Double regularization control based on level set evolution for tablet packaging image segmentation

This paper proposes a novel double regularization control(DRC) method which is used for tablet packaging image segmentation.Since the intensities of tablet packaging images are inhomogenous,it is difficult to make image segmentation.Compared to methods based on level set,the proposed DRC method has some advantages for tablet packaging image segmentation.The local regional control term and the rectangle initialization contour are first employed in this method to quickly segment uneven grayscale images and accelerate the curve evolution rate.Gaussian filter operator and the convolution calculation are then adopted to remove the effects of texture noises in image segmentation.The developed penalty energy function,as regularization term,increases the constrained conditions based on the gradient flow conditions.Since the potential function is embedded into the level set of evolution equations and the image contour evolutions are bilaterally extended,the proposed method further improves the accuracy of image contours.Experimental studies show that the DRC method greatly improves the computational efficiency and numerical accuracy,and achieves better results for image contour segmentation compared to other level set methods.     

Integrating Feature Direction Information with a Level Set Formulation for Image Segmentation

A feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and our method can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.     

综合边缘检测和区域生长的红外图像分割方法

针对红外图像的特点,提出了一种综合应用边缘检测和区域生长方法的图像分割方法。其思路为:先对图像进行边缘提取,得到边缘像素点集;然后利用该点集的平均灰度和目标区域的连通性作为生长判决条件,采用区域生长法实现图像分割。仿真结果表明,该方法能快速准确有效地实现红外图像分割,避免了单独使用边缘提取或区域生长法进行图像分割时的典型分割错误。     

A novel level set method for image segmentation by combining local and global information

A novel level set method integrating local and global statistical information is proposed in this paper. In our method, a new signed pressure force (SPF) function is constructed by two parts. One is the global average intensity of the image, which can accelerate the evolution of the curve when the contour far away from the object boundaries. The other is the intensity average of difference image between the averaging convolution image and the original image, which can guide the evolving curve to catch the boundaries of the objects. In addition, an adaptive weighting function is utilized to adjust the ratio between the global and local terms, which can eliminate the inconvenient selection of weighting parameter. By substituting the new SPF function for the edge stopping function of the geodesic active contour model, we obtain a novel adaptive hybrid segmentation model, which is capable of segmenting the images with intensity inhomogeneity. What is more, in our method, the level set function is initialized with a binary function, which reduces the computational cost for the re-initialization step. The experimental results and comparisons with several popular models on synthetic and real images indicate that our method achieves superior performance in segmenting images with noise, low contrast and intensity inhomogeneity.     

Boundary-based object segmentation in X-ray imaging using spiral search

In this paper, we propose a boundary-based method for object segmentation by using only the edge information. The proposed method is especially applied to object segmentation of dangerous firearms and knives in the X-ray images of baggage, where no colour or texture features are available to describe the target object. The Canny edge detector is used to extract edge points from the X-ray image. These edges have cluttered backgrounds and may be discontinuous. A fast spiral search is proposed to connect neighbouring points, either continuous or discontinuous, and form closed contours for individual objects. The distance and direction angle of an edge point in the search process can be obtained from a pre-constructed spiral look-up-table. No computation of the geometric features is required. Thus, the search of the coherent neighbouring points for edge connection is very fast. The experimental results have shown that the proposed method can effectively and efficiently segment a variety of firearms and knives of different shapes and sizes in the X-ray images of baggage.     

基于亚像素边缘的摄像机标定板特征提取算法

目的在视觉测量领域,摄像机的标定精度是最终测量精确度的决定性因素,为了提高标定板特征的提取精度,提出一种基于亚像素边缘的提取方法。方法针对圆点标定板,首先采集标定板图像,对图像进行处理,获取像素级别边缘,然后以边缘像素点为中心,取3×3的数字窗口计算梯度方向,在梯度方向上进行像素点灰度的双曲正切拟合,获取亚像素级别边缘,最后对亚像素边缘按照圆形进行拟合,求得圆心坐标。结果实验表明算法的分辨率达到0.03个像素,精度可达0.1个像素。结论该算法具有稳定可靠,精度高,运算速度快等特点,能够应用于图像拼接和分割,特征提取和摄像机标定等领域。     

结合数学形态学和Level Set超声图像的分割方法

针对噪声严重的超声图像,提出了一种结合数学形态学和Level Set的分割方法。首先采用全变差模型进行图像滤波,再通过交互式区域选择和数学形态学方法获得感兴趣目标的二值化图像,并把该二值化图像轮廓作为水平集方法的初始曲线。改进隐式测地活动轮廓模型(GAC)中的边缘检测函数,增强了处理弱边缘的能力。分割结果表明,该方法能够准确地提取出目标轮廓,同时减少了迭代次数和运算时间。     

