Showing papers on "Segmentation-based object categorization published in 2009"

A benchmark for 3D mesh segmentation

Abstract: This paper describes a benchmark for evaluation of 3D mesh segmentation salgorithms. The benchmark comprises a data set with 4,300 manually generated segmentations for 380 surface meshes of 19 different object categories, and it includes software for analyzing 11 geometric properties of segmentations and producing 4 quantitative metrics for comparison of segmentations. The paper investigates the design decisions made in building the benchmark, analyzes properties of human-generated and computer-generated segmentations, and provides quantitative comparisons of 7 recently published mesh segmentation algorithms. Our results suggest that people are remarkably consistent in the way that they segment most 3D surface meshes, that no one automatic segmentation algorithm is better than the others for all types of objects, and that algorithms based on non-local shape features seem to produce segmentations that most closely resemble ones made by humans.

Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data

Abstract: It has been shown that employing multiple atlas images improves segmentation accuracy in atlas-based medical image segmentation. Each atlas image is registered to the target image independently and the calculated transformation is applied to the segmentation of the atlas image to obtain a segmented version of the target image. Several independent candidate segmentations result from the process, which must be somehow combined into a single final segmentation. Majority voting is the generally used rule to fuse the segmentations, but more sophisticated methods have also been proposed. In this paper, we show that the use of global weights to ponderate candidate segmentations has a major limitation. As a means to improve segmentation accuracy, we propose the generalized local weighting voting method. Namely, the fusion weights adapt voxel-by-voxel according to a local estimation of segmentation performance. Using digital phantoms and MR images of the human brain, we demonstrate that the performance of each combination technique depends on the gray level contrast characteristics of the segmented region, and that no fusion method yields better results than the others for all the regions. In particular, we show that local combination strategies outperform global methods in segmenting high-contrast structures, while global techniques are less sensitive to noise when contrast between neighboring structures is low. We conclude that, in order to achieve the highest overall segmentation accuracy, the best combination method for each particular structure must be selected.

Multi-Atlas-Based Segmentation With Local Decision Fusion—Application to Cardiac and Aortic Segmentation in CT Scans

Abstract: A novel atlas-based segmentation approach based on the combination of multiple registrations is presented. Multiple atlases are registered to a target image. To obtain a segmentation of the target, labels of the atlas images are propagated to it. The propagated labels are combined by spatially varying decision fusion weights. These weights are derived from local assessment of the registration success. Furthermore, an atlas selection procedure is proposed that is equivalent to sequential forward selection from statistical pattern recognition theory. The proposed method is compared to three existing atlas-based segmentation approaches, namely (1) single atlas-based segmentation, (2) average-shape atlas-based segmentation, and (3) multi-atlas-based segmentation with averaging as decision fusion. These methods were tested on the segmentation of the heart and the aorta in computed tomography scans of the thorax. The results show that the proposed method outperforms other methods and yields results very close to those of an independent human observer. Moreover, the additional atlas selection step led to a faster segmentation at a comparable performance.

Image Segmentation - A Survey of Soft Computing Approaches

Abstract: Soft Computing is an emerging field that consists of complementary elements of fuzzy logic, neural computing and evolutionary computation. Soft computing techniques have found wide applications. One of the most important applications is image segmentation. The process of partitioning a digital image into multiple regions or sets of pixels is called image segmentation. Segmentation is an essential step in image processing since it conditions the quality of the resulting interpretation. Lots of approaches have been proposed and a dense literature is available In order to extract as much information as possible from an environment, multicomponent images can be used. In the last decade, multicomponent images segmentation has received a great deal of attention for soft computing applications because it significantly improves the discrimination and the recognition capabilities compared with gray-level image segmentation methods. In this paper, the main aim is to understand the soft computing approach to image segmentation.

Edge Detection Techniques for Image Segmentation - A Survey of Soft Computing Approaches

Abstract: Soft Computing is an emerging field that consists of complementary elements of fuzzy logic, neural computing and evolutionary computation. Soft computing techniques have found wide applications. One of the most important applications is edge detection for image segmentation. The process of partitioning a digital image into multiple regions or sets of pixels is called image segmentation. Edge is a boundary between two homogeneous regions. Edge detection refers to the process of identifying and locating sharp discontinuities in an image. In this paper, the main aim is to survey the theory of edge detection for image segmentation using soft computing approach based on the Fuzzy logic, Genetic Algorithm and Neural Network.

