Automatic image segmentation using constraint learning and propagation

In this paper, we propose automatic image segmentation using constraint learning and propagation. Recently, kernel learning is receiving much attention because a learned kernel can fit the given data better than a predefined kernel. To effectively learn the constraints generated by initial seeds for image segmentation, we employ kernel propagation (KP) based on kernel learning. The key idea of KP is first to learn a small-sized seed-kernel matrix and then propagate it into a large-sized full-kernel matrix. By applying KP to automatic image segmentation, we design a novel segmentation method to achieve high performance. First, we generate pairwise constraints, i.e., must-link and cannot-link, from initially selected seeds to make the seed-kernel matrix. To select the optimal initial seeds, we utilize global k-means clustering (GKM) and self-tuning spectral clustering (SSC). Next, we propagate the seed-kernel matrix into the full-kernel matrix of the entire image, and thus image segmentation results are obtained. We test our method on the Berkeley segmentation database, and the experimental results demonstrate that the proposed method is very effective in automatic image segmentation.     

SimLocator: robust locator of similar objects in images

Similar objects commonly appear in natural images, and locating and cutting out these objects can be tedious when using classical interactive image segmentation methods. In this paper, we propose SimLocator, a robust method oriented to locate and cut out similar objects with minimum user interaction. After extracting an arbitrary object template from the input image, candidate locations of similar objects are roughly detected by distinguishing the shape and color features of each image. A novel optimization method is then introduced to select accurate locations from the two sets of candidates. Additionally, a matting-based method is used to improve the results and to ensure that all similar objects are located in the image. Finally, a method based on alpha matting is utilized to extract the precise object contours. To ensure the performance of the matting operation, this work has developed a new method for foreground extraction. Experiments show that SimLocator is more robust and more convenient to use compared to other more advanced repetition detection and interactive image segmentation methods, in terms of locating similar objects in images.     

Two-stage nonparametric kernel leaning: From label propagation to kernel propagation

We introduce a kernel learning algorithm, called kernel propagation (KP), to learn a nonparametric kernel from a mixture of a few pairwise constraints and plentiful unlabeled samples. Specifically, KP consists of two stages: the first is to learn a small-sized sub-kernel matrix just restricted to the samples with constrains, and the second is to propagate this learned sub-kernel matrix into a large-sized full-kernel matrix over all samples. As an interesting fact, our approach exposes a natural connection between KP and label propagation (LP), that is, one LP can naturally induce its KP counterpart. Thus, we develop three KPs from the three typical LPs correspondingly. Following the idea in KP, we also naturally develop an out-of-sample extension to directly capture a kernel matrix for outside-training data without the need of relearning. The final experiments verify that our developments are more efficient, more error-tolerant and also comparably effective in comparison with the state-of-the-art algorithm.     

Robust foreground object segmentation from handheld camera videos with occlusion map

Extracting foreground objects from videos captured by a handheld camera has emerged as a new challenge. While existing approaches aim to exploit several clues such as depth and motion to extract the foreground layer, there are limitations in handling partial movement and cast shadow. In this paper, we bring a novel perspective to address these two issues by utilizing occlusion map introduced by object and camera motion and taking the advantage of interactive image segmentation methods. For partial movement, we treat each video frame as an image and synthesize “seeding” user interactions (i.e., user manually marking foreground and background) with both forward and backward occlusion maps to leverage the advances in high quality interactive image segmentation. For cast shadow, we utilize a paired region based shadow detection method to further refine initial segmentation results by removing detected shadow regions. Experimental results from both qualitative evaluation and quantitative evaluation on the Hopkins dataset demonstrate both the effectiveness and the efficiency of our proposed approach.     

Multiple piecewise constant with geodesic active contours (MPC-GAC) framework for interactive image segmentation using graph cut optimization

This paper proposes an improved variational model, multiple piecewise constant with geodesic active contour (MPC-GAC) model, which generalizes the region-based active contour model by Chan and Vese, 2001 [11] and merges the edge-based active contour by Caselles et al., 1997 [7] to inherit the advantages of region-based and edge-based image segmentation models. We show that the new MPC-GAC energy functional can be iteratively minimized by graph cut algorithms with high computational efficiency compared with the level set framework. This iterative algorithm alternates between the piecewise constant functional learning and the foreground and background updating so that the energy value gradually decreases to the minimum of the energy functional. The k-means method is used to compute the piecewise constant values of the foreground and background of image. We use a graph cut method to detect and update the foreground and background. Numerical experiments show that the proposed interactive segmentation method based on the MPC-GAC model by graph cut optimization can effectively segment images with inhomogeneous objects and background.     

