IMAGE SEGMENTATION BASED ON MARKOV RANDOM FIELD AND WATERSHED TECHNIQUES

IntroductionThere are many methods to perform imagesegmentation and edge detection tasks that incor-porate region- growing and edge detection tech-niques,for example,it is applying edge detectiontechniques to obtain Difference In Strength( DIS)map then employ region growing techniques towork on the map as in Refs.[1 ,2 ]. In the others,combining both special and intensity information inimage segmentation approach based on multi- reso-lution edge detection,region selection and intensi-ty thre…     

噪声符合高斯分布的曲面图像分割

针对噪声符合高斯分布的曲面图像分割问题,提出了一种基于变分水平集方法的隐式曲面上噪声符合高斯分布的图像分割模型。为定义隐式曲面上图像区域划分的动态轮廓线,引入另一个动态水平集函数,其零水平集与隐式曲面的交线即为曲面上区域划分的轮廓线。该模型采用N个水平集函数划分2^N个区域的区域竞争策略。通过变分方法得到图像分割空间轮廓线演化的梯度降方程。通过显式差分格式对演化方程进行离散。实验结果表明,该模型对曲面上噪声符合高斯分布的图像具有良好的分割效果,并且在图像分割的同时能够完全保持曲面固有的几何特征。     

Image Segmentation Using an Improved Watershed Algorithm

IntroductionOne of the firstand mostimportantoperationsin image analysis and computervision is image seg-mentation.The aim of image segmentation is thedomain- independent partition of the image into aset of regions,which are visually distinct and uni-form…     

融合边缘检测与区域生长的交通图像分割方法

在交通监控中,如何从复杂的背景中分割运动物体是至关重要的一步,针对车辆的运动阴影对图像分割产生的不利影响,提出了一种新的融合边缘检测与区域生长的彩色图像分割算法,算法同时考虑了图像的彩色信息和空间信息.该算法首先对彩色图像边缘检测,并根据检测结果设置种子像素;再基于颜色相似性生长准则,结合边缘检测结果,对每个种子点进行区域生长;最后,利用区域合并算法对剩余的像素进行合并.实验结果表明该算法很大程度上克服了阴影给图像分割带来的不利影响.     

IMAGE ANALYSIS BASED ON EDGE DETECTION TECHNIQUES

IntroductionEdges are pixels where brightness changesabruptly and often used in image analysis for find-ing region boundaries.It locates sharp changes inthe intensity function.Edges detection is basic im-age features.They carry useful information aboutobject boundaries.Edges can be used for object i-dentification,image analysis and image filteringapplications as well.We shall consider as an edgethe border between two homogeneous image re-gions having different illumination.This definitionimp…     

Fusion of remote sensing images based on nonsubsampled contourlet transform and region segmentation

The purpose of remote sensing images fusion is to produce a fused image that contains more clear, accurate and comprehensive information than any single image. A novel fusion method is proposed in this paper based on nonsubsampled contourlet transform (NSCT) and region segmentation. Firstly, the multispectral image is transformed to intensity-hue-saturation (IHS) system. Secondly, the panchromatic image and the component intensity of the multispectral image are decomposed by NSCT. Then the NSCT coefficients of high and low frequency subbands are fused by different rules, respectively. For the high frequency subbands, the fusion rules are also unalike in the smooth and edge regions. The two regions are segregated in the panchromatic image, and the segmentation is based on particle swarm optimization. Finally, the fusion image can be obtained by performing inverse NSCT and inverse IHS transform. The experimental results are evaluated by both subjective and objective criteria. It is shown that the proposed method can obtain superior results to others.     

Color image segmentation by edge linking and region grouping

A novel method toward color image segmentation is proposed based on edge linking and region grouping. Firstly, the edges extracted by the Canny detector are linked to form regions. Each of the end points of edges is connected by a direct line to the nearest pixel on another edge segment within a sub-window. A new distance is defined based on the feature that the edge tends to preserve its original direction. By sampling the lines to the image, the image is over-segmented to labeled regions. Secondly, the labeled regions are grouped both locally and globally. A decision tree is constructed to decide the importance of properties that affect the merging procedure. Finally, the result is refined by user’s selection of regions that compose the desired object. Experiments show that the method can effectively segment the object and is much faster than the state-of-the-art color image segmentation methods.     

图像压缩中的多级感兴趣区域编码方法

为了解决压缩图像质量与容积的矛盾,尤其当需要对图像采用大压缩比的情况下,使得压缩图像的视觉效果更好,提出了一种多级感兴趣区域编码方法.该方法首先对所要压缩的图像进行重要性划分,然后通过对划分的不同区域采用不同的压缩比,满足了人们对不同区域的不同压缩质量要求,得到了令人满意的图像压缩质量.     

