Hierarchical Segmentation Research Articles

Multispectral Cooperative Partition Sequence Fusion for Joint Classification and Hierarchical Segmentation

In this letter, a region-based fusion methodology is presented for joint classification and hierarchical segmentation of specific ground cover classes from high-spatial-resolution remote sensing images. Multispectral information is fused at the partition level using nonlinear techniques, which allows the different relevance of the various bands to be fully exploited. A hierarchical segmentation is performed for each individual band, and the ensuing segmentation results are fused in an iterative and cooperative way. At each iteration, a consensus partition is obtained based on information theory and is combined with a specific ground cover classification. Here, the proposed approach is applied to the extraction and segmentation of vegetation areas. The result is a hierarchy of partitions with the most relevant information of the vegetation areas at different levels of resolution. This system has been tested for vegetation analysis in high-spatial-resolution images from the QuickBird and GeoEye satellites.

Best Merge Region-Growing Segmentation With Integrated Nonadjacent Region Object Aggregation

Best merge region growing normally produces segmentations with closed connected region objects. Recognizing that spectrally similar objects often appear in spatially separate locations, we present an approach for tightly integrating best merge region growing with nonadjacent region object aggregation, which we call hierarchical segmentation or HSeg. However, the original implementation of nonadjacent region object aggregation in HSeg required excessive computing time even for moderately sized images because of the required intercomparison of each region with all other regions. This problem was previously addressed by a recursive approximation of HSeg, called RHSeg. In this paper, we introduce a refined implementation of nonadjacent region object aggregation in HSeg that reduces the computational requirements of HSeg without resorting to the recursive approximation. In this refinement, HSeg's region intercomparisons among nonadjacent regions are limited to regions of a dynamically determined minimum size. We show that this refined version of HSeg can process moderately sized images in about the same amount of time as RHSeg incorporating the original HSeg. Nonetheless, RHSeg is still required for processing very large images due to its lower computer memory requirements and amenability to parallel processing. We then note a limitation of RHSeg with the original HSeg for high spatial resolution images and show how incorporating the refined HSeg into RHSeg overcomes this limitation. The quality of the image segmentations produced by the refined HSeg is then compared with other available best merge segmentation approaches. Finally, we comment on the unique nature of the hierarchical segmentations produced by HSeg.

Predicting topic shift locations in design histories

Knowing the locations of weak-to-strong topic shifts in a design history enables hierarchical segmentation of that history. The segmentation can be the basis of hierarchical visualization, that is, semantic zoom, and more, such as visualization of co-location, co-citation, and density of linking. This research shows that a fine-grained, sub-topical linkograph of a design conversation can be used to identify the locations of topic shifts in that conversation. A design conversation spanning 11 design meetings was captured; deictic (pointing-like) references were simulated by performing a sentence-by-sentence-level linkograph analysis of the conversation (that is, the conversation was not subjectively aggregated to topical segments prior to analysis); an algorithm used the linkograph to predict the locations of topic shifts; and the linkograph-predicted topic shift locations were compared with expected topic shift locations for the same conversation. The expected topic shift locations were defined as the heads of reference series (references to transcript units) that were made in a detailed report about the meetings. The model performed well (63–80 %) on large reference series (quartiles three and four) and poorly on small reference series (quartiles one and two, and singular references). Future research will work with linkographs that are automatically constructed by both text-based and graphic design systems and aim to develop a framework that can adapt to individual histories.

Volume based mesh segmentation

Mesh segmentation has become a key ingredient in many mesh applications in computer graphics. In this paper, we propose a hierarchical segmentation that decomposes a polygonal object into meaningful parts in such a way that not only components on a higher level reveal higher degree of salience than their descendant parts but also the components on each level of hierarchy have similar degree of salience. Moreover, the number of boundaries on each level of the hierarchy is determined automatically. The proposed segmentation is based on the Minimum Slice Perimeter (MSP) function [1], which represents non-local shape features and has better interpretation for the object parts. The gradient of MSP function is used to locate the segmentation regions and a new measure of part salience is proposed to evaluate the significance of the segmentation regions. For each level of hierarchy, some most perceptually significant segmentation regions are selected based on their salience measures and boundaries are then computed from the selected segmentation regions by using a capacity that considers both the curvature and MSP gradient.

