Unsupervised scene segmentation using sparse coding context

This paper presents an approach to image understanding on the aspect of unsupervised scene segmentation. With the goal of image understanding in mind, we consider ‘unsupervised scene segmentation’ a task of dividing a given image into semantically meaningful regions without using annotation or other human-labeled information. We seek to investigate how well an algorithm can achieve at partitioning an image with limited human-involved learning procedures. Specifically, we are interested in developing an unsupervised segmentation algorithm that only relies on the contextual prior learned from a set of images. Our algorithm incorporates a small set of images that are similar to the input image in their scene structures. We use the sparse coding technique to analyze the appearance of this set of images; the effectiveness of sparse coding allows us to derive a priori the context of the scene from the set of images. Gaussian mixture models can then be constructed for different parts of the input image based on the sparse-coding contextual prior, and can be combined into an Markov-random-field-based segmentation process. The experimental results show that our unsupervised segmentation algorithm is able to partition an image into semantic regions, such as buildings, roads, trees, and skies, without using human-annotated information. The semantic regions generated by our algorithm can be useful, as pre-processed inputs for subsequent classification-based labeling algorithms, in achieving automatic scene annotation and scene parsing.     

An image segmentation method using automatic threshold based on improved genetic selecting algorithm

In this paper, an image segmentation method using automatic threshold based on improved genetic selecting algorithm is presented. Optimal threshold for image segmentation is converted into an optimization problem in this new method. In order to achieve good effects for image segmentation, the optimal threshold is solved by using optimizing efficiency of improved genetic selecting algorithm that can achieve a global optimum. The genetic selecting algorithm is optimized by using simulated annealing temperature parameters to achieve appropriate selective pressures. Encoding, crossover, mutation operator and other parameters of genetic selecting algorithm are improved moderately in this method. It can overcome the shortcomings of the existing image segmentation methods, which only consider pixel gray value without considering spatial features and large computational complexity of these algorithms. Experiment results show that the new algorithm greatly reduces the optimization time, enhances the anti-noise performance of image segmentation, and improves the efficiency of image segmentation. Experimental results also show that the new algorithm can get better segmentation effect than that of Otsu’s method when the gray-level distribution of the background follows normal distribution approximately, and the target region is less than the background region. Therefore, the new method can facilitate subsequent processing for computer vision, and can be applied to realtime image segmentation.     

Segmentation of multivariate mixed data via Lossy data coding and compression

In this paper, based on ideas from lossy data coding and compression, we present a simple but effective technique for segmenting multivariate mixed data that are drawn from a mixture of Gaussian distributions, which are allowed to be almost degenerate. The goal is to find the optimal segmentation that minimizes the overall coding length of the segmented data, subject to a given distortion. By analyzing the coding length/rate of mixed data, we formally establish some strong connections of data segmentation to many fundamental concepts in lossy data compression and rate distortion theory. We show that a deterministic segmentation is approximately the (asymptotically) optimal solution for compressing mixed data. We propose a very simple and effective algorithm which depends on a single parameter, the allowable distortion. At any given distortion, the algorithm automatically determines the corresponding number and dimension of the groups and does not involve any parameter estimation. Simulation results reveal intriguing phase-transition-like behaviors of the number of segments when changing the level of distortion or the amount of outliers. Finally, we demonstrate how this technique can be readily applied to segment real imagery and bioinformatic data.     

基于视觉一致性的图像检索

提出一种新的彩色图像分割方法,将图像分割成具有明显视觉一致性的区域,这种一致性能够模拟人观察图像时的视觉感受,例如图像中的一片区域具有相同的颜色、纹理。对这样的一致性区域建立特征描述符,如颜色编码、连通系数、面积比例,其中颜色编码是通过将像素在HSI颜色空间中量化得到,进而为整幅图像建立特征描述;然后将这种特征描述用于图像的检索。实验结果表明,这种方法不仅能够很好地模拟图像所带给人的视觉感受,而且对具有视觉一致性的图像检索效果也有很好的表现。     