Saliency driven total variation segmentation

Abstract: This paper introduces an unsupervised color segmentation method The underlying idea is to segment the input image several times, each time focussing on a different salient part of the image and to subsequently merge all obtained results into one composite segmentation We identify salient parts of the image by applying affinity propagation clustering to efficiently calculated local color and texture models Each salient region then serves as an independent initialization for a figure/ground segmentation Segmentation is done by minimizing a convex energy functional based on weighted total variation leading to a global optimal solution Each salient region provides an accurate figure/ ground segmentation highlighting different parts of the image These highly redundant results are combined into one composite segmentation by analyzing local segmentation certainty Our formulation is quite general, and other salient region detection algorithms in combination with any semi-supervised figure/ground segmentation approach can be used We demonstrate the high quality of our method on the well-known Berkeley segmentation database Furthermore we show that our method can be used to provide good spatial support for recognition frameworks

The Comparative Research on Image Segmentation Algorithms

Abstract: As the premise of feature extraction and pattern recognition, image segmentation is one of the fundamental approaches of digital image processing. This paper enumerates and reviews main image segmentation algorithms, then presents basic evaluation methods for them, finally discusses the prospect of image segmentation. Some valuable characteristics of image segmentation come out after a large number of comparative experiments.

Nuclear segmentation in microscope cell images: A hand-segmented dataset and comparison of algorithms

Abstract: Image segmentation is an essential step in many image analysis pipelines and many algorithms have been proposed to solve this problem. However, they are often evaluated subjectively or based on a small number of examples. To fill this gap, we hand-segmented a set of 97 fluorescence microscopy images (a total of 4009 cells) and objectively evaluated some previously proposed segmentation algorithms.

Medical Image Segmentation Using Genetic Algorithms

Abstract: Genetic algorithms (GAs) have been found to be effective in the domain of medical image segmentation, since the problem can often be mapped to one of search in a complex and multimodal landscape. The challenges in medical image segmentation arise due to poor image contrast and artifacts that result in missing or diffuse organ/tissue boundaries. The resulting search space is therefore often noisy with a multitude of local optima. Not only does the genetic algorithmic framework prove to be effective in coming out of local optima, it also brings considerable flexibility into the segmentation procedure. In this paper, an attempt has been made to review the major applications of GAs to the domain of medical image segmentation.

Anisotropic Mean Shift Based Fuzzy C-Means Segmentation of Dermoscopy Images

Abstract: Image segmentation is an important task in analysing dermoscopy images as the extraction of the borders of skin lesions provides important cues for accurate diagnosis. One family of segmentation algorithms is based on the idea of clustering pixels with similar characteristics. Fuzzy c-means has been shown to work well for clustering based segmentation, however due to its iterative nature this approach has excessive computational requirements. In this paper, we introduce a new mean shift based fuzzy c-means algorithm that requires less computational time than previous techniques while providing good segmentation results. The proposed segmentation method incorporates a mean field term within the standard fuzzy c-means objective function. Since mean shift can quickly and reliably find cluster centers, the entire strategy is capable of effectively detecting regions within an image. Experimental results on a large dataset of diverse dermoscopy images demonstrate that the presented method accurately and efficiently detects the borders of skin lesions.

Benchmarking Image Segmentation Algorithms

Abstract: We present a thorough quantitative evaluation of four image segmentation algorithms on images from the Berkeley Segmentation Database. The algorithms are evaluated using an efficient algorithm for computing precision and recall with regard to human ground-truth boundaries. We test each segmentation method over a representative set of input parameters, and present tuning curves that fully characterize algorithm performance over the complete image database. We complement the evaluation on the BSD with segmentation results on synthetic images. The results reported here provide a useful benchmark for current and future research efforts in image segmentation.

