Showing papers on "Structuring element published in 2017"

Detecting Morphological Filtering of Binary Images

Abstract: Morphological operators are widely used in binary image processing for several purposes, such as removing noise, detecting contours or particular structures, and regularizing shapes. In particular, morphological filters are largely adopted in scanned documents to correct the artifacts caused by acquisition and binarization, as well as other processing. In this paper, we propose a novel approach for forensics detection of morphological filtering on binary images. The proposed technique exploits some mathematical properties of the two basic morphologic operators, erosion and dilation, to define an algorithm able not only to detect the application of the filter, but also to estimate the shape of the relevant structuring element. Experimental tests demonstrate that the technique is effective and robust to the most common operations performed on binary image documents.

Morphological Filters: An Inspiration from Natural Geometrical Erosion and Dilation

Abstract: Morphological filters (MFs) are composed of two basic operators: dilation and erosion, inspired by natural geometrical dilation and erosion. MFs locally modify geometrical features of the signal/image using a probe resembling a segment of a function/image that is called structuring element. This chapter analytically explains MFs and their inspirational features from natural geometry. The basic theory of MFs in the binary domain is illustrated, and at the sequence, it has been shown how it is extended to the domain of multivalued functions. Each morphological operator is clarified by intuitive geometrical interpretations. Creative natural inspired analogies are deployed to give a clear intuition to readers about the process of each of them. In this regard, binary and grayscale morphological operators and their properties are well defined and depicted via many examples.

Airborne LiDAR Data Filtering Based on Geodesic Transformations of Mathematical Morphology

Abstract: The capability of acquiring accurate and dense three-dimensional geospatial information that covers large survey areas rapidly enables airborne light detection and ranging (LiDAR) has become a powerful technology in numerous fields of geospatial applications and analysis. LiDAR data filtering is the first and essential step for digital elevation model generation, land cover classification, and object reconstruction. The morphological filtering approaches have the advantages of simple concepts and easy implementation, which are able to filter non-ground points effectively. However, the filtering quality of morphological approaches is sensitive to the structuring elements that are the key factors for the filtering success of mathematical operations. Aiming to deal with the dependence on the selection of structuring elements, this paper proposes a novel filter of LiDAR point clouds based on geodesic transformations of mathematical morphology. In comparison to traditional morphological transformations, the geodesic transformations only use the elementary structuring element and converge after a finite number of iterations. Therefore, this algorithm makes it unnecessary to select different window sizes or determine the maximum window size, which can enhance the robustness and automation for unknown environments. Experimental results indicate that the new filtering method has promising and competitive performance for diverse landscapes, which can effectively preserve terrain details and filter non-ground points in various complicated environments

Contrast Enhancement by Top-Hat and Bottom-Hat Transform with Optimal Structuring Element: Application to Retinal Vessel Segmentation

Abstract: Automatic detection of the retinal blood vessel can be used in biometric identification, computer assisted laser surgery, and diagnosis of many eye related diseases Early detection of retinal blood vessel helps people to take proper treatment against diseases such as diabetic retinopathy, hypertension which can significantly reduce possible vision loss This paper presents an efficient and simple contrast enhancement technique where morphological operations like top-hat and bottom-hat are applied to enhance the image Edge Content-based contrast matrix is measured for selecting the optimal structuring element size and simple straightforward steps are applied for completely extracting the vessels from the enhanced retinal image The proposed method acquires an average accuracy rate of 09379 and 09504 on two publicly available DRIVE and STARE benchmark dataset respectively

Hyperspectral image classification based on morphological profiles and decision fusion

Abstract: Extended morphological profile (EMP) is an important mathematical tool for extracting structural information from the hyperspectral images. However, the accuracy of the EMP-based classification is greatly influenced by the choice of structuring element (SE). In this article, two supervised classification frameworks multiclassifier system with morphological profiles (MCSMP) and MCSMP2 are proposed that exploit rich spectral and structural information of hyperspectral images using EMPs and multiclassifier system for better classification than conventional methods. The EMPs with SEs of multiple shapes are used instead of one particular shape to better detect the response from the structures in the image. The EMPs created from SEs of different shapes are independently classified followed by decision fusion to generate final classification map. The classification results are compared with the conventional pixelwise and other EMP-based methods. The experimental results from three different types of hype...

