Showing papers on "Structuring element published in 2019"

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Abstract: Morphological reconstruction (MR) is often employed by seeded image segmentation algorithms such as watershed transform and power watershed, as it is able to filter out seeds (regional minima) to reduce over-segmentation. However, the MR might mistakenly filter meaningful seeds that are required for generating accurate segmentation and it is also sensitive to the scale because a single-scale structuring element is employed. In this paper, a novel adaptive morphological reconstruction (AMR) operation is proposed that has three advantages. First, AMR can adaptively filter out useless seeds while preserving meaningful ones. Second, AMR is insensitive to the scale of structuring elements because multiscale structuring elements are employed. Finally, the AMR has two attractive properties: monotonic increasingness and convergence that help seeded segmentation algorithms to achieve a hierarchical segmentation. Experiments clearly demonstrate that the AMR is useful for improving performance of algorithms of seeded image segmentation and seed-based spectral segmentation. Compared to several state-of-the-art algorithms, the proposed algorithms provide better segmentation results requiring less computing time.

Human visual system based optimized mathematical morphology approach for enhancement of brain MR images

Abstract: Brain tumor is a life-threatening disease with fast growth rate, which makes its detection a critical task. However, low contrast and noise content in brain magnetic resonance images (MRI) hampers the screening of brain tumor. Therefore, contrast enhancement of these images are necessary to obtain a more definitive imaging for tumor detection. This paper presents an optimized enhancement model for processing Brain MRI by employing morphological filters in coherence with human visual system (HVS) system. The HVS coherence in response of filtering process is incorporated by combination of top-hat and bottom-hat morphological operators using logarithmic image processing model. Application of morphological filter requires selection of structuring element of requisite shape and size to ensure precision in brain tumor detection. This process is challenging as brain tumors (in MRI) may vary rigorously in size and morphology with each case or stages of tumor. Herein, this constraint has been resolved by using a disk-shaped structuring element whose order (size) is optimized using particle swarm optimization algorithm. The enhancement results are quantitatively evaluated using image quality measurement parameters like contrast improvement index, average signal to noise ratio, peak signal to noise ratio and measure of enhancement.

A Feature Selection Framework-Based Multiscale Morphological Analysis Algorithm for Fault Diagnosis of Rolling Element Bearing

Abstract: Multiscale morphological analysis (MMA) is considered as a prevalent and efficient approach of mathematical morphology (MM), which has received a lot of attention in fault diagnosis. However, traditional MMA mainly focuses on the selection of structuring element (SE) scale and fault feature extraction based on single index, which is not easy to get comprehensive and rich fault information. Consequently, for the purpose of solving the issue of losing local fault information of integrating traditional MMA with single index and improving fault feature extraction accuracy, a new algorithm named feature selection framework-based multiscale morphological analysis (FS-MMA) is proposed in this paper. Within this algorithm, the weighted MMA is firstly formulated through the incorporation of three operations (i.e. combination morphological filter-hat transform (CMFH), multicale SE and weighted arithmetic), which can cover fault symptoms at different scales. Subsequently, multi-domain features of the raw vibration signal are calculated and entropy weight method (EWM) is adopted to select several typical sensitive features. Finally, grey correlation analysis (GCA) is conducted to determine the optimal SE scale of MMA and achieve fault feature extraction of rolling element bearing. The effectiveness and feasibility of the presented algorithm are validated by analyzing the simulated and experimental bearing fault data. The analysis results show that FS-MMA has better performance in bearing fault feature extraction and diagnosis accuracy compared with traditional MMA with single index.

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Abstract: Morphological reconstruction (MR) is often employed by seeded image segmentation algorithms such as watershed transform and power watershed as it is able to filter seeds (regional minima) to reduce over-segmentation. However, MR might mistakenly filter meaningful seeds that are required for generating accurate segmentation and it is also sensitive to the scale because a single-scale structuring element is employed. In this paper, a novel adaptive morphological reconstruction (AMR) operation is proposed that has three advantages. Firstly, AMR can adaptively filter useless seeds while preserving meaningful ones. Secondly, AMR is insensitive to the scale of structuring elements because multiscale structuring elements are employed. Finally, AMR has two attractive properties: monotonic increasingness and convergence that help seeded segmentation algorithms to achieve a hierarchical segmentation. Experiments clearly demonstrate that AMR is useful for improving algorithms of seeded image segmentation and seed-based spectral segmentation. Compared to several state-of-the-art algorithms, the proposed algorithms provide better segmentation results requiring less computing time. Source code is available at this https URL.