基于图像处理的药片包装视觉检测系统滤波算法

目的为了有效滤除药片包装视觉检测系统中的噪声,提升图像清晰度,保证后期图像分割、边缘处理顺利进行。方法针对药片视觉检测图像中存在大量不确定噪声,提出一种自适应模糊神经网络的图像滤波算法。在模糊神经网络结构中引入一个鲁棒性较强的隶属函数,并通过梯度下降法对模糊神经网络中的参数进行优化训练,利用优化后的网络结构对被噪声污染的图像进行滤波处理。结果仿真结果表明,该算法能够在保留较完整的图像边缘和重要细节的前提下,有效滤除药片中的噪声。结论该滤波算法有效提高了药片图像的清晰度,对于后期药片图像分割以及边缘化处理具有重要意义。     

一种基于数据融合的图像插值算法

针对传统的线性插值算法存在的边缘模糊问题,本文提出一种新算法.首先采用距离平方反比的插值方法在插值点邻域内计算水平、垂直和对角三个方向共6个插值,然后以插值距离和方向梯度构造权重,进行数据融合获得最终插值.该算法既考虑了插值距离因素,又考虑了插值方向梯度信息,有效地保护插值图像的边缘和纹理信息.实验结果表明,该算法的插值图像比传统的双线性插值法均方误差降低而平均梯度增加,是一种提高插值图像分辨率的有效方法.     

Segmentation of liver in ultrasonic images applying local optimal threshold method

Abstract

Low brightness contrast and grey level discontinuities of the ultrasonic liver image make it difficult to segment the object and the background and to extract the edges of the object using the global optimal threshold method. In this paper, we investigate a local optimal threshold method for the segmentation of ultrasound liver image. First of all, the distributed energy of the ultrasound liver image is estimated in the proposed liver segmentation. Then, the polynomials are fitted from the distributed energy data and a peak zone is defined from the minimum of the fitted polynomials. Finally, a few blocked images are divided from the number of the peak zones. Furthermore, multiple local optimal thresholds are obtained from the blocked images using Otsu’s method, and the ultrasonic liver image is segmented according to all local optimal thresholds. Experimental results validate the segmentation and edge detection of liver in the ultrasound images.     

Implementation of edge-preserving regularization for frequency-domain diffuse optical tomography

In this study, we first propose the use of edge-preserving regularization in optimizing an ill-conditioned problem in the reconstruction procedure for diffuse optical tomography to prevent unwanted edge smoothing, which usually degrades the attributes of images for distinguishing tumors from background tissues when using Tikhonov regularization. In the edge-preserving regularization method presented here, a potential function with edge-preserving properties is introduced as a regularized term in an objective function. With the minimization of this proposed objective function, an iterative method to solve this optimization problem is presented in which half-quadratic regularization is introduced to simplify the minimization task. Both numerical and experimental data are employed to justify the proposed technique. The reconstruction results indicate that edge-preserving regularization provides a superior performance over Tikhonov regularization.     

Detection and segmentation of cervical cell cytoplast and nucleus

This article aims to develop a method for the detection and segmentation of a cytoplast and nucleus from a cervix smear image. First, the technique of equalization method with Gaussian filter is adopted to eliminate noise in the image. Second, a new edge enhancement technique is proposed to work out the coarseness of each pixel, which is later used as a determining characteristic of reinforced object images. A two‐group object enhancement technique is then used to reinforce this object according to rough pixels. Third, the proposed detector enhances the gradients of the edges of the cytoplast and nucleus while suppressing the noise gradients, and then specifies the pixels with higher gradients as possible edge pixels. Finally, it picks out the two longest closed curves constructed by part of the edge pixels. Detection and segmentation performance of the proposed method is later compared with seed region growing feature extraction and level set method using 10 cervix smear images as example. Besides comparing the contour segment of the cytoplast and nucleus obtained by using different methods, we also compare the quality of the segmentation results. Experimental results show that the proposed detector demonstrates an impressive performance. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 260–270, 2009     

Block-based tri-channel hybrid segmentation of images for foreground extraction

Image segmentation is crucial in image analysis, object representation, visualization and other image processing tasks. An image can be distinguished in terms of the foreground and the background. A new hybrid segmentation of images for foreground extraction is proposed, based on Interval Neutrosophic Set (INS) and Sparse Field Active Contour. In this method, an image is represented in three channels using a Gaussian filter bank and each channel is split into blocks to which the INS is applied. The resultant neutrosophic image for three channels undergoes isodata thresholding to obtain the tri-channel edge image, which is segmented using the Sparse Field Active Contour. The proposed method is evaluated by conducting three different experiments in natural image datasets like the Semantic Dataset100, Weizmann_Seg_DB_1obj, BSR and standard MATLAB test images. Finally, it is compared to other existing segmentation methods, which shows promising achievement in terms of their evaluation metrics like overlap-based metrics, pair-counting-based method and distance measures.     

