Showing papers on "Structuring element published in 2005"

Classification of hyperspectral data from urban areas based on extended morphological profiles

Abstract: Classification of hyperspectral data with high spatial resolution from urban areas is investigated. A method based on mathematical morphology for preprocessing of the hyperspectral data is proposed. In this approach, opening and closing morphological transforms are used in order to isolate bright (opening) and dark (closing) structures in images, where bright/dark means brighter/darker than the surrounding features in the images. A morphological profile is constructed based on the repeated use of openings and closings with a structuring element of increasing size, starting with one original image. In order to apply the morphological approach to hyperspectral data, principal components of the hyperspectral imagery are computed. The most significant principal components are used as base images for an extended morphological profile, i.e., a profile based on more than one original image. In experiments, two hyperspectral urban datasets are classified. The proposed method is used as a preprocessing method for a neural network classifier and compared to more conventional classification methods with different types of statistical computations and feature extraction.

Classification of hyperspectral data from urban areas using morphological preprocessing and independent component analysis

Abstract: Classification of high-resolution hyperspectral data is investigated. Previously, in classification of high-resolution panchromatic data, simple morphological profiles have been constructed with a repeated use of morphological opening and closing operators with a structuring element of increasing size, starting with the original panchromatic image. This approach has recently been extended for hyperspectral data. In the extension, principal components of the hyperspectral imagery have been computed in order to produce an extended morphological profile. In this paper, we investigate the use of independent components instead of principal components in extended morphological profiles, i.e., selected independent components are used as base images for an extended morphological profile. In the proposed approach, the extended morphological profiles based on the independent components are used as inputs to a neural network classifier. In experiments, a hyperspectral data sets from an urban area in Pavia, Italy is classified.

Morphological Erosions and Openings: Fast Algorithms Based on Anchors

Abstract: Several efficient algorithms for computing erosions and openings have been proposed recently. They improve on van Herk's algorithm in terms of number of comparisons for large structuring elements. In this paper we introduce a theoretical framework of anchors that aims at a better understanding of the process involved in the computation of erosions and openings. It is shown that the knowledge of opening anchors of a signal f is sufficient to perform both the erosion and the opening of f. Then we propose an algorithm for one-dimensional erosions and openings which exploits opening anchors. This algorithm improves on the fastest algorithms available in literature by approximately 30% in terms of computation speed, for a range of structuring element sizes and image contents.

A low complexity architecture for binary image erosion and dilation using structuring element decomposition

Abstract: This paper describes a new hardware architecture for binary image erosion and dilation. The design is to be used in a self contained real-time surveillance system. Thus, low complexity and low power consumption are main constraints. To achieve this goal the aim has been to reduce memory requirements and the number of memory accesses per pixel. By storing only the number of consecutive ones that appears horizontally and vertically in the input image, only two internal memory accesses per calculated output pixel are required. The number of memory accesses is independent of the size of the structuring element (SE) as long as it is rectangular and only contains ones, which is a common case. The internal memory size is proportional to log/sub 2/(SE/sub height/), which means that a large span of SE sizes can be supported with a small amount of hardware.

A graph approach to color mathematical morphology

Abstract: The processing of color images has become a major field of interest, however the direct extension of their gray scale counterparts is not always possible since there is no natural ordering of color vectors. Mathematical morphology has to face with this problem since it needs a complete lattice which is generally based on a conditional ordering. We propose another approach based on a graph decimation of a given structuring element to find the supremum and the infimum of a color vector set. The effects of the proposed graph approach are studied on several morphological operators (erosion, dilatation, watershed) and compared with the conditional ordering

A hierarchical procedure for segmentation and classification of airborne LIDAR images