基于改进的离散傅里叶变换图像分割算法研究

研究图像分割特征提取优化问题。由于外界信号噪声等问题而引起图像分割分辨率低,清晰度不高,提取图像的主要特征目标是图像分割中关键的技术,针对传统的图像特征提取分割算法无法完成对图像关键特征信息适度提取,另外图像分割计算复杂,为了有效的对图像进行分割,提出了一种改进的离散傅里叶变换的图像分割算法。采用傅里叶变换算法对图像中感兴趣的区域进行分割出来后,对各个分割区域特点进行描述并组成一定的结构,从而获得最优图像分割结果。仿真结果表明,改进的算法可以有效地提取复杂图像区域中的特征信息,分割效果明显,提高了图像分割的分辨率和清晰度。     

Grey level reduction for segmentation, threshholding and binarisation of images based on optimal partitioning on an interval

Optimal reduction of the number of grey levels present in an image is a fundamental problem in segmentation, classification, lossy compression, quantisation, inspection and computer vision. We present a new algorithm based on dynamic programming and optimal partitioning of the image data space, or its histogram representation. The algorithm allows the reduction of the number of grey levels for an image in a fine to coarse fashion, starting with the original grey levels present in the image and all the way down to two grey levels that simply create a binarised version of the original image. The algorithm can also be used to find a reduced number of grey levels in a natural way without forcing a specific number ahead of time. Application of the algorithm is demonstrated in image segmentation, multi-level thresholding and binarisation, and is shown to give very good results compared to many of the existing methods.     

多主体框架下结合最大期望值和遗传算法的SAR图像分割

目的 SAR图像中固有的相干斑噪声增加了图像分割的困难.为此,提出一种分布式SAR图像分割算法.方法 首先假设图像中同质区域内像素满足同一独立的Gamma分布,依此建立SAR图像模型;为了刻画SAR图像中像素的类属性,建立标号场的MRF(Markov Random Field)模型;在Bayesian理论框架下建立图像分割模型;在多主体系统(MAS)框架下,结合MRF模型和遗传算法(GA)模拟分割模型.MAS结构由分割主体和协调主体组成,其中分割主体利用最大期望值( EM)算法估计MRF模型参数,从而实现全局分割;协调主体利用GA实现全局最优.结果 为了验证提出方法的有效性,分别对模拟和RADARSAT-I/II SAR图像进行实验,并与EM和RJMCMC算法比较.本文算法的用户精度、产品精度、总精度及kappa系数均高于EM算法.定性和定量分析结果验证了本文算法的鲁棒性和有效性.结论 实验结果表明提出的分布式MAS框架下SAR图像分割方法,能够提高分割精度.该方法适用于中高分辨率单极化的SAR图像,且具有很好的抗噪性.     

结合格式塔完形规则的自然图像分割

目的 由于自然图像容易受到光照等因素的影响,其分割精度往往达不到人类视觉感知的需求,为此提出了一种新的结合格式塔完形规则的自然图像分割方法。方法 首先采用Ncut算法对原图像进行过分割得到若干个子区域,这些局部子区域能弱化光照、背景模糊等自然因素的影响;然后引入格式塔完形规则对区域进行度量,提出了基于区域的量化计算模型,进一步弱化了自然因素的影响,而且所得的区域率更加符合人的视觉感知;最后在区域率的基础上提出了新的合并算法,该算法简单且执行效率高,通过区域合并得到最终的分割结果。结果 30幅图像的定量和目视对比实验表明,本文算法不仅能够很好地将格式塔完形规则应用到图像分割上来,而且对比实验表明,本文算法在评价指数PRI、VOI、GCE上总体性能要优于其他算法,与人工标注的结果比较接近。结论 提出了一种结合格式塔完形规则的自然图像分割方法,该方法在过分割的基础上,采用格式塔完形规则对区域进行度量,有效降低了自然图像易受自然因素的影响,提高了分割精度。实验结果表明,本文提出的结合格式塔完形规则的图像分割算法高效性而准确,但不适合于尖细物体的自然图像的分割。     

An integrated approach for scene understanding based on Markov Random Field model

In this paper, we propose a Markov Random Field model-based approach as a unified and systematic way for modeling, encoding and applying scene knowledge to the image understanding problem. In our proposed scheme we formulate the image segmentation and interpretation problem as an integrated scheme and solve it through a general optimization algorithm. More specifically, the image is first segmented into a set of disjoint regions by a conventional region-based segmentation technique which operates on image pixels, and a Region Adjacency Graph (RAG) is then constructed from the resulting segmented regions based on the spatial adjacencies between regions. Our scheme then proceeds on the RAG by defining the region merging and labeling problem based on the MRF models. In the MRF model we specify the a priori knowledge about the optimal segmentation and interpretation in the form of clique functions and those clique functions are incorporated into the energy function to be minimized by a general optimization technique. In the proposed scheme, the image segmentation and interpretation processes cooperate in the simultaneous optimization process such that the erroneous segmentation and misinterpretation due to incomplete knowledge about each problem domain can be compensately recovered by continuous estimation of the single unified energy function. We exploit the proposed scheme to segment and interpret natural outdoor scene images.     

