Real Time Edit Propagation by Efficient Sampling

It is popular to edit the appearance of images using strokes, owing to their ease of use and convenience of conveying the user's intention. However, propagating the user inputs to the rest of the images requires solving an enormous optimization problem, which is very time consuming, thus preventing its practical use. In this paper, a two‐step edit propagation scheme is proposed, first to solve edits on clusters of similar pixels and then to interpolate individual pixel edits from cluster edits. The key in our scheme is that we use efficient stroke sampling to compute the affinity between image pixels and strokes. Based on this, our clustering does not need to be stroke‐adaptive and thus the number of clusters is greatly reduced, resulting in a significant speedup. The proposed method has been tested on various images, and the results show that it is more than one order of magnitude faster than existing methods, while still achieving precise results compared with the ground truth. Moreover, its efficiency is not sensitive to the number of strokes, making it suitable for performing dense edits in practice.     

A novel position prior using fusion of rule of thirds and image center for salient object detection

Salient object detection is one of the challenging problems in the field of computer vision. Most of the models use a center prior to detect salient objects. They give more weightage to the objects which are present near the center of the image and less weightage to the ones near the corners of the image. But there may be images in which object is placed near the image corner. In order to handle such situation, we propose a position prior based on the combined effect of the rule of thirds and the image center. In this paper, we first segment the image into an optimal number of clusters using Davies-Bouldin index. Then the pixels in these clusters are used as samples to build the Gaussian mixture model whose parameters are refined using Expectation-Maximization algorithm. Thereafter the spatial saliency of the clusters is computed based on the proposed position prior and then combined into a saliency map. The performance is evaluated both qualitatively and quantitatively on six publicly available datasets. Experimental results demonstrate that the proposed model outperforms the seventeen existing state-of-the-art methods in terms of F –measure and area under curve on all the six datasets.     

Interactive chromaticity mapping for multispectral images

Multispectral images record detailed color spectra at each image pixel. To display a multispectral image on conventional output devices, a chromaticity mapping function is needed to map the spectral vector of each pixel to the displayable three dimensional color space. In this paper, we present an interactive method for locally adjusting the chromaticity mapping of a multispectral image. The user specifies edits to the chromaticity mapping via a sparse set of strokes at selected image locations and wavelengths, then our method automatically propagates the edits to the rest of the multispectral image. The key idea of our approach is to factorize the multispectral image into a component that indicates spatial coherence between different pixels, and one that describes spectral coherence between different wavelengths. Based on this factorized representation, a two-step algorithm is developed to efficiently propagate the edits in the spatial and spectral domains separately. The method presented provides photographers with efficient control over color appearance and scene details in a manner not possible with conventional color image editing. We demonstrate the use of interactive chromaticity mapping in the applications of color stylization to emulate the appearance of photographic films, enhancement of image details, and manipulation of different light transport effects.     

基于改进Harris算法的汉字图像角点检测

根据汉字图像的特点,借鉴加速分割检测特征算法的思想,提出一种改进的Harris算法对汉字图像进行角点检测。首先,计算像素值初步判断出非角点并排除;然后,通过计算传统Harris算法中的角点响应函数对剩余的像素进行角点检测;最后,借鉴加速分割检测特征算法的思想对伪角点进行删除。最终检测出的角点是汉字笔画的起点和末端的角点,为下一步特征提取中确定线段的位置和计算线段的长度提供有利的技术基础。通过对一定数量的汉字图像的实验仿真,将本文方法与几种常用的角点检测方法进行比较,本文方法在检测正确率方面有所提高,但在运行时间上没有达到最短,综合考虑正确率和运行时间,本文方法较其他几种方法有所提高。      

快速结构化图像修补

图像修补的目的是对图像中缺失的区域进行修复,或是将图像中的物体抠去并进行背景填充,以取得融合到难以用肉眼分辨的效果。在图像修补的过程中,较大的结构信息是修补的难点。为此提出了一种快速结构化的图像修补算法,该方法将图像修补分为结构修补与纹理填充两个部分,即在用户指定待修补区域与结构曲线之后,首先定义全局最优化能量函数,并用动态规划与置信度传播的算法将其最小化来完成结构修补;然后对剩余的待修补区域通过按行扫描来进行纹理填充,其中对于边界处的点是使用基于样本的修补算法,而对于待修补区域内部的点,则使用快速的加权Ashikhmin-WL算法,扫描完成后输出修补后的图像;最后实现了一个快速结构化图像修补系统,并给出一些实验结果,从实验结果中可以看到,该方法的修补流程与算法是有实际应用价值的。     