Abstract: Airborne laser scanning has become an accepted technique for acquiring Digital Surface Models of the Earth surface. One of the major and still unsolved problems is the automatic separation of the topographic surface and 3D objects which cover the topographic surface. For this purpose a hierarchical segmentation procedure using morphological operations is developed and compared with more classical methods that are using morphological operations with a single structuring element to separate terrain from non-terrain surface models. The classical methods have a limited functionality in areas where a range of very small to very big 3D objects exists as well as in areas with a big variety of height differences. Starting point for the hierarchical process are morphological operations with different structuring element sizes applied to the Laser range data. For LIDAR systems which record first and last pulse both data sets are employed. The key of the segmentation process is to analyze the generated sequence of morphologically filtered data to extract ground points with high probability and separate them from nonground points. Aggregation to regions and the extraction of regions properties provide the basis for 3D object extraction. Further analysis focuses the feature description for the 3D regions which provides the input for classifying and separating 3D objects, in particular buildings and vegetation regions, from the ground surface regions. The local range variation, surface normal and NDVI features are utilized for evaluating the segmented regions. This procedure has been applied to a data set which was recorded by the TopScan laser scanning system with the density of about 1 point per square meter. Keywordslaser scanning; Mathematical morphology; segmentation; building extraction; trees extraction

Using line segments as structuring elements for sampling-invariant measurements

Abstract: When performing measurements in digitized images, the pixel pitch does not necessarily limit the attainable accuracy. Proper sampling of a bandlimited continuous-domain image preserves all information present in the image prior to digitization. It is therefore (theoretically) possible to obtain measurements from the digitized image that are identical to measurements made in the continuous domain. Such measurements are sampling invariant, since they are independent of the chosen sampling grid. It is impossible to attain strict sampling invariance for filters in mathematical morphology due to their nonlinearity, but it is possible to approximate sampling invariance with arbitrary accuracy at the expense of additional computational cost. In this paper, we study morphological filters with line segments as structuring elements. We present a comparison of three known and three new methods to implement these filters. The method that yields a good compromise between accuracy and computational cost employs a (subpixel) skew to the image, followed by filtering along the grid axes using a discrete line segment, followed by an inverse skew. The staircase approximations to line segments under random orientations can be modeled by skewing a horizontal or vertical line segment. Rather than skewing the binary line segment we skew the image data, which substantially reduces quantization error. We proceed to determine the optimal number of orientations to use when measuring the length of line segments with unknown orientation.

Locally adaptable mathematical morphology

Abstract: We investigate how common binary mathematical morphology operators can be adapted so that the size of the structuring element (SE) can vary across the image. We show that when the SE are balls of a metric, locally adaptable erosion and dilation can be efficiently implemented as a variant of distance transformation algorithms. Opening and closing are obtained by a local threshold of a distance transformation, followed by the adaptable dilation.

Method and apparatus for efficient computation of morphology operations

Abstract: Disclosed is an algorithm for applying a morphological operation to an image. In one embodiment, the morphological operation is iteratively applied to a focal pixel of the image and to another pixel of the image. The other pixel is located at an offset with respect to the focal pixel. The offset is based on an operation count. In another embodiment, the algorithm includes performing a morphological operation on an image using a convex structuring element. A work structuring element having dimensions corresponding to the outer-most dimensions of the convex structuring element is iteratively applied to the image. The dimensions of the work structuring element are then adjusted to correspond to the remaining outer dimensions of the convex structuring element not yet covered by the previous work structuring element. The applying and adjusting steps are repeated until a predetermined number of morphological operations have been performed.

Mathematical morphology for tensor data induced by the Loewner orderingin higher dimensions

Abstract: Positive semidefinite matrix fields are becoming increasingly important in digital imaging. One reason for this tendency consists of the introduction of diffusion tensor magnetic resonance imaging (DTMRI). In order to perform shape analysis, enhancement or segmentation of such tensor fields, appropriate image processing tools must be developed. This paper extends fundamental morphological operations to the matrix-valued setting. We start by presenting novel definitions for the maximum and minimum of a set of matrices since these notions lie at the heart of the morphological operations. In contrast to naive approaches like the component-wise maximum or minimum of the matrix channels, our approach is based on the Loewner ordering for symmetric matrices. The notions of maximum and minimum deduced from this partial ordering satisfy desirable properties such as rotation invariance, preservation of positive semidefiniteness, and continuous dependence on the input data. We introduce erosion, dilation, opening, closing, top hats, morphological derivatives, shock filters, and mid-range filters for positive semidefinite matrix-valued images. These morphological operations incorporate information simultaneously from all matrix channels rather than treating them independently. Experiments on DT-MRI images with ball- and rod-shaped structuring elements illustrate the properties and performance of our morphological operators for matrix-valued data.