一种新的复杂细胞启发下的特征提取方法

鉴于V1区复杂细胞具有提取外界刺激不变本质的能力,设计了一个提取目标图像局部不变特征的方法.该方法首先使用提出的无监督算法（PCICA）,从图像中学习出类似于复杂细胞感受野的滤波器集合.然后利用这些滤波器组成的复杂细胞描述子,提取目标图像各个位置的不变特征.最后对图像特征图进行分块统计,将各区域的直方图序列作为图像的最终描述.测试结果表明,PCICA具有类似于快速独立分量分析算法（FastICA）三阶收敛的特点,从图像中学习出的滤波器集合,表现出复杂细胞感受野的拓扑结构.这些滤波器对于局部图像的微小变化并不敏感,对于检测不变特征十分有利,并在MNIST手写体数据库上取得0.84%的识别错误率.     

HIERARCHICAL CONTENT BASED IMAGE RETRIEVAL

ＩｎｔｒｏｄｕｃｔｉｏｎＡｔｒａｄｅｍａｒｋｉｍａｇｅｄａｔａｂａｓｅｉｓａｓｅｔｏｆｔｒａｄｅ－ｍａｒｋｐｉｃｔｕｒｅｓ．Ｕｓｕａｌｙｉｔｉｓｔｈｅｄｕｔｙｏｆｐａｔｅｎｔａｎｄｔｒａｄｅｍａｒｋｏｆｉｃｅｔｏｅｓｔａｂｌｉｓｈａｎｄｍａｎａｇｅｔ...     

Infrared and visible image fusion based on region of interest detection and nonsubsampled contourlet transform

In order to enhance the contrast of the fused image and reduce the loss of fine details in the process of image fusion,a novel fusion algorithm of infrared and visible images is proposed.First of all,regions of interest(RoIs)are detected in two original images by using saliency map.Then,nonsubsampled contourlet transform(NSCT)on both the infrared image and the visible image is performed to get a low-frequency sub-band and a certain amount of high-frequency sub-bands.Subsequently,the coefcients of all sub-bands are classified into four categories based on the result of RoI detection:the region of interest in the low-frequency sub-band(LSRoI),the region of interest in the high-frequency sub-band(HSRoI),the region of non-interest in the low-frequency sub-band(LSNRoI)and the region of non-interest in the high-frequency sub-band(HSNRoI).Fusion rules are customized for each kind of coefcients and fused image is achieved by performing the inverse NSCT to the fused coefcients.Experimental results show that the fusion scheme proposed in this paper achieves better efect than the other fusion algorithms both in visual efect and quantitative metrics.     

Exploiting Local and Global Characteristics for Contrast Based Visual Saliency Detection

Visual saliency is an important cue in human visual system to identify salient region in the image;it can be useful in many applications including image retrieval,object recognition,image segmentation,etc.Image contrast has been used as an effective feature to detect visual salient region.However,the conventional contrast measures either in spectral domain or in spatial domain fail to give sufficient consideration towards the local and global characteristics of the image.This paper presents a visual saliency detection algorithm based on a novel contrast measurement.This measurement extracts the spectral information of image block using the 2D discrete Fourier transform(DFT),and combines with the total variation(TV)of image block in spatial domain.The proposed algorithm is used to perform salient region detection in the image,and compared with state-of-the-art algorithms.The experimental results from the MSRA dataset validate the effectiveness of the proposed algorithm.     

Active Contours and Mumford-Shah Segmentation Based on Level Sets

IntroductionThe basic idea in active contour models orsnakes is to evolve a curve,subject to constraintsfrom a given image,in order to detect objects inthat image.For instance,starting with a curvearound the object to be detected,the curve movestoward its interior normal and has to stop on theboundary of the object.LetΩ be a bounded open subset of R2 ,with Ω its boundary. Let u0 ∶Ω→ R be a given image,and C( s)∶ [0 ,1 ]→ R2 be a parameterized curve. Inthe classical snakes and active…     

基于图像分割的图像检索新方法

利用信息熵理论,提出了一种新的相似性图像检索方法.首先,分割图像,抽取图像的分块颜色信息;再计算图像之间的颜色互信息来确定它们的相似度.与其他的颜色特征描述方法相比,该方法该算法具有抗噪声能力强、精确度高等优点.     

用于医学图像分割的区域生长方法

通过分析鼻腔解剖图的气腔区域可以确定患者打鼾原因,并对其后期手术治疗有着重要意义.从鼻腔解剖图分割出气腔区域是整个计算机辅助手段的前提.根据鼻腔解剖图的特征,提出了一种改进的区域生长方法,采用两次不同的迭代规则进行区域生长,不仅能够准确地分割气腔区域,而且克服了区域生长对生长参数敏感的缺点.同时对其他医学图像进行了实验,得出了令人满意的分割结果.     