基于区域中心的交互式图像前景提取方法

图像分割是从图像中提取有意义的区域,是图像处理和计算机视觉中的关键技术。而自动分割方法不能很好地处理前景复杂的图像,对此提出一种基于区域中心的交互式图像前景提取算法。针对图像前景的复杂度,很难用单一的相似区域描述前景,文中采用多个区域中心来刻画目标区域。为提升图像分割的稳定性,给出基于超像素颜色、空间位置和纹理信息的相似性度量方法;为确保图像分割区域的连通性和准确性,定义了基于超像素的测地距离计算方法。使用基于测地距离的超像素局部密度,来分析图像的若干区域中心;基于用户交互的方式来分析前景的区域中心,得到图像前景。经过大量彩色图像的仿真表明,在分割过程中利用少量的用户交互信息,可有效提升图像分割的稳定性和准确性。     

A closed-form solution to natural image matting

Interactive digital matting, the process of extracting a foreground object from an image based on limited user input, is an important task in image and video editing. From a computer vision perspective, this task is extremely challenging because it is massively ill-posed -- at each pixel we must estimate the foreground and the background colors, as well as the foreground opacity ("alpha matte") from a single color measurement. Current approaches either restrict the estimation to a small part of the image, estimating foreground and background colors based on nearby pixels where they are known, or perform iterative nonlinear estimation by alternating foreground and background color estimation with alpha estimation.In this paper we present a closed-form solution to natural image matting. We derive a cost function from local smoothness assumptions on foreground and background colors, and show that in the resulting expression it is possible to analytically eliminate the foreground and background colors to obtain a quadratic cost function in alpha. This allows us to find the globally optimal alpha matte by solving a sparse linear system of equations. Furthermore, the closed-form formula allows us to predict the properties of the solution by analyzing the eigenvectors of a sparse matrix, closely related to matrices used in spectral image segmentation algorithms. We show that high quality mattes for natural images may be obtained from a small amount of user input.     

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。     

Image classification without segmentation using a hybrid pyramid kernel

Image classification usually requires complicated segmentation to separate foreground objects from the background scene. However, the statistical content of a background scene can actually provide very useful information for classification. In this paper, we propose a new hybrid pyramid kernel which incorporates local features extracted from both dense regular grids and interest points for image classification, without requiring segmentation. Features extracted from dense regular grids can better capture information about the background scene, while interest points detected at corners and edges can better capture information about the salient objects. In our algorithm, these two local features are combined in both the spatial and the feature-space domains, and are organized into pyramid representations. In order to obtain better classification accuracy, we fine-tune the parameters involved in the similarity measure, and we determine discriminative regions by means of relevance feedback. From the experimental results, we observe that our algorithm can achieve a 6.37 % increase in performance as compared to other pyramid-representation-based methods. To evaluate the applicability of the proposed hybrid kernel to large-scale databases, we have performed a cross-dataset experiment and investigated the effect of foreground/background features on each of the kernels. In particular, the proposed hybrid kernel has been proven to satisfy Mercer’s condition and is efficient in measuring the similarity between image features. For instance, the computational complexity of the proposed hybrid kernel is proportional to the number of features.     

Efficient foreground extraction using RGB-D imaging

Image segmentation is one of the most important topics in the field of computer vision. As a result, many image segmentation approaches have been proposed, and interactive methods based on energy minimization such as GrabCut, have shown successful results. Automating the entire segmentation process is, however, very difficult because virtually all interactive methods require a considerable amount of user interaction. We believe that if additional information is provided to users in order to guide them effectively, the amount of interaction required can be reduced. Consequently, in this paper we propose an efficient foreground extraction algorithm, which utilizes depth information from RGB-D sensors such as Microsoft Kinect and offers users guidance in the foreground extraction process. Our approach can be applied as a pre-processing step for interactive and energy-minimization-based segmentation approaches. Our proposed method is able to segment the foreground from images and give hints that reduce interaction with users. In our method, we make use of the characteristics of depth information captured by RGB-D sensors and describe them using information from the structure tensor. Further, we show experimentally that our proposed method separates foreground from background sufficiently well for real world images.     

