Showing papers on "Structuring element published in 2010"

Morphological Attribute Profiles for the Analysis of Very High Resolution Images

Abstract: Morphological attribute profiles (APs) are defined as a generalization of the recently proposed morphological profiles (MPs). APs provide a multilevel characterization of an image created by the sequential application of morphological attribute filters that can be used to model different kinds of the structural information. According to the type of the attributes considered in the morphological attribute transformation, different parametric features can be modeled. The generation of APs, thanks to an efficient implementation, strongly reduces the computational load required for the computation of conventional MPs. Moreover, the characterization of the image with different attributes leads to a more complete description of the scene and to a more accurate modeling of the spatial information than with the use of conventional morphological filters based on a predefined structuring element. Here, the features extracted by the proposed operators were used for the classification of two very high resolution panchromatic images acquired by Quickbird on the city of Trento, Italy. The experimental analysis proved the usefulness of APs in modeling the spatial information present in the images. The classification maps obtained by considering different APs result in a better description of the scene (both in terms of thematic and geometric accuracy) than those obtained with an MP.

Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images

Abstract: Very high spatial resolution (VHR) images allow to feature man-made structures such as roads and thus enable their accurate analysis. Geometrical characteristics can be extracted using mathematical morphology. However, the prior choice of a reference shape (structuring element) introduces a shape-bias. This paper presents a new method for extracting roads in Very High Resolution remotely sensed images based on advanced directional morphological operators. The proposed approach introduces the use of Path Openings and Path Closings in order to extract structural pixel information. These morphological operators remain flexible enough to fit rectilinear and slightly curved structures since they do not depend on the choice of a structural element shape. As a consequence, they outperform standard approaches using rotating rectangular structuring elements. The method consists in building a granulometry chain using Path Openings and Path Closing to construct Morphological Profiles. For each pixel, the Morphological Profile constitutes the feature vector on which our road extraction is based.

Extended morphological processing: a practical method for automatic spot detection of biological markers from microscopic images.

Abstract: A reliable extraction technique for resolving multiple spots in light or electron microscopic images is essential in investigations of the spatial distribution and dynamics of specific proteins inside cells and tissues. Currently, automatic spot extraction and characterization in complex microscopic images poses many challenges to conventional image processing methods. A new method to extract closely located, small target spots from biological images is proposed. This method starts with a simple but practical operation based on the extended morphological top-hat transformation to subtract an uneven background. The core of our novel approach is the following: first, the original image is rotated in an arbitrary direction and each rotated image is opened with a single straight line-segment structuring element. Second, the opened images are unified and then subtracted from the original image. To evaluate these procedures, model images of simulated spots with closely located targets were created and the efficacy of our method was compared to that of conventional morphological filtering methods. The results showed the better performance of our method. The spots of real microscope images can be quantified to confirm that the method is applicable in a given practice. Our method achieved effective spot extraction under various image conditions, including aggregated target spots, poor signal-to-noise ratio, and large variations in the background intensity. Furthermore, it has no restrictions with respect to the shape of the extracted spots. The features of our method allow its broad application in biological and biomedical image information analysis.

Feature enhancement of medical images using morphology-based homomorphic filter and differential evolution algorithm

Abstract: In this paper, we present a new morphology-based homomorphic filtering technique for feature enhancement in medical images. The proposed method is based on decomposing an image into morphological subbands. The homomorphic filtering is performed using the morphological subbands. The differential evolution algorithm is applied to find an optimal gain and structuring element for each subband. Simulations show that the proposed filter improves the contrast of the features in medical images.

Application of Mathematical Morphology based filters to detect a power swing

Abstract: Mathematical Morphology (MM) has been discussed in recent literature for its possible applications in power systems. However, the application of MM as a real-time filtering tool in power systems has not been explored adequately. This paper reports further contributions to our previous efforts in this direction. The paper shows how an appropriate choice of the structuring element (SE) can help develop a method to detect power system phenomena characterized by low frequency. To illustrate the effectiveness of the proposed method, it is used to detect a power swing simulated using PSCAD/EMTDC®. Results are presented and analyzed. Based on the analysis, future work is outlined in order to construct an improved out-of-step blocking tool using this method, and to integrate this tool with a distance relay.