Nhs: network-based hierarchical segmentation for cryo-electron microscopy density maps.

Cryo-electron microscopy (cryo-EM) experiments yield low-resolution (3-30 Å) 3D-density maps of macromolecules. These density maps are segmented to identify structurally distinct proteins, protein domains, and subunits. Such partitioning aids the inference of protein motions and guides fitting of high-resolution atomistic structures. Cryo-EM density map segmentation has traditionally required tedious and subjective manual partitioning or semisupervised computational methods, whereas validation of resulting segmentations has remained an open problem in this field. We introduce a network-based hierarchical segmentation (Nhs) method, that provides a multi-scale partitioning, reflecting local and global clustering, while requiring no user input. This approach models each map as a graph, where map voxels constitute nodes and weighted edges connect neighboring voxels. Nhs initiates Markov diffusion (or random walk) on the weighted graph. As Markov probabilities homogenize through diffusion, an intrinsic segmentation emerges. We validate the segmentations with ground-truth maps based on atomistic models. When implemented on density maps in the 2010 Cryo-EM Modeling Challenge, Nhs efficiently and objectively partitions macromolecules into structurally and functionally relevant subregions at multiple scales.

Unsupervised segmentation and classification of cervical cell images

The Pap smear test is a manual screening procedure that is used to detect precancerous changes in cervical cells based on color and shape properties of their nuclei and cytoplasms. Automating this procedure is still an open problem due to the complexities of cell structures. In this paper, we propose an unsupervised approach for the segmentation and classification of cervical cells. The segmentation process involves automatic thresholding to separate the cell regions from the background, a multi-scale hierarchical segmentation algorithm to partition these regions based on homogeneity and circularity, and a binary classifier to finalize the separation of nuclei from cytoplasm within the cell regions. Classification is posed as a grouping problem by ranking the cells based on their feature characteristics modeling abnormality degrees. The proposed procedure constructs a tree using hierarchical clustering, and then arranges the cells in a linear order by using an optimal leaf ordering algorithm that maximizes the similarity of adjacent leaves without any requirement for training examples or parameter adjustment. Performance evaluation using two data sets show the effectiveness of the proposed approach in images having inconsistent staining, poor contrast, and overlapping cells.

Recursive hierarchic segmentation analysis of bone mineral density changes on digital panoramic images

The aim of this study was to demonstrate that histogram analysis and mathematical modeling of digital panoramic images (DPIs) processed using recursive hierarchic segmentation (RHSEG) discriminates normal, osteopenic, and osteoporotic cancellous bone. Forty-seven DPIs of postmenopausal women were grouped into normal, osteopenic, and osteoporotic; dual-energy x-ray absorptiometry was the reference standard. RHSEG of the mandibular angle and canine/premolar trabecular regions of interest was performed. After histogram and histogram bin analysis and generation of relative intensity functions, generalized linear mixed model analysis was used to model the data and likelihood ratio testing used to assess group differences. Histogram analyses discriminated among the groups. Receiver operating characteristic analysis of the canine/premolar data yielded area-under-the-curve accuracies of 0.78 for osteoporosis and 0.74 for osteopenia. Discrimination of osteoporosis required cubic analysis, discrimination of osteopenia required quartic analysis, and neither model alone discriminated among all groups. Analyses and mathematical modeling of mandibular trabecular bone on RHSEG-processed DPIs discriminated normal, osteoporotic, and osteopenic patients.