Automatic generation of adaptive structuring elements for road identification in VHR images

Abstract: Road extraction from very high resolution remotely sensed images is crucial in many urban applications. Acquiring automatically up-to-date and accurate information about roads is significant for various intelligent applications such as smart vehicle navigation, planning urban areas, roads monitoring and traffic management for intelligent transportation systems, and leading proper military operations. All possible knowledge about roads properties must be incorporated in designing intelligent systems that interpret and decide with high precision the existence of roads in remote sensing images. Various extraction techniques rely on mathematical morphology (MM) that detects desired road structures through a sliding standard and empirically chosen structuring element (SE) over the input image. In this paper, we design an intelligent process that not only combines spectral and spatial properties of roads but also impacts significantly the flexibility in retrieving spatial information. Indeed, we propose an adaptive algorithm that supplies tailored and most adequate arbitrary structuring elements for every image at hand. It has the significant impact of providing flexibility since every arbitrary generated SE is exclusively dedicated to the processed image. The processing consists of two major steps: a) we use the particle swarm optimization algorithm to look for the adaptive SEs; b) we introduce a priori knowledge based on human visual interpretation of roads characteristics and define some spatial indices to refine the results. We evaluated our method over many remotely sensed images; accuracy results show that the proposed method outperforms standard approaches which are limited to utilize only empirically chosen and standard SEs.

Optimized maximum principal curvatures based segmentation of blood vessels from retinal images

Abstract: In retinal image of the human eye, extracting tree shaped retinal vasculature is an important feature which helps eye care specialists or ophthalmologists to pursue proper diagnostic procedures. In this paper, an approach named Optimized Maximum Principal Curvatures Based (OPCB) segmentation is been proposed for efficient extraction of blood vessels from retinal fundus images. This algorithm proceeds into two stages. Firstly, pre-processing on input retinal images is done by Particle Swarm Optimization (PSO) technique which is an automatic process for computing the global optimum pixels of the image in order to avoid working with all or random pixels. Later, these optimal pixels are made to undergo further processing with Gaussian Filter to remove the noisy pixels among them. Secondly, the post-processing is carried out in four steps: (i)Maximum Principal Curvatures (maximum-eigenvalues) of the second order derivative matrix (Hessian) quantity of the pre-processed PSO image are computed by using ‘Lambda Function’, which then does region growing of the tree-shaped blood vessels by convolving Maximum Principal Curvatures with the mathematical erosion structuring element of. (ii)After extraction of blood vessels, section-wise contrast enhancement is performed by using Adaptive Histogram Equalization that work on 8x8 tiles of image being segmented for smoothing artificially introduced boundaries if any, and also for eliminating over amplified noise. (iii) ISODATA (Iterative Self-Organizing Data Analysis Technique) thresholding is used to classify the image globally where the image’s foreground vascular structure is segmented from the background. (iv) A ‘morphologically opened’ operation is performed to prune falsely segmented isolated regions, to achieve very accurate segmentation. This proposed technique tested online available colored retinal images of STARE and DRIVE databases. As an outcome, the proposed approach achieves the superior segmentation accuracy of 96% which outperformed many empirically proven segmentation methods which were proposed in the past.

Deep morphological neural networks

Abstract: Mathematical morphology is a theory and technique to collect features like geometric and topological structures in digital images. Given a target image, determining suitable morphological operations and structuring elements is a cumbersome and time-consuming task. In this paper, a morphological neural network is proposed to address this problem. Serving as a nonlinear feature extracting layer in deep learning frameworks, the efficiency of the proposed morphological layer is confirmed analytically and empirically. With a known target, a single-filter morphological layer learns the structuring element correctly, and an adaptive layer can automatically select appropriate morphological operations. For practical applications, the proposed morphological neural networks are tested on several classification datasets related to shape or geometric image features, and the experimental results have confirmed the high computational efficiency and high accuracy.