Street tracking based on SAR data from urban areas

Abstract: A method for street tracking is proposed The method consists of two steps First, a “blob image” of possible street candidates is created Then, the street segments from that blob image are extracted Two feature extraction approaches based on mathematical morphology are applied as preprocessing for the street tracking One method is based on using differential morphological profiles but the other uses morphological opening and closing operators with a rotating structuring element (SE) The method is tested on an AIRSAR image from Los Angeles with and without noise filtering The obtained results are measured using two indexes; correctness and completeness Of the two methods used in the feature extraction, the SE rotation appears to give better results Noise filtering does not have a major effect in street tracking for the AIRSAR image

An efficient ECG background normalization

Abstract: This paper presents an improved morphological approach for baseline wander correction in electrocardiogram (ECG) signals, with emphasis on preserving all required clinical information of the original signal The algorithm consists of only one stage of morphological processing (while similar morphological filters need two stages) The morphological operators are applied to approximate the baseline drift Then it is subtracted from the input signal to leave a corrected-baseline signal The performance of the algorithm is evaluated with real ECGs containing artificial and real baseline drift Compared with all existing morphological methods, there is a substantial improvement, especially in reducing distortion of the baseline waveform in any part of the signal The experimental results prove that the proposed method is less sensitive to the size of the structuring element if a reasonable size is considered

Classification of hyperspectral ROSIS data from urban areas

Abstract: Classification of high-resolution hyperspectral ROSIS 03 (Reflective Optics System Imaging Spectrometer) data based on extended morphological profiles is considered. For classification of high-resolution panchromatic data, simple morphological profiles are constructed with a repeated use of morphological opening and closing operators with a structuring element of increasing size, starting with the original panchromatic image. In order to apply the morphological approach to hyperspectral data, principal components of the hyperspectral imagery are computed. The most significant principal components are used as base images for an extended morphological profile, i.e., a profile based on more than one original image. The extended morphological profiles arc used as inputs to a neural network classifier. In experiments, two hyperspectral data sets from an urban area in Pavia, Italy are classified.

Morphological filter based on genetic learning

Abstract: A novel method for optimal morphological filtering parameters, namely the genetic training algorithm for morphological filters (GTAMF), which adopts new crossover and mutation operators called the curved cylinder crossover and master-slave mutation, is presented in this paper Experimental results show that this method is practical, easy to extend, and improves the performances of morphological filters The operation of a morphological filer can be divided into two basic problems that include morphological operation and structuring element (SE) selection The rules for morphological operations are predefined so the filter's properties depend merely on the selection of SE By means of adaptive optimizing training, structuring elements possess the shape and structural characteristics of image targets, namely some information can be obtained by SE Morphological filters formed in this way become intelligent and can provide good filtering results and robust adaptability to image targets with clutter background

Minimax distance transform correlation filter based target detection in FLIR imagery

Abstract: This paper proposes a method to detect objects of arbitrary poses and sizes from a complex forward looking infrared (FLIR) image scene exploiting image correlation technique along with the preprocessing of the scene using a class of morphological operators. This presented automatic target recognition (ATR) algorithm consists of two steps. In the first step, the image is preprocessed, by employing morphological reconstruction operators, to remove the background as well as clutter and to intensify the presence of both low or high contrast targets. This step also involves in finding the possible candidate target regions or region of interests (ROIs) and passing those ROIs to the second step for classification. The second step exploits template-matching technique such as minimax distance transform correlation filter (MDTCF) to identify the true target from the false alarms in the pre-selected ROIs after classification. The MDTCF minimizes the average squared distance from the filtered true-class training images to a filtered reference image while maximizing the mean squared distance of the filtered false-class training images to this filtered reference image. This approach increases the separation between the false-class correlation outputs and the true-class correlation outputs. Classification is performed using the squared distance of a filtered test image to the chosen filtered reference image. The proposed technique has been tested with real life FLIR image sequences supplied by the Army Missile Command (AMCOM). Experimental results, obtained with these real FLIR image sequences, illustrating a wide variety of target and clutter variability, demonstrate the effectiveness and robustness of the proposed method.