Adaptive dichotomous image segmentation toolkit

The article deals with the adaptive hierarchical segmentation of the digital image divided into segments of the calculated form. The dichotomous segmentation is examined, in which case the vast majority of segments are divided into two nested segments. A method is described for the rapid construction of a dichotomous hierarchy by a given criterion for the proximity of segments by the iterative merging of adjacent segments of an initial image decomposition. The numerical characteristic of the regularity of the dichotomous hierarchy of segments is introduced. Variants are constructed of the hierarchical approximation of the image by nested partitions (levels of the hierarchy) formed from the segments with repetitions. Three basic types of transformations are determined on the set of hierarchical decompositions. In order to optimize the approximation of visible objects by image segments, 22 algorithms are studied of its partition to successively increase the number of segments. Depending on the number of segments, the required standard deviation is estimated. A comparison with similar solutions is given.

A Marker-Based Approach for the Automated Selection of a Single Segmentation From a Hierarchical Set of Image Segmentations

The Hierarchical SEGmentation (HSEG) algorithm, which combines region object finding with region object clustering, has given good performances for multi- and hyperspectral image analysis. This technique produces at its output a hierarchical set of image segmentations. The automated selection of a single segmentation level is often necessary. We propose and investigate the use of automatically selected markers for this purpose. In this paper, a novel Marker-based HSEG (M-HSEG) method for spectral-spatial classification of hyperspectral images is proposed. Two classification-based approaches for automatic marker selection are adapted and compared for this purpose. Then, a novel constrained marker-based HSEG algorithm is applied, resulting in a spectral-spatial classification map. Three different implementations of the M-HSEG method are proposed and their performances in terms of classification accuracies are compared. The experimental results, presented for three hyperspectral airborne images, demonstrate that the proposed approach yields accurate segmentation and classification maps, and thus is attractive for remote sensing image analysis.

Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration

We present a bottom-up aggregation approach to image segmentation. Beginning with an image, we execute a sequence of steps in which pixels are gradually merged to produce larger and larger regions. In each step, we consider pairs of adjacent regions and provide a probability measure to assess whether or not they should be included in the same segment. Our probabilistic formulation takes into account intensity and texture distributions in a local area around each region. It further incorporates priors based on the geometry of the regions. Finally, posteriors based on intensity and texture cues are combined using “a mixture of experts” formulation. This probabilistic approach is integrated into a graph coarsening scheme, providing a complete hierarchical segmentation of the image. The algorithm complexity is linear in the number of the image pixels and it requires almost no user-tuned parameters. In addition, we provide a novel evaluation scheme for image segmentation algorithms, attempting to avoid human semantic considerations that are out of scope for segmentation algorithms. Using this novel evaluation scheme, we test our method and provide a comparison to several existing segmentation algorithms.

Topic-Based Hierarchical Segmentation

Latent Dirichlet allocation (LDA) is a new paradigm of topic model which is powerful to capture the latent topic information from natural language. However, the topic information in text streams, e.g. meeting recording, lecture transcription and conversational dialogue, are inherently heterogeneous and nonstationary without explicit boundaries. It is difficult to train a precise topic model from the observed text streams. Furthermore, the usage of words in different paragraphs within a document is varied with different composition styles. In this paper, we present a new hierarchical segmentation model (HSM) where the heterogeneous topic information in stream level and the word variations in document level are characterized. We incorporate the contextual topic information in stream-level segmentation. The topic similarity between sentences is used to form a beta distribution reflecting the prior knowledge of document boundaries in a text stream. The distribution of segmentation variable is adaptively updated to achieve flexible segmentation and is used to group coherent sentences into a topic-specific document. For each pseudo-document, we further use a Markov chain to detect the stylistic segments within a document. The words in a segment are accordingly generated by the same composition style, which differs from the style of the next segment. Each segment is represented by a Markov state, and so the word variations within a document are compensated. The whole model is trained by a variational Bayesian EM procedure and is evaluated on using TDT2 corpus. Experimental results show benefits by using the proposed HSM in terms of perplexity, segmentation error, detection accuracy and F measure.