Differential Area Profiles

Abstract: In this paper a new feature descriptor, the differential area profile (DAP), is presented. DAPs, like the regular differential morphological profiles, are computed from some size distribution. The proposed method is based on the area metric given by regular connected area filters. Area compared to local width, i.e. the diameter of the structuring element in the corresponding set of openings by reconstruction in classical DMPs, leads to a rather different multi-scale decomposition. This is investigated here and an example on a very high resolution satellite image tile is given.

Neural network trained morphological processing for the detection of defects in woven fabric

Abstract: Basic morphological operations such as the erosion, dilation, opening, and closing often fail to detect various types of defects that may be present in woven fabric, mainly because of the heuristic selection of structuring element needed for these operations. In this paper, an artificial neural network (ANN) is utilized for the selection of structuring element, where ANN is trained by two pre‐assigned normalized numbers related to the warp and weft counts of the test fabric. The test gray fabric image is pre‐processed to remove noise and the interlaced grating structure of weft and warp and then converted to a binary image by thresholding. An intensity threshold value of the processed fabric image and the dimension of a sliding window needed for correlation operation are obtained from the trained ANN. Defects are detected after morphological reconstruction of the processed binary fabric image, where an ANN trained structuring element is used. The technique is tested on 317 samples for eight different type...

Clustering-driven watershed adaptive segmentation of bubble image

Abstract: In order to extract froth morphological feature, a bubble image adaptive segmentation method was proposed. Considering the image’s low contrast and weak froth edges, froth image was coarsely segmented by using fuzzy c means (FCM) algorithm. Through the attributes of size and shape pattern spectrum, the optimal morphological structuring element was determined. According to the optimal parameters, some image noises were removed with an improved area opening and closing by reconstruction operation, which consist of image regional markers, and the bubbles were finely separated from each other by watershed transform. The experimental results show that the structural element can be determined adaptively by shape and size pattern spectrum, and the froth image is segmented accurately. Compared with other froth image segmentation method, the proposed method achieves much high accuracy, based on which, the bubble size and shape features are extracted effectively.

Multi structuring element top-hat transform to detect linear features

Abstract: Multi structuring element top-hat transform is proposed in this paper to improve the performance of top-hat transform. The desired image feature is treated as a set. And, the set is divided into different subsets. Then, multi structuring elements corresponding to different subsets are constructed. After that, top-hat transform is performed by using the constructed structuring elements, and the results are combined and processed to reconstruct the desired image feature. To verify the efficiency of multi structuring element top-hat transform, the application of linear feature detection is discussed. The analysis and experimental results of multi structuring element top-hat transform show that, because of the efficient performance of multi structuring element top-hat transform, the linear features of different real images in different applications can be efficiently detected. Moreover, multi structuring element top-hat transform can be widely used in different applications.

Plastic bottle shape classification using partial erosion-based approach

Abstract: In this paper, a work on representing plastic bottle shape using erosion based approach for an automated classification is reported. Morphological operations are used to describe the structure or form of an image. By using the two-dimensional description of plastic bottle silhouettes, edge detection of the object silhouette is performed followed by the erosion process. This work will compare two versions of erosion which are regular erosion, the Matlab function imerode and the improved version of erosion which is called partial erosion. Normalization procedure in which the sum pixel value after erosion is divided by the sum pixel of the whole silhouette is done. The normalized values are grouped into histograms of 9 bins of sum pixel value(9HbSPV), find its maximum number to form as a feature set and is then used as inputs to train a neural network for plastic bottle shape classification. Results obtained showed that the proposed feature extraction method can be applied to discriminate plastic bottles according to shape, either slim or broad bottles, efficiently.

Gabor filtering-based scale and rotation invariance feature for 2d barcode region detection

Abstract: 2D barcode region detection is a non trivial problem for barcode revognition and decoding especially in complex backgrounds. Currently, morphological processing has been widely applied to extract potential regions of Data Matrix barcodes due to its low computation complexity. However, this method leads to two problems, adaptive selection of morphological structuring element and high false accept rate. To solve these problems, this paper proposes an innovative method for 2D barcode region detection based on Gabor filtering and BP neural network. The contributions are two folds: 1) we propose a texture feature formulation independent of scale and rotation; 2) BP neural network can avoid the difficulty in morphological structure construction. Large scale experiments show the accuracy and robustness of the proposed method over the traditional morphological method.