A novel fuzzy pixel intensity correlation based segmentation algorithm for early detection of Alzheimer’s disease

Abstract: Alzheimer’s disease (AD) is considered to be one of the most fatal neurological disorders and is identified as significant tissue loss in the hippocampus region of human brain. This paper presents a fuzzy based novel segmentation algorithm for brain MRI images. A structuring element for opening of gray scale converted test MRI scans has been proposed in this regard. It effectively enhances the contrast of lateral ventricle region of brain which contains crucial information for mild cognitive impairment (MCI). Proposed rule-base of higher order fuzzy system dynamically chooses edge pixels and accordingly predicts the next probable edge pixel. Proposed fuzzy inference system is inspired by fuzzy connectedness algorithm and converts probable edge pixels into edge pixels depending on the intensity correlation between ordered pixels in support of rule-base and assembles it into an edge contour. Our proposition is finally tested over several ADNI brain images of different subject and orientation. Experimental results identify a promising improvement in detection of object boundaries and enhance contrast both qualitatively and quantitatively.

Contrast Enhancement of Medical X-Ray Image Using Morphological Operators with Optimal Structuring Element.

Abstract: To guide surgical and medical treatment X-ray images have been used by physicians in every modern healthcare organization and hospitals. Doctor's evaluation process and disease identification in the area of skeletal system can be performed in a faster and efficient way with the help of X-ray imaging technique as they can depict bone structure painlessly. This paper presents an efficient contrast enhancement technique using morphological operators which will help to visualize important bone segments and soft tissues more clearly. Top-hat and Bottom-hat transform are utilized to enhance the image where gradient magnitude value is calculated for automatically selecting the structuring element (SE) size. Experimental evaluation on different x-ray imaging databases shows the effectiveness of our method which also produces comparatively better output against some existing image enhancement techniques.

Fault Diagnosis of Rolling Element Bearing Using an Adaptive Multiscale Enhanced Combination Gradient Morphological Filter

Abstract: The extraction of the vibration impulse signal plays a crucial role in the fault diagnosis of rolling element bearing. However, the detection of weak fault signals generally suffers the strong background noise. To solve this problem, a new adaptive multiscale enhanced combination gradient morphological filter (MECGMF) is proposed for the fault diagnosis of rolling element bearing. In this method, according to the filtering ability of four basic morphological filter operators, an enhanced combination gradient morphological operation (ECGMF) is first proposed. This design enhances the ability of MECGMF to extract impulse signals from strong background noise. And accordingly, a new adaptive selection strategy named kurtosis fault feature ratio (KFFR) is proposed to select an optimal structuring element (SE) scale. Subsequently, the optimal SE scale is the largest measure of multiscale morphological filtering for extracting bearing fault information. In the meanwhile, the effectiveness of the proposed method is verified by simulation and experiment. Finally, the experimental results demonstrate that MECGMF can effectively restrain the noise interference and extract fault characteristic signals of rolling element bearing from strong background noise. Moreover, comparative tests show that the proposed method is more effective in detecting wind turbine bearing failures.

Quantum Circuit Realization of Morphological Gradient for Quantum Grayscale Image

Abstract: In this paper, based on the principle of classical morphology operations, the flat grayscale dilation and erosion operations are proposed for NEQR quantum image model. Furthermore, through combining these two morphology operations, we further realize the morphological gradient operation. As the basis of designing of grayscale morphology operations, a series of quantum circuit designs arepresented, which includes special add one operation UA1(n) and special subtract one operation US1(n) both for an n-length qubits sequence, quantum unitary operation UC, parallel subtractor (PS) module, quantum comparator output the large QCOL and quantum comparator output the small QCOS modules. When designsthe concrete quantum circuit, a sequence of UA1(n) and US1(n) modules are used to obtain the quantum image sets based on the shape of specific structuring element. Then, the searching for maximaor minima in a certain space is involved, which can be solved by cascading a series of QCOL and QCOS modules in certain order. Finally, the PS module can be used to calculate the difference of the maxima and minima for producing the morphological gradient. The circuit’s complexity analysis illustrate that our scheme is very lower to the classical morphology operations.

