基于二维对称Tsallis交叉熵的小目标图像阈值分割

现有的阈值分割方法应用于目标与背景面积相差悬殊的小目标图像时,几乎都失效.为此,提出了基于对称Tsallis交叉熵及背景与目标面积差的小目标图像阈值分割方法.对称Tsallis交叉熵准则能确保准确分割时目标和背景内部的灰度均匀,而背景与目标面积差可抑制均等分割的趋势,二者综合构成了更为合理的阈值选取准则函数.首先导出了一维阈值选取公式;然后经推广得到基于二维斜分对称Tsallis交叉熵及背景与目标面积差的阈值选取公式,给出了其快速递推算法及相应的简化方法.大量实验结果表明:与目前性能较优越的二维斜分Otsu、最大熵、非对称交叉熵阈值分割方法相比,所提出的方法在小目标图像分割效果上具有极为明显的优势.     

基于二维直方图斜分的最小类内方差阈值分割

本文提出一种新的二维直方图区域斜分方法,导出了基于二维直方图区域斜分的最小类内方差阈值分割快速迭代算法,在实验结果和分析中给出了分割结果和运行时间,并与基于二维直方图直分的Otsu原始算法及其他三种改进算法进行了比较.结果表明本文提出的二维直方图区域斜分方法可以运用于几乎所有的基于二维直方图的阈值分割,使分割后的图像内部区域均匀,边界形状准确,更有稳健的抗噪性.基于区域斜分的最小类内方差阈值分割快速迭代算法的运行时间与二维Otsu原始算法和文献[12]中的改进算法相比减少了4个数量级,约为区域直分Otsu快速递推算法的1/4,不到文献[11]中快速算法的4%.     

基于Otsu准则和直线截距直方图的阈值分割

对二维Otsu法中类间离散度测度进行了分析,发现按该算法对被噪声污染图像的二维直方图进行划分时,所得两类的类内均值点容易远离主对角线,因而抗噪声能力不足。针对以上情况,本文提出了一种新算法,该算法基于二维直方图中直线阈值分割的思想,利用像素点的二维信息直接建立阈值直线的截距直方图;然后应用Otsu准则对该一维直方图求解最佳截距阈值,并应用该阈值和二维信息完成图像分割。对提出的算法与传统二维Otsu法进行了比较和分析,结果表明:提出的算法可以有效避免传统算法在抗噪方面的缺陷,当实验图像的噪声方差大于0.003且逐渐增加时,提出的算法抗噪表现稳健;另外,提出的算法计算阈值的速度比基于二维Otsu法的直分法和直线阈值法快2个数量级以上,占用内存空间更少。因而提出的算法是一种抗噪稳健且快速有效的阈值分割算法,更适于实时应用。     

基于萤火虫算法的二维熵多阈值快速图像分割

提出了基于萤火虫算法的二维熵多阈值快速图像分割方法以改善分割复杂图像和多目标图像时存在计算量大、计算时间长的问题。首先,分析了二维熵阈值分割原理,将二维熵单阈值分割扩展到二维熵多阈值分割。然后,引入萤火虫算法的思想,研究了萤火虫算法的仿生原理和寻优过程;提出了基于萤火虫算法的二维熵多阈值快速图像分割方法。最后,使用该方法对典型图像进行阈值分割实验,并与二维熵穷举分割法、粒子群算法(PSO)二维熵多阈值分割法进行比较。实验结果表明:该方法在单阈值分割、双阈值分割和三阈值分割时分别比二维熵穷举分割法快3.91倍,1040.32倍和8128.85倍;另外,在阈值选取的准确性和计算时间方面均优于PSO二维熵多阈值分割法。结果显示,基于萤火虫算法的二维熵多阈值快速图像分割方法能快速有效地解决复杂图像和多目标图像的分割问题。     

基于最小Tsallis交叉熵的阈值图像分割方法

利用Tsallis熵的非广延性(nonextensivity),本文提出了一种最小Tsallis交叉熵阈值分割方法.该方法通过引入一个参数q.在阈值的选择过程中不仅考虑了目标和背景之间的信息昔差异,而且考虑了目标和背景之间的相互关系,克服了传统最小交叉熵忽略目标和背景之间的相互关系所导致的阈值选择不恰当的缺点.实验结果表明,通过选择合适的参数q,所提出方法的分割效果明显优于传统的最小交叉熵阈值法.     