Learning of structuring elements for morphological image model with a sparsity prior

Abstract: This paper presents a learning method of a structuring element for morphological image generative model by using a maximum a posterior (MAP) estimation. Mathematical morphology provides set-theoretic image processing methods. In the morphological processing, an image is approximated as a union of translated and level-shifted structuring elements. The specification of the structuring element is crucial to application of the morphology for image processing tasks. In this paper, we introduce the MAP estimation of the structuring element from an input image for the morphological modeling. Sparse prior density functions of approximation errors and occurrence of the structuring elements are assumed for the learning. The structuring element is optimized to maximize the likelihood that is estimated from the prior density functions. In experiments, we show that the proposed learning method is capable to extract fundamental micro-structures of texture images as the structuring elements.

A binarization algorithm for digital meter image based on gray-scale morphology

Abstract: Through analyzing and researching the characteristic of the digital meter image and the effect of the top-hat transform and bottom-hat transform, a kind of binarization algorithm for digital meter image based on gray-scale morphology is presented. A gray-scale digital meter image is processed by top-hat transform and bottom-hat transform separately after a specifically kind of structuring element is chosen. And then, a contrast enhancement image is achieved by subtracting the image obtained by bottom-hat transform from the original image plus the image obtained by Top-hat transform. The binarization procedure is accomplished after threshold value is acquired by the adaptive threshold method. The Experimental results show the effectiveness and robustness for digital meter image with uneven illumination of the algorithm.

Orthogonal shift level comparison reuse for structuring element shape independent VLSI-Architectures of 2D morphological operations

Abstract: In this work we present an efficient and flexible - structuring element shape independent - new VLSI-architecture design approach for 2D morphological operations. Contrary to common used architecture design concepts based on structuring element areal decomposition is the ability to handle arbitrary non-convex flat structuring elements. Furthermore, no intermediate image data storage over several image lines is required and the amount of comparators and registers is reduced by reusing results on so called orthogonal shift levels. This leads to efficient realizations regarding hardware complexity and maximum clock frequency.

Adaptive filter and morphological operators using binary PSO

Abstract: Mathematical morphology is a tool for processing shapes in image processing. Adaptively finding the specific morphological filter is an important and challenging task in morphological image processing. In order to model the filter and filtering sequence for morphological operations adaptively, a novel technique based on binary particle swarm optimization (BPSO) is proposed. BPSO is a discrete PSO, where the components values of a particle position vector are either zero or one. The proposed method can be used for numerous types of applications, where the morphological processing is involved including but not limited to image segmentation, noise suppression and patterns recognition etc. The paper illustrates a fair amount of experimental results showing the promising ability of the proposed approach over previously known solutions. In particular, the proposed method is evaluated for noise suppression problem.

Performance Evaluation of Automated Algorithm for Breast Cancer Cell Counting

Abstract: This paper presents an automated algorithm for breast cancer cell counting and its performance. The algorithm for analyzing stained breast cancer cell image consists of four procedures, i.e. image preprocessing, segmentation, feature extraction, and classification. In the image preprocessing, the wavelet transform is performed. The global thresholding and morphological operations are performed in segmentation. In the feature extraction, the average of b* in CIE L*a*b* color space is extracted. The segmented cells are classified by using extracted feature. If the average of b* is positive, the cancer cell is positive cell. In addition, if the average of b* is negative, the cancer cell is negative cell. The segmentation results show that the average performance is 85% when square-shaped structuring element and city block distance transform are used. The classification results show that the average performance is 94%.

New Alternating Sequential Filters and the application for impulsive noise removal

Abstract: Alternating Sequential Filters (ASFs) are important composing operations of mathematical morphology in different applications. However, because of the image detail smoothing of the opening and closing operations in ASFs, ASFs can not perform very well. New top-hat transform had been proposed through reconstructing the used structuring elements, which can protect image details. And, the main operations in new top-hat transform can achieve the same purpose of opening or closing for bright or black feature extraction. In light of this, a new class of ASFs based on new top-hat transform is proposed in this paper. An application of impulsive noise suppression is used to show the efficient performance of new ASFs. Experimental results show that new ASFs perform better than ASFs, and can be widely used in different applications.