A Separating Algorithm for Overlapping Red Blood Cell Images

Abstract: Overlapping appears frequently is all images The algorithm based on the knowledge that red blood cells are disk-shaped Granulometry is employed to estimate cell’s radius R Every contour point corresponds to center point of a circle with radius R estimated with the information of radius and chain code, which will assemble central areas of every single cell Then, morphological dilation with a disk-shaped structuring element of radius R is applied to every central area The intersection of the result of dilation operation and the original binary image is used to estimate the shape of every single cell Experiments show the algorithm can obtain acceptable separating result It can also be used for images of other kind of disk-shaped cells and granules

Multiscale segmentation of oil slick in sar images based on morphological pyramid

Abstract: We propose a new approach based on the Marangoni theory, particularly a dampening of the wave spectra energy. The observation is decomposed into multiscale analysis using a pseudo morphological pyramid, named here as a alternating contextual filter, to improve the detection of local variations of the wave spectrum. The morphological thick gradient contrast is first performed with a varying structuring element. The filtering is balanced by the low pass image. The residue image gives information about the surface energy spectrum in relation to the dispersion equation. Then images generated are merged with the help of fuzzy c-mean algorithm to achieve the segmentation process. The method is tested on ERS2 SAR and ENVISAT ASAR Images. The obtained results are promising and show an improvement of the oil slick detection. 1. INTRODUCTION ERS Synthetic Aperture Radar (SAR) images had proved their interest in large scale detection and monitoring of pollution on ocean surface. Advanced SAR (ASAR) images greatly offers new possibilities of applications [1]. Up until now, several methods based on intensity images have been used to measure signatures of oil slick by a spaceborne mono-frequency Synthetic Aperture Radar (SAR) [2] [3]. Among these methods, the Multiscale Oil Slick Segmentation (MOSS) with Markov Chain Model (MCM) [4] has been based on the behaviour of wave spectra [5]. It has proved multiscale analysis to be an original approach to explain the effects of slick on sea, to characterize ocean surface polluted, particularly the dampening of the wave spectra energy, and then to classify oil slicks pixels. In this previous work, the multiscale analysis has been implemented by wavelet packets decomposition for frequential texture characterization. But, the local variation of the wave spectrum required being characterise structurally [3]. The multiscale contrast thick gradients resulting from the morphological pyramid [6], with a varying structuring element, are non linear approaches suitable to answer these two points of view. A conflict area (beyond the possible classes) has been appeared too in the images detection result of the MCM. To raise this ambiguity, the locations will be refining with fuzzy model algorithm. The paper is organized as follows. Section 2 recalls the main concept of ocean modelling. Then, the method (section 3) operates in two mains steps: the multiscale decomposition by morphological pyramid based on contextual filtering and the multi spectral fuzzy classification performed to merge additional sub-bands generated. Experimental results are illustrated in section 4, at the same time, on ENVISAT ASAR and ERS2 SAR images, to evaluate these two radar results. Conclusions are reported in section 5.

Structuring Elements Following the Optical Flow

Abstract: This paper deals with the combination of classical morphological tools and motion compensation techniques. Morphological operators have proven to be efficient for filtering and segmenting still images. For video sequences however, using motion information to modify the morphological processing is necessary. In previous work, iterative frame by frame segmentation using motion information has been developed in various forms. In this paper, motion is used at a very low level, by locally modifying the shape of the structuring element in a video sequence considered as a 3D data block. Motion adapted morphological tools are described and their use is demonstrated on video sequences. Moreover, the features of the motion model best suited to our purpose are also discussed.

The Habitat Abstraction of the High Resolution Remote Sensing Imagery Based on Wavelet Transform and Mathematics Morphologic Subject

Abstract: This article discusses the method of using Wavelet Transform and Mathematics Morphologic Subject to extract the canal of the area objects on the high resolution remote sensing image. As the experiment showed, after the veins partition of the images using the Wavelet Transform, the habitat extraction on the high resolution remote sensing image can be implemented by using the sorts of operators combined by the basic operation of Mathematics Morphologic Subject, choosing the right structure element and the vector tracking, the result of the method can be directly used in the application of GIS.