基于分水岭算法的灵武长枣图像分割方法研究

传统分水岭算法常常会因阈值选择不当而导致图像分割出现各种各样的问题,尤其是过分割问题。在传统分水岭算法的基础上,以灵武长枣图像为研究对象,运用遗传算法对随机选取的阈值进行优化选择;对自然光照环境下的20幅灵武长枣图像,采用改进后的分水岭算法对其进行分割。首先在传统分水岭算法的基础上,利用遗传算法对阈值进行寻优,得到最优的图像分割阈值,再利用最大类间方差法和数学形态学等方法对图像进行后处理,最终得到分割图像,将分割图像与人工分割得到的图像进行比较,分割的正确率能达到89.99%,且分割效果远远优于传统分水岭算法。实验表明,该方法能够得到最优分割阈值并且能够满足机器识别对图像分割的要求。     

Generating and coding of fractal graphs by neural network andmathematical morphology methods

We present an algorithm for generating a class of self-similar (fractal) graphs using simple probabilistic logic neuron networks and show that the graphs can be represented by a set of compressed encoding. An algorithm for quickly finding the coding, i.e., recognizing the corresponding graphs, is given and the coding are shown to be optimal (i.e., of minimal length). The same graphs can also be generated by a mathematical morphology method. These results may possibly have applications in image compression and pattern recognition.     

图像阈值化的自适应粗糙熵方法

摘 要：目的：图像阈值化将灰度图像转换为二值图像,被广泛应用于多个领域。因实际工程应用中固有的不确定性,自动阈值选择仍然是一个极具挑战的课题。针对图像自动阈值化问题,提出了一种利用粗糙集的自适应方法。方法：该方法分析了基于粗糙集的图像表示框架,建立了图像粗糙粒度与局部灰度标准差的相互关系,通过最小化自适应粗糙粒度准则获得最优的划分粒度。进一步在该粒度下构造了图像目标和背景的上下近似集及其粗糙不确定度,通过搜索灰度级最大化粗糙熵获得图像最优灰度阈值,并将图像目标和背景的边界作为过渡区,利用其灰度均值作为阈值完成图像二值化。结果：对所提出的方法通过多个图像分三组进行了实验比较,包括三种经典阈值化方法和一种利用粗糙集的方法。其中,所提出的方法生成的可视化二值图像结果远远优于传统粗糙集阈值化方法。此外,也采用了误分率、平均结构相似性、假阴率和假阳率等指标进一步量化评估与比较相关实验结果。定性和定量的实验结果表明,所提出方法的图像分割质量较高、性能稳定。结论：所提出的方法适应能力较好,具有合理性和有效性,可以作为现有经典方法的有力补充。     

改进的交互式Otsu红外图像分割算法

为提高红外图像中目标分割的精度和抗噪性能,提出了一种改进的交互式Otsu图像分割算法。采用图像信息熵特征和类间方差特征对经典Otsu算法的阈值判别函数进行改进,获得的最优阈值能较好地将目标从背景中分割出来,且具有良好的边缘保持效果,提高了算法的分割精度。同时,针对红外图像目标单一的特点,采用交互式粗分割的思路,先在红外图像中提取包含目标的局部封闭区域,进而在提取的区域内进行改进的Otsu分割。通过对红外图像激光光斑目标提取过程的实验结果表明：改进的Otsu分割算法大大降低了背景噪声对分割算法的影响,提高了抗噪性能与分割精度,且最大程度地减少分割算法的运算量,并较好地保持了目标模糊边缘,分割效果优于传统的Otsu算法和相关的改进Otsu算法。     

Image segmentation by three-level thresholding based on maximum fuzzy entropy and genetic algorithm

In the paper, a three-level thresholding method for image segmentation is presented, based on probability partition, fuzzy partition and entropy theory. A new fuzzy entropy has been defined through probability analysis. The image is divided into three parts, namely, dark, gray and white part, whose member functions of the fuzzy region are Z-function and Π-function and S-function, respectively, while the width and attribute of the fuzzy region can be determined by maximizing fuzzy entropy. The procedure for finding the optimal combination of all the fuzzy parameters is implemented by a genetic algorithm with appropriate coding method so as to avoid useless chromosomes. The experiment results show that the proposed method gives good performance.     