Effectiveness of extrapolation-directed multistep search in unsupervised design for morphological filters for noise removal

Abstract: To recover texture images from impulse noise by the opening operator which is one of morphological operations, a suitable structuring element (SE) has to be estimated. In this paper, we apply a Genetic Algorithm (GA) to an unsupervised design problem of SEs. In previous work, it was shown that deterministic Multi-step Crossover Fusion (dMSXF) which is a promising interpolation-directed crossover method worked very well on the design of SEs. However, dMSXF does not work effectively when parents' characteristics are extremely similar to each other, and an extrapolation search method which explores outside the distribution of the population is required. Here, we introduce deterministic Multi-step Mutation Fusion (dMSMF) as a complementary search of dMSXF for exploring the extrapolation domain to improve the search performance. Through experiments, it is shown that dMSXF+dMSMF can design effective SEs stably.

Fuzzy techniques for noise removal in image sequences and interval-valued fuzzy mathematical morphology

Abstract: Image sequences play an important role in today's world. They provide us a lot of information. Videos are for example used for traffic observations, surveillance systems, autonomous navigation and so on. Due to bad acquisition, transmission or recording, the sequences are however usually corrupted by noise, which hampers the functioning of many image processing techniques. A preprocessing module to filter the images often becomes necessary. After an introduction to fuzzy set theory and image processing, in the first main part of the thesis, several fuzzy logic based video filters are proposed: one filter for grayscale video sequences corrupted by additive Gaussian noise and two color extensions of it and two grayscale filters and one color filter for sequences affected by the random valued impulse noise type. In the second main part of the thesis, interval-valued fuzzy mathematical morphology is studied. Mathematical morphology is a theory intended for the analysis of spatial structures that has found application in e.g. edge detection, object recognition, pattern recognition, image segmentation, image magnification… In the thesis, an overview is given of the evolution from binary mathematical morphology over the different grayscale morphology theories to interval-valued fuzzy mathematical morphology and the interval-valued image model. Additionally, the basic properties of the interval-valued fuzzy morphological operators are investigated. Next, also the decomposition of the interval-valued fuzzy morphological operators is investigated. We investigate the relationship between the cut of the result of such operator applied on an interval-valued image and structuring element and the result of the corresponding binary operator applied on the cut of the image and structuring element. These results are first of all interesting because they provide a link between interval-valued fuzzy mathematical morphology and binary mathematical morphology, but such conversion into binary operators also reduces the computation. Finally, also the reverse problem is tackled, i.e., the construction of interval-valued morphological operators from the binary ones. Using the results from a more general study in which the construction of an interval-valued fuzzy set from a nested family of crisp sets is constructed, increasing binary operators (e.g. the binary dilation) are extended to interval-valued fuzzy operators.

A Study on Implementation of Advanced Morphological Operations

Abstract: Mathematical morphology stresses the role of shape in image pre-processing, segmentation, and object description. It constitutes a set of tools that have solid mathematical background and lead to fast algorithms. The basic entity is a point set. Morphology operates using transformations that are described using operators in a relatively simple non linear algebra. Mathematical morphology constitutes a counterpart to traditional signal processing based on linear operators (such as convolution). In images, morphological operations are relations of two sets. One is an image and the second a small probe, called a structuring element, that systematically traverses the image; its relation to the image in each position is stored in the output image. Fundamental operations of mathematical morphology are dilation and erosion. Dilation expands an object to the closest pixels of the neighborhood. Erosion shrinks the object. Erosion and dilation are not invertible operations; their combination constitutes new operations—opening and closing. Thin and elongated objects are often simplified using a skeleton that is an archetypical stick replacement of original objects. The skeleton constitutes a line that is in the middle of the object. To study the pattern trends with shape as primitive the present article experimented the operations of hit or miss, thinning and gradient operations on textures. The experiments clearly shows uniform patterns in cloth textures and where as more number of regions with different topologies are exhibited by the tree bark textures. This factors clearly co-insides with the nature of these textures.

Protein spot detection in 2D-GE images using morphological operators

Abstract: This work addresses the detection of protein spots in 2D gel electrophoresis images. A novel morphology-based approach is proposed, which utilizes the dilation operator for the localization of regional intensity maxima associated with protein spots. A disk-shaped structuring element (SE) is selected in agreement with the prevalent roundish shape of the majority of protein spots. Thus, spots within rectangular-shaped streaks are correctly detected. SE size is set considering that a certain radius value allows the discrimination of individual spots located in complex spot regions as well as small-sized spots. Moreover, spurious intensity maxima associated with noise are ignored by applying regional intensity constraints. The results of the experimental evaluation lead to the conclusion that the proposed approach detects more actual protein spots and less false spots than a renowned 2D-GE image analysis software package. Furthermore, it does not require user intervention.