Reference-free detection of semiconductor assembly defect

Abstract: This paper aims at developing a novel defect detection algorithm for the semiconductor assembly process by image analysis of a single captured image, without reference to another image during inspection The integrated circuit (IC) pattern is usually periodic and regular Therefore, we can implement a classification scheme whereby the regular pattern in the die image is classified as the acceptable circuit pattern and the die defect can be modeled as irregularity on the image The detection of irregularity in image is thus equivalent to the detection of die defect We propose a method where the defect detection algorithm first segments the die image into different regions according to the circuit pattern by a set of morphological segmentations with different structuring element sizes Then, a feature vector, which consists of many image attributes, is calculated for each segmented region Lastly, the defective region is extracted by the feature vector classification

Spectral morphology for feature extraction from multi- and hyper-spectral imagery

Abstract: For accurate and robust analysis of remotely-sensed imagery it is necessary to combine the information from both spectral and spatial domains in a meaningful manner. The two domains are intimately linked: objects in a scene are defined in terms of both their composition and their spatial arrangement, and cannot accurately be described by information from either of these two domains on their own. To date there have been relatively few methods for combining spectral and spatial information concurrently. Most techniques involve separate processing for extracting spatial and spectral information. In this paper we will describe several extensions to traditional morphological operators that can treat spectral and spatial domains concurrently and can be used to extract relationships between these domains in a meaningful way. This includes the investgation and development of suitable vector-ordering metrics and machine-learning-based techniques for optimizing the various parameters of the morphological operators, such as morphological operator, structuring element and vector ordering metric. We demonstrate their application to a range of multi- and hyper-spectral image analysis problems.

Reconstruction of pore space from a pore connectivity network via morphological transformations

Abstract: Summary Pore and grain regions were separated via thresholding techniques from sandstone images. A mathematical morphologybased framework was followed to pack the random pore space with overlapping and nonoverlapping disks. This framework has several advantages in implementation and is generally applicable to multiscale images. The random pore space was reconstructed in two ways from the minimum morphological information through: (a) overlapping and (b) nonoverlapping disks of various shapes and sizes. The structuring elements employed to carry out this analysis included octagon, square and rhombus templates. The results achieved through these two types of reconstruction of sandstone pores are compared. These results provided the basis on which to test the accuracy of these techniques. Reconstruction recovery was tested by computing shapiness indices for the reconstructed pores achieved through the two methods.

Shape detection based on mathematical morphology

Abstract: A novel algorithm for shape detection based on mathematical morphology is presented. Two stages are involved. In the first stage, a shape model is learned automatically from learning examples belonging to the same object class. It is a collection of subparts with the description of relations among subparts, represented by a fuzzy graph. In the second stage, the generated model is used to detect similar shapes from images of complex real scenes. Subparts of the shape are detected in sequence based on their saliency, and then the geometric configuration among those detected subparts is checked. A morphological component detector is proposed to detect each subpart by using a soft structuring element, derived from the shape model. Satisfactory results are shown when testing the algorithm on synthetic and real images.

Decomposition of 3d convex structuring element in morphological operation for parallel processing architectures

Abstract: Morphological operations with 3D images require a huge amount of computation. The decomposition of structuring elements used in the morphological operations such as dilation and erosion greatly reduces the amount of computation. This paper presents a new method for the decomposition of a 3D convex structuring element into a set of basis convex structuring elements. Furthermore, the decomposition method is applied to the neighborhood decomposition, in which each basis is one of the combinations of the origin voxel and its 26 neighborhood voxels. First, we derived the set of decomposition conditions on the lengths of the original and the basis convex structuring elements, and then the decomposition problem is converted into a linear integer optimization problem. The objective of the optimization is to minimize a cost function representing the optimal criterion of the parallel processing computer architecture on which the operation is performed. Thus, our method can be used to obtain the different optimal decompositions minimizing the amount of computation for different parallel processing computer architectures.

Gas filtering structure e.g. silicon carbide filtering structure, selecting method for e.g. diesel engine, involves processing image comprising morphological erosion produced by structuring element to obtain another image

Abstract: The method involves processing, according to a wall surface image, an image comprising a morphological erosion produced by a structuring element e.g. disk, in such a way that another image characterizing the uniformity and the homogeneity of a wall microstructure is obtained. Dimensions and the morphology of the structuring element are selected based on median diameter of pores, measured by mercury porosimetry. An independent claim is also included for a silicon carbide based filtering structure.