An automatic fuzzy c-means algorithm for image segmentation

Fuzzy c-means (FCM) algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm must be estimated by expertise users to determine the cluster number. So, we propose an automatic fuzzy clustering algorithm (AFCM) for automatically grouping the pixels of an image into different homogeneous regions when the number of clusters is not known beforehand. In order to get better segmentation quality, this paper presents an algorithm based on AFCM algorithm, called automatic modified fuzzy c-means cluster segmentation algorithm (AMFCM). AMFCM algorithm incorporates spatial information into the membership function for clustering. The spatial function is the weighted summation of the membership function in the neighborhood of each pixel under consideration. Experimental results show that AMFCM algorithm not only can spontaneously estimate the appropriate number of clusters but also can get better segmentation quality.     

Instant Propagation of Sparse Edits on Images and Videos

The ability to quickly and intuitively edit digital contents has become increasingly important in our everyday life. We propose a novel method for propagating a sparse set of user edits (e.g., changes in color, brightness, contrast, etc.) expressed as casual strokes to nearby regions in an image or video with similar appearances. Existing methods for edit propagation are typically based on optimization, whose computational cost can be prohibitive for large inputs. We re‐formulate propagation as a function interpolation problem in a high‐dimensional space, which we solve very efficiently using radial basis functions. While simple to implement, our method significantly improves the speed and space cost of existing methods, and provides instant feedback of propagation results even on large images and videos.     

Multiple resolution segmentation of textured images

A multiple resolution algorithm is presented for segmenting images into regions with differing statistical behavior. In addition, an algorithm is developed for determining the number of statistically distinct regions in an image and estimating the parameters of those regions. Both algorithms use a causal Gaussian autoregressive model to describe the mean, variance, and spatial correlation of the image textures. Together, the algorithms can be used to perform unsupervised texture segmentation. The multiple resolution segmentation algorithm first segments images at coarse resolution and then progresses to finer resolutions until individual pixels are classified. This method results in accurate segmentations and requires significantly less computation than some previously known methods. The field containing the classification of each pixel in the image is modeled as a Markov random field. Segmentation at each resolution is then performed by maximizing the a posteriori probability of this field subject to the resolution constraint. At each resolution, the a posteriori probability is maximized by a deterministic greedy algorithm which iteratively chooses the classification of individual pixels or pixel blocks. The unsupervised parameter estimation algorithm determines both the number of textures and their parameters by minimizing a global criterion based on the AIC information criterion. Clusters corresponding to the individual textures are formed by alternately estimating the cluster parameters and repartitioning the data into those clusters. Concurrently, the number of distinct textures is estimated by combining clusters until a minimum of the criterion is reached     

基于mean-shift全局立体匹配方法

针对图像全局立体匹配精度高、计算量大的问题,提出基于mean shift图像分割的全局立体匹配方法。首先,通过mean shift算法对图像进行分割,获取图像同质区域数量和区域的标号。在计算匹配代价时,根据像素所属的分割区域,对像素进行筛选,从而提高匹配代价计算速度;其次,在代价聚合前,将mean shift算法获取的同质区域数K值赋值给K-means聚类算法,对像素再次聚类,提高立体匹配精度和速度;最后通过TRW-S置信传播解决能量最小化问题。实验表明,该算法明显提高了匹配的准确性和速度,与单纯的全局匹配算法相比,具有更大的优势。     

利用Gabor方向导数相关矩阵的角点检测

为了提高角点检测的准确率,提出了一种使用图像的Gabor方向导数构建相关矩阵来进行图像角点检测的算法。算法首先通过Canny边缘检测算法提取检测图像的边缘轮廓;然后使用Gabor滤波器对图像进行平滑,利用每一个边缘像素和其邻近像素的Gabor方向导数构建相关矩阵,若相关矩阵的归一化特征值的和大于预定阈值并且是局部极大值,则标记该像素为角点。算法利用邻近像素Gabor方向导数之间的相关信息提取角点,与传统的基于轮廓的角点检测算法相比,检测性能更加稳健。实验结果表明：在含噪声和无噪声情况下,提出的算法检测到的真实角点更多,而错误角点更少,整体性能有明显提升     