A Survey on Various Fabric Defect Detection Methods

Abstract: A survey on various fabric defect detection algorithms is conducted. A local homogeneity, mathematical morphology based novel fabric flaw identification algorithm is implemented. Initial phase includes the construction of a neoteric homogeneity image (H-image), from which the local homogeneity of every pixel is calculated. From the H-image we arrive at the Histogram which is required to select the suitable threshold value which results in producing the Binary image. Using the Binary image we can excerpt the convenient size and shape of the Structuring Element (SE) that is needed for mathematical morphology. In a second phase, a sequence of Morphological operations are carried out on the image with the Structuring Element in order to identify any flaws in the garments. Simulation outputs depict perfect flaw identification having false alarms to be less. Secondly, we put forward an automated image processing for identifying stripe deficiencies in circular shaped knitted cloth materials. We represent how a clearly viewable flaw can be optically embellished to upgrade human verification and how image processing based on descriptor and machine learning could be utilized to permit automatic stripe identification. Finally in this study, data sets obtained by applying local binary pattern and gray level co-occurrence matrix feature extraction methods on Tilda textile data are trained with artificial neural networks and two different models are created and success rates are compared.

Morphological-Based Localization of an Iris Image

Abstract: Iris recognition is one of the reliable biometric techniques used for human identification purpose. It provides the unique information about a person with natural features such as both the left and right eye irises of a person is different and stable with the age and also the quality of the iris is not affected by contact lenses and eyeglasses. The authors suggested that iris recognition fails due to the tedious process involved during localization. The failure rate can be decreased by performing edge detection with a suitable localization algorithm. The authors proved that histogram equalization is one of the best image enhancement techniques to process an image with probability density function of different gray-level values. The edges of an image are identified using an edge detection algorithm using mean value and threshold values, and the localization of an image is rectified by the neighbors of a pixel and structuring element morphological operations. Compare the performance of the algorithms and prove that the localization of an edge using the structuring element of the morphological operation produces the best results compared with other morphological operations using the neighbors of a pixel.

An investigation of a CT noise reduction using a modified of wiener filtering-edge detection

Abstract: The aims of this study were to investigate the noise reduction in a CT image using a modified Wiener filtering-edge detection method. We modified the noise reduction algorithm of a combination of the Wiener filter and edge detection by addition of a dilation stage after edge detection. We then evaluated kernel size of the Wiener filter, threshold values in the edge detection, and size of structuring elements in the dilation process. Images of adult anthropomorphic and self-built wire phantoms were acquired by the new 4-row multislice CT Toshiba Alexion™. The images of the anthropomorphic phantom were used for a visual evaluation, while the images of the wire-phantom were used to obtain the spatial resolution and noise of the images. A Wiener filter-edge detection filter coupled with dilation, potentially reduced more CT noise. We found that the spatial resolution and noise of the filtered images were influenced by the size of the Wiener filter kernel, threshold of edge detection, and size of structuring element.

Structuring Element-counting Approach for Morphological Pattern Spectrum-based Image Manipulation Detection

Abstract: The use of digital images has become quite widespread in legal, medical, and private contexts. However, anyone can easily edit or manipulate any digital image on a computer. Thus, an effective method for detecting digital image manipulation is required for retaining authenticity. Image-manipulation detection is applied in investigations of crimes and photographic evidence. In this paper, we describe a technique for detecting a manipulated image by morphological pattern spectrum. Before we have researched morphological pattern spectrum detected manipulation. We propose the new technique which counts a number of the same scale as the structuring element scale by morphological pattern spectrum in an image. So it can judge a manipulated image in detail because the new technique can detect the number of a manipulated scale. Thus, even if the previous technique judge a large different in the pattern spectrum between the original image and the manipulated image, the new technique can judge to be actually small manipulation.

The QRS complex detection using morphological filtering

Abstract: This article presents a method of QRS complex detection and more precisely the R wave in an electrocardiogram (ECG) based on the mathematics morphology which calls upon the four operators’ morphology, erosion, dilation, opening and closing. These operators are combined with a window relocated which is called the structuring element. Morphological filtering uses the structuring element to extract the shape information from ECG signal. The effectiveness of the proposed algorithm is tested by using recordings obtained from the MIT-BIH arrhythmia database. Experiment results show that the proposed algorithm outperforms the other algorithms.