自然场景图像中叶片区域快速多阈值提取方法

针对自然场景中植物叶片图像分割效果不佳,难以从含有多个叶片的图像中提取出完整叶片区域的问题,提出了一种叶片区域的快速多阈值提取方法。首先,使用人工蜂群算法优化Otsu多阈值选取的过程,以类间方差为适应度函数获取最优的多个阈值,在获取最优多阈值的过程中以迭代的方式自适应地确定出适合于叶片图像的分割阈值数目,然后使用边缘检测,逻辑运算和形态学操作等从多阈值分割结果中去除背景元素,提取独立、完整的叶片区域。实验结果表明,当对包含一个和多个叶片的自然场景图像进行处理时,该方法能够较为快速地得到更为完整、准确的叶片区域。     

SAR图像的最优分割方法

根据SAR图像的概率密度函数获得图像的拟然函数,然后将似然函数和边界约束方程结合起来,提出适合于SAR图像分割的代价函数,其中边界约束方程引入邻域结构信息来保证区域边界的规则性,通过使代价函数最小来获得图像的最优分割。算法首先将原图分割成一定大小的块状区域作为初始分割,每一区域代表一个类别;然后随机调整相邻两个区域之间的像素,通过比较代价函数的变化,利用模拟退火算法确定接受该调整的概率。模拟退火是一种求解全局最优的算法,当温度趋向于0时,它可以获得使代价函数最小的SAR图像的分割。最后,利用基于相似性的融合方法对分割进行后期处理,将相似的较小的区域融合成较大的区域,使得分割更合理。我们将该算法应用到一些SAR测试图像上,获得了比较满意的结果。     

带噪图像的多扫描阈值分割编码算法的研究

零树编码算法是一种有效的图像编码算法,但是噪声会破坏零树结构特性,影响零树编码算法的效率,针对噪声图像提出一种基于多扫描阈值的图像分割编码算法,该算法利用多扫描阈值结构对噪声图像进行软阈值去噪、并完善逐次逼近量化过程;对重要高频子带采用图像分割编码,只对重要系数进行编码, 将大量非重要系数集中成图像块不予编码,更有效地降低码率.实验结果表明,算法有效地去除了噪声,提高了编码图像的质量和编码效率,在相同的压缩比条件下,算法在编码速度、图像复原质量方面都优于EZW算法.     

Markov random field models for unsupervised segmentation oftextured color images

We present an unsupervised segmentation algorithm which uses Markov random field models for color textures. These models characterize a texture in terms of spatial interaction within each color plane and interaction between different color planes. The models are used by a segmentation algorithm based on agglomerative hierarchical clustering. At the heart of agglomerative clustering is a stepwise optimal merging process that at each iteration maximizes a global performance functional based on the conditional pseudolikelihood of the image. A test for stopping the clustering is applied based on rapid changes in the pseudolikelihood. We provide experimental results that illustrate the advantages of using color texture models and that demonstrate the performance of the segmentation algorithm on color images of natural scenes. Most of the processing during segmentation is local making the algorithm amenable to high performance parallel implementation     

基于互信息准则的图像平滑和分割

在计算机视觉领域,尺度空间扮演着一个很重要的角色。多尺度图像分析的基础是自动尺度选择,但它 的性能非常主观和依赖于经验。基于互信息的度量准则,文章提出了一种自动选取最优尺度的模型。首先,研究 专注于基于形态学算子的多尺度图像平滑去噪方法,这种技术不需要噪声方差的先验知识,可以有效地消除照度 的变化。其次,通过递归修剪 Huffman 编码树,设计了一个基于聚类的无监督图像分割算法。一个特定的聚类数 从信息理论的角度来看,提出的聚类算法可以保留最大的信息量。最后,用一系列的实验对算法的性能进行了验证, 并从数学上进行了详细的证明和分析,实验结果表明本文提出的算法能获得最优尺度的图像平滑和分割性能 。