A New Approach for the Improving Result of Edge Detection

Abstract: A novel morphological edge detection using adaptive weighted morphological operators is presented. The newly introduced operators employ a weighted structuring element and apply multiplication or division in place of addition and subtraction in classical morphological operations. It judges its edge and its direction by morphological operation. If the edge exists, a big weight factor is put; if the edge doesn’t exist, a small weight factor is put. Thus we can achieve an intensified edge detector. Experimental results prove that the new operators’ performance dominates those of classical operators for images in geometric feature detection, and obtain superb detail edges.

Fingerprint image denoising using morphological amoebas

Abstract: This paper deals with noisy problem in the fingerprint images. With the help of pilot images from Canny edge detection, the method of morphological amoebas can simultaneously reduces noises and keeps useful details by filtering images with non-fixed kernels, outperforms classical morphological operations and other filters with fixed, space-invariant structuring element. What's more, even the approach needs computing the structuring elements for every point in the image, the run-time speed of this algorithm is still faster than some nonlinear algorithms. Finally, a practice with satisfactory result proves that this method do work effectively.

Feature recognition for underwater weld images

Abstract: Real-time sensing and detecting of underwater weld position is a key technique. Laser vision sensing is a good-prospect detecting method. Therein welding image processing and feature recognition are important parts. Noise features of underwater weld image in different water conditions are described. Underwater V-groove weld image pre-processing is discussed. Mean Shift algorithm application to underwater weld image segmentation is studied, and Hough transform to recognize image features of underwater weld is explored. Experiment results show, after such a series of operation as power transformation, limited contrast histogram equalization, top-hat operation, omnidirectional structuring element cascade filtering, underwater weld image is well pre-processed; weld feature image is more effectively segmented by Mean Shift algorithm than by C-means clustering; Hough transform is applicable to precisely recognizing V-groove weld feature points.

Log x-ray image edge detection based on fractal-morphology analysis

Abstract: The aim of this study is to assess log quality and extract the internal defects information from a log x-ray image with fractal and mathematical morphology method. Firstly, the log image is divided into sub areas, calculate the multi-scale fractal feature (D MF ) of each sub areas, the D MF values of different regions in a log image are normally different. According to the values of D MF the internal defects in log can be detected and classified. In order to obtain more continuous edges of the defects in log x-ray image, mathematical morphology theory was also applied in this paper and square structuring element is selected to do a further processing. The experimental result show that, compare to the traditional methods, the method for edge detection of the image based on fractal and mathematical morphology, achieved a better anti-noise performance and preserving the useful defects detail of the log x-ray image effectively.

A Study of Morphological Edge Detector by Multidirectional Structuring Element

Abstract: In this paper we present a morphologic edge detector using multidirectional structuring element approach for detecting edges of complex images under noisy condition. The experimental results show that the proposed edge detector has the desirable properties that a good edge detector should have. Comparative study reveals its detection performance exceeds conventional edge detectors and other morphologic edge detectors.

An improved morphological edge detection algorithm of medical image

Abstract: Medical images usually contain much noise which affects the edge detection accuracy Focusing on this problem, based on the edge detection operator in mathematical morphology, an improved edge detection algorithm is presented by combining the features of the multi-structure elements and the multi-scale edge detection algorithm The algorithm performs opening and closing operations on the data with the alternative sequence filters and the structure elements The weighting operation is applied with different weight coefficients for horizontal, vertical and diagonal directions, while the edge detection operator with dilation type is calculated to obtain the improved edge detection algorithm The steps of the algorithm are described The algorithm is used to extract the edge of MRI image as well as the image of Lena The experimental results indicate the algorithm can considerably improve the edge resolution of the traditional morphological edge detection methods and is practical

De-noising of the pulse signal based on morphology

Abstract: In order to remove the baseline drift,this paper proposes a morphological filtering approach in mathematical morphology by combining open-closing and close-opening operations with different-size structuring elements.The experimentalresults have shown that this approach can effectively and instantly eliminate baseline drift in pulse wave.Furthermore,with comparison with other algorithms,the algorithm displaysits superiority.