Novel Open Source Morphology Using GPU Processing With LTU- CUDA

Abstract: A mathematical morphology is used as a tool for extracting image components that are useful in the representation and description of region shape. The mathematical morphology operations of dilation, erosion, opening, and closing are important building blocks of many other image processing algorithms. The data parallel programming provides an opportunity for performance acceleration using highly parallel processors such as GPU. NVIDIA CUDA architecture offers relatively inexpensive and powerful framework for performing these operations. However the generic morphological erosion and dilation operation in CUDA NPP library is relatively naive, but it provides impressive speed ups only for a limited range of structuring element sizes. The vHGW algorithm is one of the fastest for computing morphological operations on a serial CPU. This algorithm is compute intensive and can be accelerated with the help of GPU. This project implements vHGW algorithm for erosion and dilation independent of structuring element size has been implemented for different types of structuring elements of an arbitrary length and along arbitrary angle on CUDA programming environment with GPU hardware as GeForce GTX 480. The results show maximum performance gain of 20 times than the conventional serial implementation of algorithm in terms of execution time.

Efficient Lung CT Image Segmentation using Mathematical Morphology and the Region Growing algorithm

Abstract: Computer Aided Diagnosis (CAD) systems are often used during Today's medical practicality. It helps the physician to perform an accurate detection and diagnosis of Lung Pathologies. Lung CT image segmentation is a prerequisite in lung CT analysis. In this paper we proposed an automated hybrid method for lung segmentation based on both mathematical morphology and the region growing algorithm. the seed points are selected automatically without any user interaction. Also, the structuring element used in mathematical morphology operation is dynamic and it changes its shape and parameters according to the input 2D lung CT slices.

A Novel Algorithm for Analysis of a Local Shape In the 3-D Gray Image

Abstract: For shape analysis in 3-D, probably skeletonization will become a momentous tool for analyzing the different shapes in 3-D, as similar to the 2-D. This paper discusses about topology preserving 3-D skeletonization sequential algorithm which computes curve skeletons for the given solid object. The original geometry of the given object will be well-preserved by curve skeleton. In the proposed algorithm, each voxel of the three-dimensional image is classified as two classes: boundary, corner. The object is scanned with the use of a structuring element, border and corner voxels are classified based on the certain condition proposed in this paper. This algorithm does not require any computations which are complex, large number of windows which make implementation a complex. The proposed algorithm is various 3-D simulated images and resulting skeletons are found to satisfactory. The 3-D simulated images and its skeletons are viewed with the help of ImageJ software.

A Fractal-Based Approach to Network Characterization Applied to Texture Analysis

Abstract: This work proposes a new method for texture analysis that combines fractal descriptors and complex network modeling. At first, the texture image is modeled as a network. Then, the network is converted into a surface where the Cartesian coordinates and the vertex degree is mapped into a 3D point in the surface. Then, we calculate a description vector of this surface using a method inspired by the Bouligand-Minkowski technique for estimating the fractal dimension of a surface. Specifically, the descriptor corresponds to the evolution of the volume occupied by the dilated surface, when the radius of the spherical structuring element increases. The feature vector is given by the concatenation of the volumes of the dilated surface for different radius values. Our proposal is an enhancement of the classic complex networks descriptors, where only the statistical information was considered. Our method was validated on four texture datasets and the results reveal that our method leads to highly discriminative textural features.

Image Regularization with Morphological Gradient Priors Using Optimal Structuring Elements for Each Pixel

Abstract: As an image prior for image restoration, the use of the sum of the morphological gradient for an image has been proposed. In this paper, we propose a method of optimizing the structuring element (SE) for each pixel, in particular, by greatly reducing the computational burden for optimization by adopting a new evaluation method for the SE in simulated annealing. By optimizing the SE for each pixel, edges of the image can be faithfully evaluated, and the improvement of restoration accuracy can be expected. An experimental result shows the effectiveness of the proposed method.