基于局部坐标二次微分的自适应全变分去噪复原

针对传统TV去噪复原算法以梯度模值作为图像的边缘检测算子,无法清晰地识别边缘和灰度渐变区及去除平坦区内的孤立噪声的问题,提出了一种基于局部坐标二次微分的边缘检测算子对传统模型进行改进。改进后的模型能根据各像素点的新检测算子信息,自适应选取复原模型中决定扩散强弱的参数,并且利用图像局部信息对正则化项和保真项进行加权。同时在数值实现上,采用一种基于梯度矢量的方向变化的方法来实现散度离散化,以更加有效地保留图像的局部细节信息。数值试验表明,该算法在克服灰度渐变区内的阶梯效应和保留图像的细节边缘方面明显优于传统算法。     

Image segmentation model based on adaptive adjustment of global and local information

In this article, an adaptive mixture model for image segmentation that synthesizes both global information and local information using a new adaptive balance function has been proposed. Given the variety of possible image characteristics that may have to be processed, the proposed model can adaptively adjust the weighting to drive curve evolution trends and states. In this way, the intensity information of weak boundaries and complex backgrounds can be extracted more precisely, thus enabling the model to produce better results for low‐contrast images and complex structures. In addition, a Gaussian filtering process has been added to the model to smooth and standardize the level set function, and a parameter has been introduced to speed up the curve evolution. A penalty term is also used to eliminate the need for complex re‐initialization procedures. Experimental results for various kinds of images efficiently demonstrate the good performance of the proposed model in terms of both speed and accuracy. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 179–187, 2016     

A new images segmentation method based on modified particle swarm optimization algorithm

The partitioning of an image into several constituent components is called image segmentation. Many approaches have been developed; one of them is the particle swarm optimization (PSO) algorithm, which is widely used. PSO algorithm is one of the most recent stochastic optimization strategies. In this article, a new efficient technique for the magnetic resonance imaging (MRI) brain images segmentation thematic based on PSO is proposed. The proposed algorithm presents an improved variant of PSO, which is particularly designed for optimal segmentation and it is called modified particle swarm optimization. The fitness function is used to evaluate all the particle swarm in order to arrange them in a descending order. The algorithm is evaluated by performance measures such as run time execution and the quality of the image after segmentation. The performance of the segmentation process is demonstrated by using a defined set of benchmark images and compared against conventional PSO, genetic algorithm, and PSO with Mahalanobis distance based segmentation methods. Then we applied our method on MRI brain image to determinate normal and pathological tissues. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 265–271, 2013     

基于改进MultiResUNet网络的甲状腺超声图像分割

甲状腺超声图像分割在临床超声图像研究中有很重要的意义。针对甲状腺超声图像信噪比低,斑点噪声多,且甲状腺形态不确定等问题,提出了一种改进的MultiResUNet分割网络(称为Oct-MRU-Net网络)。该方法在MultiResUNet网络的基本结构的基础上引入Octave卷积,并采用改进的Inception模块学习不同空间尺度的特征,将训练过程中的特征图按通道方向分为高低频特征。其中,高频特征描述图像细节和边缘信息,低频特征描述图像整体轮廓信息。在甲状腺超声图像分割过程中可以重点关注高频信息,减少空间冗余,从而实现对边缘更加精细的分割。实验结果表明,Oct-MRU-Net网络的性能相较于U-Net网络和MultiResUNet网络都有较大的提升,说明该网络对甲状腺超声图像的分割效果较好。     

Fast unsupervised texture segmentation using Texel similarity map

Unsupervised texture segmentation is a challenging topic in computer vision. It is difficult to obtain boundaries of texture regions automatically in real-time, especially for cluttered images. This paper presents a new fast unsupervised texture segmentation method. First, the Texel similarity map (TSM) is used to compare the changes of intensity and gray level of neighboring pixels to determine whether they are identical. Then, a scheme called multiple directions integral images (MDII) is proposed to quickly evaluate the TSM. With the aid of MDII, one pixel’s similarity value can be computed in constant time. Finally, the proposed segmentation method is tested on both artificial texture and natural images. Experimental results show that the proposed method performs well on a wide range of images, and outperforms state-of-the-art method on segmentation speed.     

一种基于DA-GMRF的无监督图像分割方法

提出一种基于间断自适应高斯马尔可夫随机场(DA-GMRF)模型的无监督图像分割方法.针对MRF模型中的过平滑问题,利用边缘信息构造能量函数,定义了一种DA-GMRF模型.利用灰度直方图势函数自动确定分类数及分割阈值,进行多阈值分割,得到DA-GMRF模型中标记场的初始化,用Metroplis采样器算法进行标记场的优化,实现了图像的无监督分割.实验结果表明了该方法的有效性.     

基于U-net的水位线检测

提出一种基于U-net水位线自动分割的新方法,并通过多种场景进行验证。首先标记出原始图像中的水和背景并对其灰度化;然后利用处理后的图像和原始图像制作出数据集,把数据集作为输入利用U-net对图像进行分割;最后将所有分割出来的图像进行边缘提取得到水位线。实验结果表明:U-net水位自动分割可以精确地标记出水位线,同时解决了在水位测量过程中图像背景所带来的影响,分割效果明显优于其它分割方法,识别率达到96%以上。