基于斜分倒数交叉熵和蜂群优化的火焰图像阈值选取

提出了基于斜分倒数交叉熵和蜂群优化的火焰图像阈值选取方法以便更为准确地分割火焰图像。以最小倒数交叉熵作为阈值选取准则,解决了Shannon熵定义中存在的无意义值问题。同时,以二维直方图斜分方式更加准确地划分目标和背景,提高了算法抗噪性能,且使需要选取的阈值个数由两个变为一个,减少了算法运行时间。此外,采用蜂群优化算法加速对最佳阈值的搜索,使速度提升了约80%~140%,进一步提高了算法的实时性。最后,针对火焰图像进行了大量实验,并与二维斜分最大Shannon熵法、基于混沌小生境粒子群优化(NCPSO)的二维斜分最大倒数熵法进行了比较。结果表明,提出的方法在分割效果上优势明显,且抗噪性能更好,是一种实时有效的火焰图像分割方法。     

基于直方图估计和形状分析的沥青路面裂缝识别算法

提出了一种基于直方图估计和形状分析的沥青路面裂缝识别算法,该算法首先将1024×1024像素大小的路面裂缝图像分为256个64×64像素大小的子块,然后采用直方图估计的方法获得每个子块图像原始直方图的混合高斯拟合函数,两个高斯函数的交叉点即是每个子块图像的最优分割阈值。利用该阈值对整幅图像进行二值化后,在两种尺度条件下采用形状分析方法对子块二值图像进行快速分类和"野点"删除,最终实现了裂缝区域的精确定位。试验结果表明:本文提出的阈值分割方法应用于裂缝图像分割,其性能要优于极小误差法、Ostu阈值法、最大熵法等经典算法;采用形状分析对分割后二值化图像进行后续处理,可实现裂缝区域的快速、准确定位。     

低对比度图像中改进的二维熵阈值分割法

为了实现对低对比度图像中目标的识别和提取,采用二维熵值理论,重新定义了二维直方图坐标的含义,利用二维最大熵作为判定准则,对图像进行阈值切割.利用低对比度图像的特点,采取了压缩循环边界条件方法并结合递推加速算法,对比传统的阈值切割方法,取得了良好的分割效果,同时也提高了原始二维最大熵的计算效率,增强了低对比度下图像目标识别率,有良好的应用前景.     

基于Hessian矩阵和熵的CT序列图像裂缝分割方法

工业CT序列图像的各向不同性和伪影会影响裂缝分割精确度和准确度,因此提出一种基于Hessian矩阵和熵的各向不同性工业CT序列图像裂缝自动分割方法。首先,用基于Hessian矩阵的多尺度线状滤波增强裂缝区域,抑制非线状区域;然后,建立一种新的二维直方图,获取滤波之后层内和层间的信息;再根据直方图的最大类熵确定阈值区间,最终得到裂缝的二值化分割结果。实验表明,所提方法不仅能够满足实际工业CT序列图像裂缝分割中精确、自动的分割要求,而且相较其他4种已有方法,能够得到更完整、更准确的分割结果。     

阈值分解下的冷轧极薄带钢表面缺陷分割

为分割具有低对比度和噪声复杂的冷轧极薄带钢缺陷,在二维Otsu分割算法的基础上进行了改进。为了避免在一个很大的二维空间上搜索阈值,分解二维Otsu分割算法的二维直方图,分别在图像像素灰度直方图和像素邻域灰度直方图上进行阈值求解,并将获得的阈值作为最佳分割阈值。为改善分解过程中忽略的边缘和噪声影响,将平衡因子加入到像素邻域灰度分割阈值求解中。最后通过大量实验对二维Otsu分割算法、量子粒子群双阈值分割算法和改进分割算法的分割结果进行对比分析。实验表明,该算法能够快速高效地分割出冷轧极薄带钢表面的各种缺陷。     

图像阈值分割的Fisher准则函数法

针对图像分割中的阈值选取问题，通过引入模式识别理论中的Fisher评价函数作为图像分割的准则函数，提出了基于Fisher评价函数法的图像分割新技术。该方法利用图像直方图计算各灰度级下的Fisher评价函数值，其最大值即对应于最佳分割闲值。对该方法进行了详尽的图像分割实验，并与著名的Otsu法、最大熵法、最小误差准则法进行了详细比较，结果表明该方法具有分割性能稳定、计算速度快以及受目标大小影响小等优点，是一种实用有效的图像阈值分割新方法。     

改进的遗传算法在实时图像分割中的应用

为了自动确定图像分割的最佳阈值,提出了一种改进的自适应遗传算法,并利用该算法对二维Fisher准则图像分割评价函数进行全局优化提高分割阈值的求解速度,快速得到最佳分割阈值。该算法能够根据个体适应度大小和群体的分散程度自动调整遗传控制参数,从而能够在保持群体多样性的同时加快收敛速度,克服了基本遗传算法的收敛性差、易早熟问题。采用TI公司的DSP芯片TMS320VC5416,结合FPGA,搭建了多目标实时测量平台,并利用本文算法对图像阈值快速求解,实现了多目标的实时测量计算。实验结果表明,该算法具有良好的收敛速度和稳定性,阈值计算时间比二维Fisher准则法缩短了18ms(约63%左右);阈值范围稳定在3个像素以内,能够满足实时多目标测量要求。     

基于线性插值的图像分块分割算法

图像分割是图像处理中的一个重要问题,全局阈值法和局部阈值法是图像分割中广泛采用的两类方法。全局阈值法效率高,但是对局部信息不敏感;局部阈值法对局部信息保存较好,但是计算效率不高。针对这一问题,该文提出一种基于分块的图像分割算法。首先将图像分块,然后,每块内采用最大类间方差法计算阈值,最后,块与块之间采用线性插值的方式平滑分割图像。实验表明,该文提出的算法和全局阈值法相比能较好地保存局部信息,和局部阈值法相比有更高的运行效率,在实际中推荐使用。     