二值图像中拐点的实时检测算法

鉴于数字图像中的拐点通常成为重要的信息载体,因此准确、稳定和实时地检测出拐点便成为拐点检测算法面临的主要问题,针对该问题,提出了一种新的二值图像中拐点的实时检测算法。该算法与传统基于边界链码的拐点检测算法不同,其是首先构建像素的k(k>8)邻域,并将图像中物体的边界表示为k邻域链码;然后根据曲率定义的差分形式计算各边界点处的曲率;最后通过检测曲率直方图的局部峰值精确定位出拐点,并利用拐角内部像素的颜色统计信息迅速判断出拐点的凸凹性.为验证该算法的效果,给出了该算法与4种已有算法的对比实验.结果表明,该算法不仅稳定性、准确性较高,而且算法简单,实时性强,并适合于嵌入式计算环境。     

Segmentation of color textures

This paper describes an approach to perceptual segmentation of color image textures. A multiscale representation of the texture image, generated by a multiband smoothing algorithm based on human psychophysical measurements of color appearance is used as the input. Initial segmentation is achieved by applying a clustering algorithm to the image at the coarsest level of smoothing. The segmented clusters are then restructured in order to isolate core clusters, i.e., patches in which the pixels are definitely associated with the same region. The image pixels representing the core clusters are used to form 3D color histograms which are then used for probabilistic assignment of all other pixels to the core clusters to form larger clusters and categorise the rest of the image. The process of setting up color histograms and probabilistic reassignment of the pixels to the clusters is then propagated through finer levels of smoothing until a full segmentation is achieved at the highest level of resolution     

结合基因表达式编程与空间模糊聚类的图像分割

目的 针对模糊C-均值聚类图像分割方法存在的对初始值敏感及抗噪性能差的问题,提出一种结合基因表达式编程与空间模糊聚类的图像分割方法。方法 首先,利用基因表达式编程算法对图像进行初次分割,即将聚类中心编码成染色体,通过适应度评价引导搜索获得优化的聚类中心;然后在隶属度计算中引入空间函数,以初次分割结果作为初始值,使用空间模糊聚类对图像进行二次分割。结果 对加噪的合成图像和Berkeley图像的分割实验显示,本文方法在聚类划分系数（VPC）、聚类划分熵（VPE）和峰值信噪比（PSNR）等评价指标上总体性能优于经典的模糊C-均值聚类和空间模糊C-均值聚类分割算法,其中VPC值平均高出0.062 4和0.061 1,VPE值平均降低0.117 0和0.101 1,而PSNR值平均提升了约13.312 1 dB和3.308 4 dB;在对Berkeley图像库中的6幅图片的分割实验显示,本文方法对图像分割的VPC值均在0.93以上,相比两种对比方法平均提高0.157 6和0.013 3,VPE值保持在0.1附近,均低于对比方法,PSNR值平均提高2.896 3 dB和1.934 4 dB;在多目标分割实验上,随着聚类数目增加,3种方法的分割性能均有下降,但本文方法性能曲线最为平缓,受聚类数目的影响最小。虽然本文方法所需的运行时间略有增加,但求解所需的迭代次数却极大地减少。结论 本文提出的图像分割方法具有很强的抗噪性、更高的分割精度和稳定性,适用于需要更精确结果、对时间要求不高的分割场景。     

图像四叉树剖分下的自适应数字水印算法

提出了一种图像四叉树矩形剖分下的自适应数字水印算法。通过对原始图像在多个尺度上进行最小二乘多项式逼近,将图像进行非均匀剖分,并以四叉树结构的形式进行表达。该四叉树结构既实现了对原始图像的逼近,同时携带了图像的纹理结构信息。通过统计各子区域上的剖分网格数目,计算不同区域上水印嵌入的强度,从而实现自适应数字水印方案。实验结果表明,该算法具有良好的透明性和顽健性。     

