Hierarchical Segmentation Algorithm Research Articles

A pyramidal image segmentation algorithm

The problem of image segmentation (division into homogeneous regions) basing on color and texture region differences is considered. A two-level hierarchical pyramidal segmentation algorithm is proposed for solution of this problem. The homogeneity criterion is the estimated adjacency of the image elements and regions in the combined color-texture feature space. A metric in this space is introduced and studied. The results are verified on a set of test images of different types.

Lidar-based Mapping of Forest Volume and Biomass by Taxonomic Group Using Structurally Homogenous Segments

This study evaluated the potential of an object-oriented approach to forest type classification as well as volume and biomass estimation using small-footprint, multiple return lidar data. The approach was applied to coniferous, deciduous, and mixed forest stands in the Virginia Piedmont, U.S.A. A multiresolution, hierarchical segmentation algorithm was applied to a canopy height model (CHM) to delineate objects ranging from 0.035 to 5.632 ha/average object. Per-object lidar point (per return height and intensity) and CHM distributional parameters were used as input to a discriminant classification of 2-class (deciduous-coniferous) and 3-class (deciduous-coniferous-mixed) forest definitions. Lidar point-height-based and CHM classifications yielded overall accuracies of 89 percent and 79 percent, respectively. Volume and biomass estimates exhibited differences of no more than 5.5 percent compared to field estimates, while showing distinctly improved precisions (up to 45.5 percent). There were no significant differences between accuracies for varying object sizes, which implies that reducing the lidar point coverage would not affect classification accuracy. These results lead to the conclusion that a lidar-based approach to forest type classification and volume/biomass assessment has the potential to serve as a single-source inventory tool.

Utilizing Hierarchical Segmentation to Generate Water and Snow Masks to Facilitate Monitoring Change with Remotely Sensed Image Data

The hierarchical segmentation (HSEG) algorithm is a hybrid of hierarchical step-wise optimization and constrained spectral clustering that produces a hierarchical set of image segmentations. This segmentation hierarchy organizes image data in a manner that makes the image's information content more accessible for analysis by enabling region-based analysis. This paper discusses data analysis with HSEG and describes several measures of region characteristics that may be useful analyzing segmentation hierarchies for various applications. Segmentation hierarchy analysis for generating land/water and snow/ice masks from MODIS (Moderate Resolution Imaging Spectroradiometer) data was demonstrated and compared with the corresponding MODIS standard products. The masks based on HSEG segmentation hierarchies compare very favorably to the MODIS standard products. Further, the HSEG based land/water mask was specifically tailored to the MODIS data and the HSEG snow/ice mask did not require the setting of a critical threshold as required in the production of the corresponding MODIS standard product.

Utilisation of contour criteria in micro-segmentation of SAR images

The segmentation of SAR (Synthetic Aperture Radar) images is greatly complicated by the presence of coherent speckle. To carry out this process a hierarchical segmentation algorithm based on stepwise optimization is used. It starts with each individual pixel as a segment and then sequentially merges the segment pair that minimizes the criterion. In a hypothesis testing approach, we show how the stepwise merging criterion is derived from the probability model of image regions. The Ward criterion is derived from the Gaussian additive noise model. A new criterion is derived from the multiplicative speckle noise model of SAR images. The first merging steps produce micro-regions. With standard merging criteria, the high noise level of SAR images results in the production of micro-regions that have unreliable mean and variance values and irregular shapes. If the micro-segments are not correctly delimited then the following steps will merge segments from different fields. In examining the evolution of the initial segments, we see that the merging should take into account spatial aspects. In particular, the segment contours should have good shapes. We present three measures based on contour shapes, using the perimeter, the area and the boundary length of segments. These measures are combined with the SAR criterion in order to guide correctly the segment merging process. The new criterion produces good micro-segmentation of SAR images. The criterion is also used in the following merges to produce larger segments. This is illustrated by synthetic and real image results.

Unsupervised Segmentation of Natural Images

This paper presents an unsupervised segmentation method of natural images that uses Statistical Geometrical Features as texture descriptors and a hierarchical segmentation algorithm. We propose an extraction of texture features to obtain good boundary features and uniform texture features by incorporating an anisotropic diffusion preprocess. The proposed unsupervised hierarchical segmentation algorithm is performed in four stages: hierarchical splitting, local agglomerative merging, global agglomerative merging and pixelwise classification. We make some experiments to demonstrate the effectiveness of the proposed technique for segmentation of different natural images.

Hierarchical genetic image segmentation algorithm based on histogram dichotomy

A new hierarchical distributed genetic algorithm for image segmentation is proposed based on histogram dichotomy without an a priori number of image regions. Experimental results show that the proposed method outperforms the original distributed genetic algorithm.