Region-based Segmentation and Object Detection

Abstract: Object detection and multi-class image segmentation are two closely related tasks that can be greatly improved when solved jointly by feeding information from one task to the other [10, 11]. However, current state-of-the-art models use a separate representation for each task making joint inference clumsy and leaving the classification of many parts of the scene ambiguous. In this work, we propose a hierarchical region-based approach to joint object detection and image segmentation. Our approach simultaneously reasons about pixels, regions and objects in a coherent probabilistic model. Pixel appearance features allow us to perform well on classifying amorphous background classes, while the explicit representation of regions facilitate the computation of more sophisticated features necessary for object detection. Importantly, our model gives a single unified description of the scene—we explain every pixel in the image and enforce global consistency between all random variables in our model. We run experiments on the challenging Street Scene dataset [2] and show significant improvement over state-of-the-art results for object detection accuracy.

Spectral clustering of linear subspaces for motion segmentation

Abstract: This paper studies automatic segmentation of multiple motions from tracked feature points through spectral embedding and clustering of linear subspaces We show that the dimension of the ambient space is crucial for separability, and that low dimensions chosen in prior work are not optimal We suggest lower and upper bounds together with a data-driven procedure for choosing the optimal ambient dimension Application of our approach to the Hopkins155 video benchmark database uniformly outperforms a range of state-of-the-art methods both in terms of segmentation accuracy and computational speed

Globally optimal segmentation of multi-region objects

Abstract: Many objects contain spatially distinct regions, each with a unique colour/texture model. Mixture models ignore the spatial distribution of colours within an object, and thus cannot distinguish between coherent parts versus randomly distributed colours. We show how to encode geometric interactions between distinct region+boundary models, such as regions being interior/exterior to each other along with preferred distances between their boundaries. With a single graph cut, our method extracts only those multi-region objects that satisfy such a combined model. We show applications in medical segmentation and scene layout estimation. Unlike Li et al. [17] we do not need “domain unwrapping” nor do we have topological limits on shapes.

Multi-class image segmentation using conditional random fields and global classification

Abstract: A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentation which combines two methods for this integration: a Conditional Random Field (CRF) which couples to local image features and an image classification method which considers global features. The CRF follows the approach of Reynolds & Murphy (2007) and is based on an unsupervised multi scale pre-segmentation of the image into patches, where patch labels correspond to the random variables of the CRF. The output of the classifier is used to constraint this CRF. We demonstrate and compare the approach on a standard semantic segmentation data set.

Active segmentation with fixation

Abstract: The human visual system observes and understands a scene/image by making a series of fixations. Every “fixation point” lies inside a particular region of arbitrary shape and size in the scene which can either be an object or just a part of it. We define as a basic segmentation problem the task of segmenting that region containing the “fixation point”. Segmenting this region is equivalent to finding the enclosing contour - a connected set of boundary edge fragments in the edge map of the scene - around the fixation. We present here a novel algorithm that finds this bounding contour and achieves the segmentation of one object, given the fixation. The proposed segmentation framework combines monocular cues (color/intensity/texture) with stereo and/or motion, in a cue independent manner. We evaluate the performance of the proposed algorithm on challenging videos and stereo pairs. Although the proposed algorithm is more suitable for an active observer capable of fixating at different locations in the scene, it applies to a single image as well. In fact, we show that even with monocular cues alone, the introduced algorithm performs as well or better than a number of image segmentation algorithms, when applied to challenging inputs.

Adaptive fuzzy moving K-means clustering algorithm for image segmentation

Abstract: Image segmentation remains one of the major challenges in image analysis. Many segmentation algorithms have been developed for various applications. Unsatisfactory results have been encountered in some cases, for many existing segmentation algorithms. In this paper, we introduce three modified versions of the conventional moving k-means clustering algorithm called the fuzzy moving k-means, adaptive moving k-means and adaptive fuzzy moving k-means algorithms for image segmentation application. Based on analysis done using standard images (i.e. original bridge and noisy bridge) and hard evidence on microscopic digital image (i.e. segmentation of Sprague Dawley rat sperm), our final segmentation results compare favorably with the results obtained by the conventional k-means, fuzzy c-means and moving k-means algorithms. The qualitative and quantitative analysis done proved that the proposed algorithms are less sensitive with respect to noise. As such, the occurrence of dead centers, center redundancy and trapped center at local minima problems can be avoided. The proposed clustering algorithms are also less sensitive to initialization process of clustering value. The final center values obtained are located within their respective groups of data. This enabled the size and shape of the object in question to be maintained and preserved. Based on the simplicity and capabilities of the proposed algorithms, these algorithms are suitable to be implemented in consumer electronics products such as digital microscope, or digital camera as post processing tool for digital images.