A method to compensate for light attenuation with depth in three-dimensional DNA image cytometry using a confocal scanning laser microscope

A method to compensate for attenuation of detected light with increased depth of the collected optical section, and its application in three-dimensional (3-D) DNA image cytometry is described. The method is based on studying the stack of 2-D histograms that can be formed from each consecutive pair of sections in a stack of optical serial sections. An attenuation factor is calculated interactively and a new compensated section series is computed. Formalin-fixed paraffin-embedded rat tissue was stained with propidium iodide. Each cell nucleus is extracted by thresholding and its total intensity is calculated. The coefficient of variation (CV) of the total intensity of all cells in each stack is computed. For comparison the CV of the same cells is computed in the uncompensated stacks. This study shows a significantly lower CV for the compensated data, thus contributing to the accuracy of DNA quantification in 3-D DNA image cytometry.     

Automatic thresholding of three-dimensional microvascular structures from confocal microscopy images

We have combined confocal microscopy, image processing, and optimization techniques to obtain automated, accurate volumetric measurements of microvasculature. Initially, we made tissue phantoms containing 15-μm FocalCheck™ microspheres suspended in type I collagen. Using these phantoms we obtained a stack of confocal images and examined the accuracy of various thresholding schemes. Thresholding algorithms from the literature that utilize a unimodal histogram, a bimodal histogram, or an intensity and edge-based algorithm all significantly overestimated the volume of foreground structures in the image stack. Instead, we developed a heuristic technique to automatically determine good-quality threshold values based on the depth, intensity, and (optionally) gradient of each voxel. This method analyzed intensity and gradient threshold methods for each individual image stack, taking into account the intensity attenuation that is seen in deeper images of the stack. Finally, we generated a microvascular construct comprised of rat fat microvessel fragments embedded in collagen I gels and obtained stacks of confocal images. Using our new thresholding scheme we were able to obtain automatic volume measurements of growing microvessel fragments.     

Exudates segmentation using inverse surface adaptive thresholding

This paper presents a new approach to detect exudates and optic disc from color fundus images based on inverse surface thresholding. The strategy involves the applications of fuzzy c-means clustering, edge detection, otsu thresholding and inverse surface thresholding. The main advantage of the proposed approach is that it does not depend on manually selected parameters that are normally chosen to suit the tested databases. When applied to two sets of databases the proposed method outperforms methods based on watershed segmentation and morphological reconstruction. The proposed method obtained 98.2 and 90.4 in terms of sensitivity for Standard Diabetic Retinopathy Database – Calibration Level 1 (DIARETDB1) and a local dataset provided by National University Hospital of Malaysia (NUHM), respectively.     

A novel segmentation approach for noisy medical images using Intuitionistic fuzzy divergence with neighbourhood‐based membership function

Medical image segmentation demands higher segmentation accuracy especially when the images are affected by noise. This paper proposes a novel technique to segment medical images efficiently using an intuitionistic fuzzy divergence–based thresholding. A neighbourhood‐based membership function is defined here. The intuitionistic fuzzy divergence–based image thresholding technique using the neighbourhood‐based membership functions yield lesser degradation of segmentation performance in noisy environment. Its ability in handling noisy images has been validated. The algorithm is independent of any parameter selection. Moreover, it provides robustness to both additive and multiplicative noise. The proposed scheme has been applied on three types of medical image datasets in order to establish its novelty and generality. The performance of the proposed algorithm has been compared with other standard algorithms viz. Otsu's method, fuzzy C‐means clustering, and fuzzy divergence–based thresholding with respect to (1) noise‐free images and (2) ground truth images labelled by experts/clinicians. Experiments show that the proposed methodology is effective, more accurate and efficient for segmenting noisy images.     

Microscopic melanoma detection and classification: A framework of pixel‐based fusion and multilevel features reduction

The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel‐based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean‐based function is implemented and fed input to top‐hat and bottom‐hat filters which later fused for contrast stretching, (b) seed region growing and graph‐cut method‐based lesion segmentation and fused both segmented lesions through pixel‐based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy‐based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method.     

Detection of partial occlusions of assembled components to simplify the disassembly tasks

An automatic disassembly cell requires of a computer vision system for recognition and localization of the products and each of theirs components. The detection of occlusions adds more information to the knowledge base to identify components and products, and generate a trustworthy and precise relational model (generic graph of hierarchic relations among the different components that make up the product). In this paper, a method to detect partial occlusions in assembled components is presented. This method is based on the fusion of regions and edges information, and it offers a certain degree of simplification for the recognition and modelled of the disassembly tasks, of the set of components which compose the product. The proposed approach to detect regions is a hybrid approach between RGB and HSV spaces. The bi-dimensional histogram V/S is employed for the selection of the appropriate thresholds which serve as an aid to diminish the influence of the highlights and shadows in images. The goal of this paper is to present an approach for the detection of occlusions in assembled components from a combination of HSV and RGB spaces, a bi-dimensional histogram and an edge detector.