Hierarchical Statistical Shape Models of Multiobject Anatomical Structures: Application to Brain MRI

The accurate segmentation of subcortical brain structures in magnetic resonance (MR) images is of crucial importance in the interdisciplinary field of medical imaging. Although statistical approaches such as active shape models (ASMs) have proven to be particularly useful in the modeling of multiobject shapes, they are inefficient when facing challenging problems. Based on the wavelet transform, the fully generic multiresolution framework presented in this paper allows us to decompose the interobject relationships into different levels of detail. The aim of this hierarchical decomposition is twofold: to efficiently characterize the relationships between objects and their particular localities. Experiments performed on an eight-object structure defined in axial cross sectional MR brain images show that the new hierarchical segmentation significantly improves the accuracy of the segmentation, and while it exhibits a remarkable robustness with respect to the size of the training set.

Integrating multiple cues into adaptive hierarchical segmentation for high-resolution remote-sensing images

Image segmentation has been, and still is, a hot research topic in computer vision and pattern recognition. However, few existing segmentation algorithms are suitable for all objects presented in high-resolution remote-sensing (HRRS) images, because the relevant methods often implement segmentation in the same mode for the whole image rather than considering the different characteristics of various objects. Therefore, this article proposes an adaptive hierarchical segmentation framework for HRRS images by integrating multiple cues (e.g. intensity, texture and boundary). This two-stage framework first analyses the class of region presented in the study image, then according to this analysis, partitions each region class by adaptively utilizing the proper segmentation method with the most representative features. The distinctive characteristics of this framework are that the first stage simplifies the problem before using the segmentation method, and the second stage guarantees that the segmentation is carried out with the representative cues and corresponding suitable method for these cues. The performance of the proposed segmentation framework is demonstrated through a complete set of experimental results and substantiated using quantitative criteria.

A Maximum-Entropy Segmentation Model for Statistical Machine Translation

Segmentation is of great importance to statistical machine translation. It splits a source sentence into sequences of translatable segments. We propose a maximum-entropy segmentation model to capture desirable phrasal and hierarchical segmentations for statistical machine translation. We present an approach to automatically learning the beginning and ending boundaries of cohesive segments from word-aligned bilingual data without using any additional resources. The learned boundaries are then used to define cohesive segments in both phrasal and hierarchical segmentations. We integrate the segmentation model into phrasal statistical machine translation (SMT) and conduct experiments on the newswire and broadcast news domain to investigate the effectiveness of the proposed segmentation model on a large-scale training data. Our experimental results show that the maximum-entropy segmentation model significantly improves translation quality in terms of BLEU. We further validate that 1) the proposed segmentation model significantly outperforms syntactic constraints which are used in previous work to constrain segmentations; and 2) it is necessary to capture hierarchical segmentations besides phrasal segmentations.

Reversible Image Data Hiding Using Quad-tree Segmentation and Histogram Shifting

This paper is working towards a high capacity histogram-based reversible data hiding algorithm with a relatively lower distortion introduced after embedding the secret message. The proposed algorithm can be thought of as an improved version of the traditional histogram shifting method. To take advantage of simple local distribution of pixel intensities, the idea behind the proposed algorithm is to consider the multiple local histograms, each of which is derived from pixels in a locally contiguous sub-image area, instead of the single histogram for the whole image area. We develop a hierarchical segmentation scheme that is able to hierarchically partition the input host image into several variable-sized blocks of pixels under a maximal capacity criterion for each block partition. These partitioned blocks are organized as a tree structure for the ease of representation. The secret message and the partition tree information are then embedded in these image blocks. With the proposed segmentation scheme, the algorithm can easily find a suitable non-overlapped partition of the image to significantly increase embedding capacity. Experimental results reveal that the proposed method can indeed provide higher embedding capacity than the traditional histogram shifting method while maintaining a high visual quality that is comparable to the traditional one without spatial segmentation scheme.

Validation of a market orientation adoption scale in rural tourism enterprises. Relationship between the characteristics of the enterprise and extent of market orientation adoption

Market orientation (MO) is considered as a competitive strategy for the rural tourism sector. A MO adoption scale is proposed and validated for the rural tourism sector. Given the importance of MO, it is important to know the relationship between a firm's characteristics and MO adoption. This study makes a hierarchical segmentation to predict the behaviour of these firms when adopting the MO. Activity and category are the two characteristics that most effectively predict a firm's behaviour. The contribution made by this work is of interest given the new field of application achieved and which have implications for the professional sector.