渐进式前景更新和区域关联的图像协同分割

目的 图像协同分割技术是通过多幅参考图像以实现前景目标与背景区域的分离，并已被广泛应用于图像分类和目标识别等领域中。不过，现有多数的图像协同分割算法只适用于背景变化较大且前景几乎不变的环境。为此，提出一种新的无监督协同分割算法。方法 本文方法是无监督式的，在分级图像分割的基础上通过渐进式优化框架分别实现前景和背景模型的更新估计，同时结合图像内部和不同图像之间的分级区域相似度关联进一步增强上述模型估计的鲁棒性。该无监督的方法不需要进行预先样本学习，能够同时处理两幅或多幅图像且适用于同时存在多个前景目标的情况，并且能够较好地适应前景物体类的变化。结果 通过基于iCoseg和MSRC图像集的实验证明，该算法无需图像间具有显著的前景和背景差异这一约束，与现有的经典方法相比更适用于前景变化剧烈以及同时存在多个前景目标等更为一般化的图像场景中。结论 该方法通过对分级图像分割得到的超像素外观分布分别进行递归式估计来实现前景和背景的有效区分，并同时融合了图像内部以及不同图像区域之间的区域关联性来增加图像前景和背景分布估计的一致性。实验表明当前景变化显著时本文方法相比于现有方法具有更为鲁棒的表现。     

Assessment of crowdsourcing and gamification loss in user-assisted object segmentation

There has been a growing interest in applying human computation – particularly crowdsourcing techniques – to assist in the solution of multimedia, image processing, and computer vision problems which are still too difficult to solve using fully automatic algorithms, and yet relatively easy for humans. In this paper we focus on a specific problem – object segmentation within color images – and compare different solutions which combine color image segmentation algorithms with human efforts, either in the form of an explicit interactive segmentation task or through an implicit collection of valuable human traces with a game. We use Click’n’Cut, a friendly, web-based, interactive segmentation tool that allows segmentation tasks to be assigned to many users, and Ask’nSeek, a game with a purpose designed for object detection and segmentation. The two main contributions of this paper are: (i) We use the results of Click’n’Cut campaigns with different groups of users to examine and quantify the crowdsourcing loss incurred when an interactive segmentation task is assigned to paid crowd-workers, comparing their results to the ones obtained when computer vision experts are asked to perform the same tasks. (ii) Since interactive segmentation tasks are inherently tedious and prone to fatigue, we compare the quality of the results obtained with Click’n’Cut with the ones obtained using a (fun, interactive, and potentially less tedious) game designed for the same purpose. We call this contribution the assessment of the gamification loss, since it refers to how much quality of segmentation results may be lost when we switch to a game-based approach to the same task. We demonstrate that the crowdsourcing loss is significant when using all the data points from workers, but decreases substantially (and becomes comparable to the quality of expert users performing similar tasks) after performing a modest amount of data analysis and filtering out of users whose data are clearly not useful. We also show that – on the other hand – the gamification loss is significantly more severe: the quality of the results drops roughly by half when switching from a focused (yet tedious) task to a more fun and relaxed game environment.     

Robust interactive image segmentation using structure-aware labeling

Interactive image segmentation has remained an active research topic in image processing and graphics, since the user intention can be incorporated to enhance the performance. It can be employed to mobile devices which now allow user interaction as an input, enabling various applications. Most interactive segmentation methods assume that the initial labels are correctly and carefully assigned to some parts of regions to segment. Inaccurate labels, such as foreground labels in background regions for example, lead to incorrect segments, even by a small number of inaccurate labels, which is not appropriate for practical usage such as mobile application. In this paper, we present an interactive segmentation method that is robust to inaccurate initial labels (scribbles). To address this problem, we propose a structure-aware labeling method using occurrence and co-occurrence probability (OCP) of color values for each initial label in a unified framework. Occurrence probability captures a global distribution of all color values within each label, while co-occurrence one encodes a local distribution of color values around the label. We show that nonlocal regularization together with the OCP enables robust image segmentation to inaccurately assigned labels and alleviates a small-cut problem. We analyze theoretic relations of our approach to other segmentation methods. Intensive experiments with synthetic and manual labels show that our approach outperforms the state of the art.     