PWP3D: Real-time Segmentation and Tracking of 3D Objects.

Abstract: We formulate a probabilistic framework for simultaneous region-based 2D segmentation and 2D to 3D pose tracking, using a known 3D model. Given such a model, we aim to maximise the discrimination between statistical foreground and background appearance models, via direct optimisation of the 3D pose parameters. The foreground region is delineated by the zero-level-set of a signed distance embedding function, and we define an energy over this region and its immediate background surroundings based on pixel-wise posterior membership probabilities (as opposed to likelihoods). We derive the differentials of this energy with respect to the pose parameters of the 3D object, meaning we can conduct a search for the correct pose using standard gradient-based non-linear minimisation techniques. We propose novel enhancements at the pixel level based on temporal consistency and improved online appearance model adaptation. Furthermore, straightforward extensions of our method lead to multi-camera and multi-object tracking as part of the same framework. The parallel nature of much of the processing in our algorithm means it is amenable to GPU acceleration, and we give details of our real-time implementation, which we use to generate experimental results on both real and artificial video sequences, with a number of 3D models. These experiments demonstrate the benefit of using pixel-wise posteriors rather than likelihoods, and showcase the qualities, such as robustness to occlusions and motion blur (and also some failure modes), of our tracker.

Maximin affinity learning of image segmentation

Abstract: Images can be segmented by first using a classifier to predict an affinity graph that reflects the degree to which image pixels must be grouped together and then partitioning the graph to yield a segmentation. Machine learning has been applied to the affinity classifier to produce affinity graphs that are good in the sense of minimizing edge misclassification rates. However, this error measure is only indirectly related to the quality of segmentations produced by ultimately partitioning the affinity graph. We present the first machine learning algorithm for training a classifier to produce affinity graphs that are good in the sense of producing segmentations that directly minimize the Rand index, a well known segmentation performance measure. The Rand index measures segmentation performance by quantifying the classification of the connectivity of image pixel pairs after segmentation. By using the simple graph partitioning algorithm of finding the connected components of the thresholded affinity graph, we are able to train an affinity classifier to directly minimize the Rand index of segmentations resulting from the graph partitioning. Our learning algorithm corresponds to the learning of maximin affinities between image pixel pairs, which are predictive of the pixel-pair connectivity.

Natural image segmentation with adaptive texture and boundary encoding

Abstract: We present a novel algorithm for unsupervised segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. Our algorithm achieves state-of-the-art results on the Berkeley Segmentation Dataset compared to other popular methods.

Single image defocus map estimation using local contrast prior

Abstract: Image defocus estimation is useful for several applications including deblurring, blur magnification, measuring image quality, and depth of field segmentation. In this paper, we present a simple yet effective approach for estimating a defocus blur map based on the relationship of the contrast to the image gradient in a local image region. We call this relationship the local contrast prior. The advantage of our approach is that it does not require filter banks or frequency decomposition of the input image; instead we only need to compare local gradient profiles with the local contrast. We discuss the idea behind the local contrast prior and demonstrate its effectiveness on a variety of experiments.

Robust fuzzy clustering-based image segmentation

Abstract: The fuzzy clustering algorithm fuzzy c-means (FCM) is often used for image segmentation. When noisy image segmentation is required, FCM should be modified such that it can be less sensitive to noise in an image. In this correspondence, a robust fuzzy clustering-based segmentation method for noisy images is developed. The contribution of the study here is twofold: (1) we derive a robust modified FCM in the sense of a novel objective function. The proposed modified FCM here is proved to be equivalent to the modified FCM given by Hoppner and Klawonn [F. Hoppner, F. Klawonn, Improved fuzzy partitions for fuzzy regression models, Int. J. Approx. Reason. 32 (2) (2003) 85-102]. (2) We explore the very applicability of the proposed modified FCM for noisy image segmentation. Our experimental results indicate that the proposed modified FCM here is very suitable for noisy image segmentation.

FLoSS: Facility location for subspace segmentation

Abstract: Subspace segmentation is the task of segmenting data lying on multiple linear subspaces. Its applications in computer vision include motion segmentation in video, structure-from-motion, and image clustering. In this work, we describe a novel approach for subspace segmentation that uses probabilistic inference via a message-passing algorithm.