Watershed-based hierarchical SAR image segmentation

Watershed transformation is a powerful image segmentation tool recently developed in mathematical morphology. In order to segment images initially oversegmented by watershed transformation, two approaches are considered: one is the thresholding of the gradient image proposed by us which is capable of keeping more salient image contours; the other is the well known centroid linkage region growing algorithm which merges regions with certain statistical similarities. By choosing suitable thresholds in the two approaches, hierarchical image segmentation algorithms can be constructed. A Ratio of Averages (ROA) edge detector is proposed to replace the morphological edge detectors prior to watershed transformation when applied to Synthetic Aperture Radar (SAR) images. Applications to SAR agricultural image segmentation with these hierarchical segmentation algorithms are presented. It is demonstrated that the algorithms are efficient in the segmentation of the SARimages and appropriate for land use applications when the land cover is made up of individual plots.

Adaptation of the Hierarchical Stepwise Segmentation Algorithm for automatic segmentation of a SAR mosaic

This Letter describes the application of a Hierarchical Stepwise Segmentation Algorithm to SAR mosaic images. The objective was to obtain an efficient procedure which can be used to segment and classify large zones of the CAMP (Central Africa Mosaic Project) radar image mosaic in tropical forest regions. Validation of the algorithm has been carried out using data from the CAMP project.

Efficient segmentation of large‐area skin images: a statistical evaluation

This paper is the second of a series describing research and development performed by the SPOTS project towards automating the process of monitoring pigmented lesions for change over time. Several parameters of the system are introduced along with the methods used for determining appropriate settings. We then describe our experimental setup and present a detailed statistical analysis to evaluate system performance. There exist three sets of parameters in our system related to image segmentation, classification, and a region-growing step that can be individually tuned. The multiresolution hierarchical segmentation algorithm contains both a set of weights for the tristimulus color values used in calculating color differences and a contrast threshold used to identify root nodes that represent image segments. These were tuned using a synthetic image to simulate a pigmented lesion with irregular border and by estimating the parameters by successive approximations. The neural network classification used to detect lesion segments was trained using a 10-fold cross-validation, and the output classification threshold was set to yield a small false negatives ratio. Finally, there is a growing threshold used to determine whether neighbor regions should be merged in the region-growing step that was selected to minimize the change in area for different translations of a synthetic lesion. In order to evaluate the performance of the system, we compared the identified lesions with manually localized lesions. Ten images of the same area were taken from two subjects presenting lesions of varying size and different background skin texture. A sample of two images from the set was used to simulate variations in acquisition. Five operators were asked to trace lesion boundaries in two passes, separated by a few days, to evaluate the consistency of operators among themselves. The system was then run on the images using the optimal set of parameters. The results were analyzed for independent observation, matched pass, and doubly-matched pass data. Independent observation data indicates that the system finds significantly more objects than any of the human operators, but the areas reported are not significantly different on average. Matched pass data show that the correlations of the system with human operators is quite high. The system agrees with humans only slightly less than they do among themselves and has a tendency to report slightly smaller areas. The correlation between system and human peformance was further reinforced by the doubly-matched arrangement. These results indicate that our system is as reliable and consistent as our human reference, yielding similar performance.

Morphological multiscale segmentation for image coding

This paper is concerned with a hierarchical segmentation algorithm for image coding. It is based on mathematical morphologyl which is very attractive for this purpose. Indeed, morphology can efficiently deal with geometrical features such as size, shape, contrast or connectivity that can be considered as object-oriented, and therefore segmentation-oriented, features. The proposed algorithm follows a purely top-down procedure. It first takes into account the most global information of the image and produces a coarse (with a reduced number of regions) segmentation. Then, the segmentation is improved by introducing regions corresponding to more local information. Each segmentation stage relies on four basic steps: simplification, feature extraction, decision and quality estimation. The simplification removes information from the input image to make it easier to segment. Morphological filters based on reconstruction processes are proved to be very efficient for this purpose. The feature extraction, called marker extraction, identifies the presence of homogeneous regions. The goal of the decision is to locate precisely the contours of the regions detected by the feature extraction. This decision process is performed by the watershed algorithm. Finally, the quality estimation concentrates on an image, called the coding residue, all the information about the regions that have not been properly represented by the current segmentation. The procedure allows the introduction of the texture and contour coding schemes within the segmentation algorithm. The coding residue is transmitted to the next segmentation stage to improve the segmentation and coding quality. Examples of transformations which can fit within this structure are described and discussed. Finally, some segmentation and coding examples are presented to show the validity and interest of the coding approach.

Post‐segmentation classification of images containing small agricultural fields

Abstract This paper presents results from applying a hierarchical segmentation algorithm to two agricultural data sets characterised by small fields. Several new techniques were developed over the course of this project. These include a new supervised classification technique for identifying segments and the inclusion of other information derived from the segmentation process. In addition, a technique for including cartographic information to help structure the segmentation is also described. The results indicate that significant improvement in classification accuracy can be achieved. A number of problems which arise when working with segmentation data are also reported and discussed. These problems appear to be different enough from those encountered in pixel classifications to be worth describing in greater detail. The paper concludes with the lines of research being pursued to circumvent these problems and to further increase the fidelity of the segmentation results.