LoCoPalettes: Local Control for Palette-based Image Editing

Palette-based image editing takes advantage of the fact that color palettes are intuitive abstractions of images. They allow users to make global edits to an image by adjusting a small set of colors. Many algorithms have been proposed to compute color palettes and corresponding mixing weights. However, in many cases, especially in complex scenes, a single global palette may not adequately represent all potential objects of interest. Edits made using a single palette cannot be localized to specific semantic regions. We introduce an adaptive solution to the usability problem based on optimizing RGB palette colors to achieve arbitrary image-space constraints and automatically splitting the image into semantic sub-regions with more representative local palettes when the constraints cannot be satisfied. Our algorithm automatically decomposes a given image into a semantic hierarchy of soft segments. Difficult-to-achieve edits become straightforward with our method. Our results show the flexibility, control, and generality of our method.     

一种快速的图像区域分割算法

提出一种新的快速图像区域分割算法.这种方法首先抽取图像所有像素点的颜色、纹理与位置特征,并将图像划分成子块,以子块内像素点特征的平均值作为子块的特征向量,然后运用Mean shift算法进行聚类,获得聚类簇数和初始蔟中心,最后再利用改进的K均值算法进行聚类,实现图像的快速分割.实验结果表明新方法不仅分割速度快,而且得到的分割结果稳定,避免了过度分割.     

模糊图像中的飞机识别方法

针对模糊图像中飞机识别问题,提出一种基于角点和核聚类的飞机识别方法。该方法提取图像的角点特征,对角点进行核聚类,根据聚类结果识别飞机的角点,完成飞机的定位识别。在核聚类算法中,引入有效性函数,能自适应的确定聚类数目,解决了现有核聚类算法需要事先确定聚类数的弱点。实验表明,角点特征具有位移、旋转、尺度不变性,自适应核聚类算法能准确识别模糊图像中的飞机,具有较好的鲁棒性。     

基于FCM和图割的交互式图像分割方法

为了提高在前景和背景颜色相似情况下图像的分割效果,提出了一种基于模糊C均值聚类（FCM）和图割的交互式图像分割方法。首先,利用分水岭算法对图像进行预处理,将图像分成多个小区域,用区域代替像素点进行分析。然后,采用模糊C均值算法对用户标记的前景区域和背景区域分别进行聚类分析,挖掘用户交互所提供的隐藏信息。用未标记区域的颜色分量到前景区域及背景区域类心的最小距离表示相似能量,用未标记区域与其相邻区域的相关性表示先验能量。最后,利用最大流/最小割算法求能量函数的全局最优解。与其他方法相比,该文方法具有较好的分割性能,能从前景背景相似的图像中较精确地提取感兴趣的物体,且用户操作简单。     

DeepProp: Extracting Deep Features from a Single Image for Edit Propagation

Edit propagation is a technique that can propagate various image edits (e.g., colorization and recoloring) performed via user strokes to the entire image based on similarity of image features. In most previous work, users must manually determine the importance of each image feature (e.g., color, coordinates, and textures) in accordance with their needs and target images. We focus on representation learning that automatically learns feature representations only from user strokes in a single image instead of tuning existing features manually. To this end, this paper proposes an edit propagation method using a deep neural network (DNN). Our DNN, which consists of several layers such as convolutional layers and a feature combiner, extracts stroke‐adapted visual features and spatial features, and then adjusts the importance of them. We also develop a learning algorithm for our DNN that does not suffer from the vanishing gradient problem, and hence avoids falling into undesirable locally optimal solutions. We demonstrate that edit propagation with deep features, without manual feature tuning, can achieve better results than previous work.     

Kernel-induced fuzzy clustering of image pixels with an improved differential evolution algorithm

A modified differential evolution (DE) algorithm is presented for clustering the pixels of an image in the gray-scale intensity space. The algorithm requires no prior information about the number of naturally occurring clusters in the image. It uses a kernel induced similarity measure instead of the conventional sum-of-squares distance. Use of the kernel function makes it possible to partition data that is linearly non-separable and non hyper-spherical in the original input space, into homogeneous groups in a transformed high-dimensional feature space. A novel search-variable representation scheme is adopted for selecting the optimal number of clusters from several possible choices. Extensive performance comparison over a test-suite of 10 gray-scale images and objective comparison with manually segmented ground truth indicates that the proposed algorithm has an edge over a few state-of-the-art algorithms for automatic multi-class image segmentation.