Implementation of Linear Structuring Element in OpenCV for Blood Vessel Segmentation from Color Fundus Images

Abstract: This paper presents an improved blood vessel segmentation technique from color fundus images using morphology operation. More accurate blood vessel segmentation from fundus images plays key role for screening of diabetic retinopathy and glaucoma. This paper has made significant contributions by developing linear structuring element for blood vessel detection using OpenCV. The proposed method involves three stages namely; pre-processing, generation of linear structuring element and detection of blood vessels from fundus image, In first stage, color fundus images are pre-processed or enhanced as these images often suffer from uneven illumination, low contrast and noise. In second stage, twelve linear structuring elements are generated and finally, in the third stage, blood vessel segmentation algorithm is applied to improve the extraction of diagnostic features such as microaneurysms and hemorrhages, leading to more accurate detection of diabetic retinopathy.

From Structuring Elements to Structuring Neighborhood Systems

Abstract: In the context of mathematical morphology based on structuring elements to define erosion and dilation, this paper generalizes the notion of a structuring element to a new setting called structuring neighborhood systems. While a structuring element is often defined as a subset of the space, a structuring neighborhood is a subset of the subsets of the space. This yields an extended definition of erosion; dilation can be obtained as well by a duality principle. With respect to the classical framework, this extension is sound in many ways. It is also strictly more expressive, for any structuring element can be represented as a structuring neighborhood but the converse is not true. A direct application of this framework is to generalize modal morpho-logic to a topological setting.

Zonohedral Approximation of Spherical Structuring Element for Volumetric Morphology

Abstract: Performing dilation and erosion using large structuring elements can be computationally slow – a problem especially pronounced when processing volumetric data. To reduce the computational complexity of dilation/erosion using spherical structuring elements, we propose a method for approximating a sphere with a zonohedron. Since zonohedra can be created via successive dilations/erosions of line segments, this allows morphological operations to be performed in constant time per voxel. As the complexity of commonly used methods typically scales with the size of the structuring element, our method significantly improves the run time. We use the proposed approximation to detect large spherical objects in volumetric data. Results are compared with other image analysis frameworks demonstrating constant run time and significant performance gains.

Forensic Image Reconstruction Based on Efficient Morphological Operational Model

Abstract: Fragmented forensic image recovering from unallocated space plays an important role in computer forensics and investigation For clear-cut investigation, it is necessary to reconstruct the recovered forensic images Morphological operations can reconstruct the recovered images Existing paper applies different methods to a damaged image based on structuring element, but cannot recuperate damaged image properly This paper proposed a morphological image processing model that applies some operations like H-maxima transform, bottom-hat transformation, erosion, opening, dilation, closing operations based on structuring elements to sharp the final output image This model can fill all holes of the damaged image properly compared to reference model Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR) of the proposed model is higher than the reference model This paper applies security mechanism such as watermarking with Discrete Cosine Transform (DCT) to hide the image in the forensic workstation

Nonlinear Quantum-Inspired Weighting Structuring Element for Bearing Impulse Response Signal Processing

Abstract: In order to solve the disadvantage of conventional structuring element (CSE) where amplitude does not change in accordance with the analyzed signal, the quantum theory is combined and a nonlinear quantum-inspired weighting structuring element (NQWSE) is proposed. The NQWSE which is utilized to extract the bearing impulse response signal can adjust its amplitude according to the mechanical signal. Firstly, after constructing the multiple quantum bits system for signals, the mapping method which is employed to map the quantum space to the real space is presented and the parameters of the mapping method are set. The nonlinear amplitude probability is calculated based on the stochastic characteristics of the bearing signals, while the dynamic amplitude is calculated based on the local feature of the bearing signals in a subwindow. Then the mathematical formula of NQWSE is derived by incorporating the mathematical expectation into the quantum theory and the mapping method. Finally, the NQWSE is applied to extract the fault information of a failure bearing. The results reveal that NQWSE can extract the bearing impulse response signals exactly.

Morphology based Character Recognition of Overlapped and Touched Objects

Abstract: This paper presents an attempt made to recognize characters from English alphabets and numbers by first segmenting them using bounding box and then recognizing each character individually. Each character data set contains 26 alphabets. For connected characters morphological operations are used that process the image based on shapes. The input image is processed using morphological operations by applying a structuring element and creating an output image of the same size. For the purpose of character recognition template matching technique is used. The proposed system shows good recognition rates as compared to other similar schemes for character segmentation and recognition.