been established to automatically diagnose ALL. This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images. The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks (CNNs) to identify the existence of ALL in blood smears. An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images. A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set. The latent features are used to perform image classification using Support Vector Machine (SVM) classifier. The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features. Moreover, the classification performance of the system with various sizes of the latent feature set is evaluated. The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.     

Reduced quaternion matrix for color texture classification

As a newly developed singular value decomposition of the reduced quaternion matrix (SVDRQ), the two reduced quaternion unitary matrices can effectively capture the intrinsic geometric structures and smooth contours of color texture image. The projection vector by the two unitary matrices is used as dominant features for color texture classification. In this paper, we proposed new algorithm to implement the computation of the SVDRQ, and then proposed new color texture classification scheme based on SVDRQ, the Euclidean distance is applied as classifier in the proposed scheme. It is demonstrated by the experiments that our proposed scheme significantly improves the color texture classification accuracy in comparison with several conventional texture classification approaches.     

Automated White Blood Cell Disease Recognition Using Lightweight Deep Learning

White blood cells (WBC) are immune system cells, which is why they are also known as immune cells. They protect the human body from a variety of dangerous diseases and outside invaders. The majority of WBCs come from red bone marrow, although some come from other important organs in the body. Because manual diagnosis of blood disorders is difficult, it is necessary to design a computerized technique. Researchers have introduced various automated strategies in recent years, but they still face several obstacles, such as imbalanced datasets, incorrect feature selection, and incorrect deep model selection. We proposed an automated deep learning approach for classifying white blood disorders in this paper. The data augmentation approach is initially used to increase the size of a dataset. Then, a Darknet-53 pre-trained deep learning model is used and fine-tuned according to the nature of the chosen dataset. On the fine-tuned model, transfer learning is used, and features engineering is done on the global average pooling layer. The retrieved characteristics are subsequently improved with a specified number of iterations using a hybrid reformed binary grey wolf optimization technique. Following that, machine learning classifiers are used to classify the selected best features for final classification. The experiment was carried out using a dataset of increased blood diseases imaging and resulted in an improved accuracy of over 99%.     

An efficient fuzzy classifier with feature selection based on fuzzyentropy

This paper presents an efficient fuzzy classifier with the ability of feature selection based on a fuzzy entropy measure. Fuzzy entropy is employed to evaluate the information of pattern distribution in the pattern space. With this information, we can partition the pattern space into nonoverlapping decision regions for pattern classification. Since the decision regions do not overlap, both the complexity and computational load of the classifier are reduced and thus the training time and classification time are extremely short. Although the decision regions are partitioned into nonoverlapping subspaces, we can achieve good classification performance since the decision regions can be correctly determined via our proposed fuzzy entropy measure. In addition, we also investigate the use of fuzzy entropy to select relevant features. The feature selection procedure not only reduces the dimensionality of a problem but also discards noise-corrupted, redundant and unimportant features. Finally, we apply the proposed classifier to the Iris database and Wisconsin breast cancer database to evaluate the classification performance. Both of the results show that the proposed classifier can work well for the pattern classification application.     

Face localization using fuzzy classifier with wavelet-localized focus color features and shape features

This paper proposes a new fuzzy classifier (FC)-based face localization approach. The FC used is a self-organizing TS-type fuzzy network with support vector learning (SOTFN-SV). The SOTFN-SV learns consequent parameters using a linear support vector machine to improve generalization ability. The FC is first applied to segment human skin pixels in scaled hue and saturation (hS) color space, after which connected skin-color regions are regarded as face candidates. The FC is then applied to detect and localize faces from the candidates. The proposed FC-based face localization approach uses shape and wavelet-localized focus color features. A best fitting ellipse of each face candidate is found to obtain shape features. Focus color features are extracted from four focus regions, including the two eyes, the mouth, and the face skin-color region. To find these focus color regions, the Haar-wavelet transformation is first applied to the face candidates in the YCb color space to localize all possible pairs of eye candidates. The mouth region is then localized according to its geometric relationship with the eyes. The hS color features of the located eyes, mouth, and face skin are extracted. These focus color features, together with shape features, serve as inputs to another FC for final face localization. Comparisons with various classifiers and face detection methods demonstrate the advantage of the FC-based skin color segmentation and face localization method.     

基于集成学习的图像垃圾邮件过滤方法

目前的图像垃圾邮件过滤技术，大都采用国际上通用的垃圾图像数据集作为训练集，与中国国内图像垃圾邮件的图像特点不一致，图像数据缺乏实时更新，且分类器单一，过滤效果难以保证。针对该问题，在建立国内垃圾邮件图像数据库的基础上，首先提取图像的颜色、纹理和形状特征，再经K-NN分类算法优选出HSV颜色直方图特征对不同分类器进行训练、测试和性能比较，提出将基于粗糙集的K-NN算法、Naive Bayes算法和SVM算法构成的3种基分类器相结合，并基于串行迭代提升的方法形成集成学习的强分类器。该方法可以实现对国内图像垃圾邮件的有效过滤，使图像垃圾邮件过滤的准确率和召回率同时得到提升，分别为97.3%和96.1%，误判率降低到了2.7%。     

基于局部形态和彩色特征的烧结状态识别

提出了一种基于局部形态和彩色特征的回转窑烧结状态识别方法。使用SIFT描述回转窑图像的局部形态特征,将彩色的回转窑图像的三个分量都转化为八个等级,用局部三维直方图来描述局部的颜色和亮度特征,将两种特征融合得到局部形态和彩色特征。使用词袋（Bag-of-Words）模型表示图像并利用神经网络分类器实现对烧结状态的识别。实验结果表明,基于局部形态和彩色特征的识别方法能够获得较高的识别精度。     

基于卷积神经网络与集成学习的交通标志识别

为提高复杂情况（如遮挡、透视畸变等）下交通标志识别的精度,提出一种有效的基于卷积神经网络(Convolutional Neural Network, CNN)与集成学习的交通标志识别方法。首先通过融合颜色分割、形态学处理、形状检测等多种方法分割出交通标志,然后利用卷积神经网络对其特征进行提取并分别采用支持向量机(Support Vector Machine, SVM)和Softmax多类分类器对其进行识别,最后将2种分类结果进行集成作为最终的识别结果。实验结果表明,本文算法可有效提高复杂情况下交通标志识别精度,整体上具有较高的性能。