自动交互图像分割中的贝叶斯网络模型构建

由于贝叶斯模型和各种图像测量结果,置信传播会更新每个节点的相关概率,提出了在自动交互图像分割过程中应用的新型贝叶斯网络模型。从过度分割模型中的超级像素点区域、边区域、顶点和测量结果之间的统计相关性来构造多层贝叶斯网络模型。除了自动图像分割,贝叶斯网络模型也可用于交互式图像分割中,现有交互分割往往被动地依靠用户提供的准确调整,提出新型主动输入选择方式作为准确调整。实验采用Weizmann数据集和VOC 2006图像集来评估,实验结果表明贝叶斯网络模型可以进行效果更好的自动分割,主动输入选择可以提高整体分割精度。     

Video chroma keying via global sampling and trimap propagation

Chroma keying is a widely used video editing technique, which finely separates the foreground objects from the background. Two major concerns are involved in chroma keying problems: alpha estimation and foreground color restoration. The alpha values reveal the opacity property of the foreground objects. The foreground color restoration removes the background color influence to the foreground appearance especially at transparent regions and objects’ boundaries. In this paper, the color range of the solid background is well analyzed to automatically separate foreground from background. Global sampling is utilized to robustly and reliably estimate the foreground color at boundaries and transparent regions. Furthermore, we propose to propagate the geometric shape of foreground boundaries between adjacent frames by using optical flow and thin plate splines interpolation. The trimap, which is an initial foreground/background/unknown segmentation of each frame can be automatically updated for each video frame by using our proposed propagation method. Compared to previous methods, our proposed matting method estimates high-quality alpha matte and reliable foreground color with least user interference.     

Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking

Appearance modeling is very important for background modeling and object tracking. Subspace learning-based algorithms have been used to model the appearances of objects or scenes. Current vector subspace-based algorithms cannot effectively represent spatial correlations between pixel values. Current tensor subspace-based algorithms construct an offline representation of image ensembles, and current online tensor subspace learning algorithms cannot be applied to background modeling and object tracking. In this paper, we propose an online tensor subspace learning algorithm which models appearance changes by incrementally learning a tensor subspace representation through adaptively updating the sample mean and an eigenbasis for each unfolding matrix of the tensor. The proposed incremental tensor subspace learning algorithm is applied to foreground segmentation and object tracking for grayscale and color image sequences. The new background models capture the intrinsic spatiotemporal characteristics of scenes. The new tracking algorithm captures the appearance characteristics of an object during tracking and uses a particle filter to estimate the optimal object state. Experimental evaluations against state-of-the-art algorithms demonstrate the promise and effectiveness of the proposed incremental tensor subspace learning algorithm, and its applications to foreground segmentation and object tracking.     

Interactive image segmentation by maximal similarity based region merging

Efficient and effective image segmentation is an important task in computer vision and object recognition. Since fully automatic image segmentation is usually very hard for natural images, interactive schemes with a few simple user inputs are good solutions. This paper presents a new region merging based interactive image segmentation method. The users only need to roughly indicate the location and region of the object and background by using strokes, which are called markers. A novel maximal-similarity based region merging mechanism is proposed to guide the merging process with the help of markers. A region R is merged with its adjacent region Q if Q has the highest similarity with Q among all Q's adjacent regions. The proposed method automatically merges the regions that are initially segmented by mean shift segmentation, and then effectively extracts the object contour by labeling all the non-marker regions as either background or object. The region merging process is adaptive to the image content and it does not need to set the similarity threshold in advance. Extensive experiments are performed and the results show that the proposed scheme can reliably extract the object contour from the complex background.     

Adaptive propagation matting based on transparency of image

Image matting is an essential technique in many image and video editing applications. Although many matting methods have been proposed, it is still a challenge for most to obtain satisfactory matting results in the transparent foreground region of an image. To solve this problem, this paper proposes a novel matting algorithm, i.e. adaptive transparency-based propagation matting (ATPM) algorithm. ATPM algorithm considers image matting from a new slant. We pay attention to the transparencies of the input images and creatively assign them into three categories (highly transparent, strongly transparent and little transparent) according to the transparencies of the foreground objects in the images. Our matting model can make relevant adjustment in terms of the transparency types of the input images. Moreover, many current matting methods do not perform well when the foreground and background regions have similar color distributions. Our method adds texture as an additional feature to effectively discriminate the foreground and background regions. Experimental results on the benchmark dataset show that our method gets high-quality matting results for images of three transparency types, especially provides more accurate results for highly transparent images comparing with the state-of-the-art methods.     

形状模板约束的图像协同分割

已有的协同分割方法没有考虑到同一类图像所具有的目标形状相似性,从而使得分割结果不一致。提出了形状模板约束的图像交互协同分割算法,通过少量用户交互提高协同分割质量。该算法首先定义形状模板;然后通过形状上下文实现分割结果传递,自动形成图像分割所需的前景和背景掩码;最后采用最小割理论进行分割边界优化。实验结果表明,与已有的协同分割算法相比,该算法能在简单用户交互下明显提高分割质量,使分割结果更具有语义性。