Saliency motivated pulse coupled neural network for underwater laser image segmentation

The detection range of underwater laser imaging technology achieves 4—6 times of detection range of conventional camera in intervening water medium, which makes it very promising in oceanic research, deep sea exploration and robotic works. However, the special features in underwater laser images, such as speckle noise and non-uniform illumination, bring great difficulty for image segmentation. In this paper, a novel saliency motivated pulse coupled neural network(SM-PCNN) is proposed for underwater laser image segmentation. The pixel saliency is used as external stimulus of neurons. For improvement of convergence speed to optimal segmentation, a gradient descent method based on maximum two-dimensional Renyi entropy criterion is utilized to determine the dynamic threshold. On the basis of region contrast in each iteration step, the real object regions are effectively distinguished,and the robustness against speckle noise and non-uniform illumination is improved by region selection. The proposed method is compared with four other state-of-the-art methods which are watershed, fuzzy C-means, meanshift and normalized cut methods. Experimental results demonstrate the superiority of our proposed method to allow more accurate segmentation and higher robustness.     

一种多阶段处理的红外小目标检测方法

提出了一种二阶段红外图像序列小目标检测方法.该方法由2个相序的处理阶段组成,即目标的预侦测阶段和目标的确认阶段.在处理的第一阶段,通过快速扫描输入图像,根据视觉特征的显著性抽取潜在的目标集合.这些潜在的目标在第二个处理阶段通过双均值滤波方法被进一步地识别,判断出真目标,剔除假目标.统计分析在理论上证实了这种算法结构的高效和合理性.实验结果表明该方法在运算速度上有显著的优势.     

Detecting shifted double JPEG compression tampering utilizing both intra-block and inter-block correlations

Copy-paste forgery is a very common type of forgery in JPEG images.The tampered patch has always suffered from JPEG compression twice with inconsistent block segmentation.This phenomenon in JPEG image forgeries is called the shifted double JPEG(SDJPEG) compression.Detection of SDJPEG compressed image patches can make crucial contribution to detect and locate the tampered region.However,the existing SDJPEG compression tampering detection methods cannot achieve satisfactory results especially when the tampered region is small.In this paper,an effective SDJPEG compression tampering detection method utilizing both intra-block and inter-block correlations is proposed.Statistical artifacts are left by the SDJPEG compression among the magnitudes of JPEG quantized discrete cosine transform(DCT) coefficients.Firstly,difference 2D arrays,which describe the differences between the magnitudes of neighboring JPEG quantized DCT coefficients on the intrablock and inter-block,are used to enhance the SDJPEG compression artifacts.Then,the thresholding technique is used to deal with these difference 2D arrays for reducing computational cost.After that,co-occurrence matrix is used to model these difference 2D arrays so as to take advantage of second-order statistics.All elements of these co-occurrence matrices are served as features for SDJPEG compression tampering detection.Finally,support vector machine(SVM) classifier is employed to distinguish the SDJPEG compressed image patches from the single JPEG compressed image patches using the developed feature set.Experimental results demonstrate the efficiency of the proposed method.     

Monitoring Thermal Coagulation with Ultrasonic Textures

The feasibility of using B-mode ultrasound image textures and pattern recognition technique to characterize the thermal coagulation in vitro during radiofrequency ablation was investigated. The changes of ultrasonic textures in the different regions of samples varied with the heating time in the in-vitro experiments, which would result in that the coagulated and noncoagulated regions of tissue had different ultrasonic textures. Using support vector machine to extract the ultrasonic texture features and characterize the state of tissue, the size and boundaries of thermal lesions could be detected and measured more exactly than only using the gray scale information of B-mode ultrasound image. The proposed method would be applied to the image-guided radiofrequency ablation (IGRA) procedure for monitoring the thermal coagulation.     

结合区域分割和Wishart分类器的机场跑道区域快速检测方法

提出了一种结合区域分割和Wishart分类器的极化合成孔径雷达图像机场跑道区域快速检测方法; 利用简单线性迭代聚类算法分割极化合成孔径雷达图像, 并将分割得到的超像素作为后续分类处理的基本单元; 采用一种优化后的距离度量方式给超像素分配类别标签, 解决了传统Wishart距离度量因子冗余运算量大的问题; 分析了机场跑道区域像素的极化散射特性, 利用机场跑道区域的弱散射特性从分类结果中提取感兴趣区域; 利用机场跑道的结构特征筛选辨识感兴趣区域, 进而确定机场跑道区域的准确位置; 利用极化合成孔径雷达实测数据测试了算法的有效性, 并与传统基于像素的检测结果进行对比。试验结果表明: 该算法在复杂大场景下能够快速有效检测出机场跑道区域, 检测出的跑道轮廓清晰, 结构比较完整; 采用简单线性迭代聚类算法预处理图像极大地降低了后续处理的复杂性; 针对墨西哥湾试验数据, Wishart分类器处理单元个数分别是Freeman+Wishart算法和FCM+Wishart算法的1.0%和2.4%, 整个检测过程耗时分别为Freeman+Wishart算法和FCM+Wishart算法的9.9%和27.1%;针对大岛试验数据, Wishart分类器处理单元个数分别是Freeman+Wishart算法和FCM+Wishart算法的1.0%和2.6%, 整个检测过程耗时分别为Freeman+Wishart算法和FCM+Wishart算法的14.0%和31.8%。可见, 所提检测方法的实时性能优于基于像素的检测方法。