Hierarchical segmentation-based software for cover classification analyses of seabed images (Seascape)

8 Marine Technology Unit (UTM-CSIC), Passeig Maritim de la Barceloneta 37-49, 08003 Barcelona, Spain ABSTRACT: An important aspect of marine research is to quantify the areal coverage of benthic communities. It is technically feasible to efficiently obtain images of marine environments at differ- ent depths and benthic habitats over large spatial and temporal scales. Currently, there is a large and growing library of digital images to analyze, representing a valuable benthic ecological archive. Benthic coverage is the basis of studies on biodiversity, characterization of communities and evaluation of changes over temporal and spatial scales. However, there is still a lack of auto- matic or semi-automatic analytical methods for deriving ecologically relevant data from these images. We introduce a software program named Seascape to obtain semi-automatically seg- mented images (patch outlines) from underwater photographs of benthic communities, where each individual patch (species/categories) is routinely associated to its area cover and perimeter. Seascape is an analog to the classical and better known discipline of landscape ecology approach, which focuses on the concept that communities can be observed as a patch mosaic at any scale. The process starts with a hierarchical segmentation, using a color space criteria adapted to the problem of segmenting complex benthic images. As an endproduct, we obtain a set of images segmented into classified homogenous regions at different resolution levels (hierarchical seg - mentation). To illustrate the versatility and capacity of Seascape, we analyzed 4 digital images from different habitats and depths: coral reefs (Pacific Ocean), coralligenous communities (NW Mediterranean Sea), deep-water coral reefs (NW Mediterranean Sea) and the Antarctic continental shelf (Weddell Sea). The development of this semi-automatic outline tool and its use for classifica- tion constitute an important step forward in the analysis and processing time of underwater seabed images at any scale.

SPATIALLY ADAPTIVE MORPHOLOGICAL IMAGE FILTERING USING INTRINSIC STRUCTURING ELEMENTS

This paper deals with spatially adaptive morphological filtering, extending the theory of mathematical morphology to the paradigm of adaptive neighborhood. The basic idea in this approach is to substitute the extrinsically-defined, fixed-shape, fixed-size structuring elements generally used by morphological operators, by intrinsically-defined, variable-shape, variable-size structuring elements. These last so-called intrinsic structuring elements fit to the local features of the image, with respect to a selected analyzing criterion such as luminance, contrast, thickness, curvature or orientation. The resulting spatially-variant morphological operators perform efficient image processing, without any a priori knowledge of the studied image and some of which satisfy multiscale properties. Moreover, in a lot of practical cases, the elementary adaptive morphological operators are connected, which is topologically relevant. The proposed approach is practically illustrated in several application examples, such as morphological multiscale decomposition, morphological hierarchical segmentation and boundary detection.

GEODESIC RECONSTRUCTION, SADDLE ZONES & HIERARCHICAL SEGMENTATION

The morphological reconstruction based on geodesic operators, is a powerful tool in mathematical morphology. The general definition of this reconstruction supposes the use of a marker function f which is not necessarily related to the function g to be built. However, this paper deals with operations where the marker function is defined from given characteristic regions of the initial function f, as it is the case, for instance, for the extrema (maxima or minima) but also for the saddle zones. Firstly, we show that the intuitive definition of a saddle zone is not easy to handle, especially when digitised images are involved. However, some of these saddle zones (regional ones also called overflow zones) can be defined, this definition providing a simple algorithm to extract them. The second part of the paper is devoted to the use of these overflow zones as markers in image reconstruction. This reconstruction provides a new function which exhibits a new hierarchy of extrema. This hierarchy is equivalent to the hierarchy produced by the so-called waterfall algorithm. We explain why the waterfall algorithm can be achieved by performing a watershed transform of the function reconstructed by its initial watershed lines. Finally, some examples of use of this hierarchical segmentation are described.

Contour Detection and Hierarchical Image Segmentation

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.