Supervised Classification of Breast Cancer Malignancy Using Integrated Modified Marker Controlled Watershed Approach

Abstract: Worldwide statistics inform that breast cancer occupies second position causing mortality among women. Symptomatic detection of the disease in its early stage is important for treatment to help the internists and radiologists in their diagnosis. In the proposed module, nuclei locations are obtained using Hough Transform. Nuclei Segmentation of the pre-processed Hematoxylin and Eosin stained breast cancer histopathological images is done using Proposed Modified - Marker Controlled Watershed Approach (MMCWA). Small fixed Structuring Element (SE) size removes respective bright and dark details during opening and closing morphology & large SE size removes huge contour details of the input image. So, in the proposed MMCWA, by using weighted variance method, the adaptive Structuring Element size of the SE map is obtained to protect all details in the image. A total of 20 features, including 5 shape based features and 15 texture features were extracted for classification using Decision Trees, SVM and KNN classifiers. Algorithmic performance evaluation is accomplished and proved that the proposed integrated MMCWA provides better results than the traditional marker controlled watershed. The proposed module was trained with 96 images and tested over 24 images taken from the digital database.

Application of optimized multiscale mathematical morphology for bearing fault diagnosis

Abstract: In order to suppress noise effectively and extract the impulsive features in the vibration signals of faulty rolling element bearings, an optimized multiscale morphology (OMM) based on conventional multiscale morphology (CMM) and iterative morphology (IM) is presented in this paper. Firstly, the operator used in the IM method must be non-idempotent; therefore, an optimized difference (ODIF) operator has been designed. Furthermore, in the iterative process the current operation is performed on the basis of the previous one. This means that if a larger scale is employed, more fault features are inhibited. Thereby, a unit scale is proposed as the structuring element (SE) scale in IM. According to the above definitions, the IM method is implemented on the results over different scales obtained by CMM. The validity of the proposed method is first evaluated by a simulated signal. Subsequently, aimed at an outer race fault two vibration signals sampled by different accelerometers are analyzed by OMM and CMM, respectively. The same is done for an inner race fault. The results show that the optimized method is effective in diagnosing the two bearing faults. Compared with the CMM method, the OMM method can extract much more fault features under strong noise background.

Depth Recovery for Kinect Sensor Using Contour-Guided Adaptive Morphology Filter

Abstract: Consumer-grade RGB-D cameras, such as Kinect sensors, can provide support for much more real-time tasks of 3-D vision than game controllers. However, the inherent depth degradations caused by their infrared ranging will constrain their application potential, but can hardly be avoided through the improvement of the sensor design. Therefore, in this paper, we proposed a contours-guided shape-adaptive morphology filter to efficiently recover the depth of Kinect sensors. First, we put forward a statistical concept to quantitatively evaluate the texture richness of imaging sensors’ data and verify the applicability of morphology filtering on both Kinect 1 and 2 depth data. Then, considering the significance of the semantic contours, a multiresolution RGB-D contour extraction method is introduced to suppress the texture inside objects. Therewith, shape-adaptive structuring element (SASE) for each missing or untrusted depth pixel is created in terms of the contour guidance and the feature of human visual system. Efficient and accurate depth recovery can be finally achieved by combining morphology filtering and the obtained SASEs. Experiments on simulated data set, real Kinect 1, and Kinect 2 data show that our method performs better than many competing state-of-the-art approaches, and avoids the blurring around depth discontinuities.

A specific structuring element-based opening method for rapid geometry measurement of weld pool

Abstract: This paper focuses on measuring weld pool geometry by removing interferences overlapped with the weld pool region in images. The images come from a vision system observing deep penetrate C O 2 laser welding. The measurement is achieved through computer vision. First, Otsu’s method is used for threshold processing to get the binary image. Second, morphological opening with a specific structuring element is used to remove interferences and recover the weld pool. This method is called specific structuring element-based opening (SSEO). It effectively eliminates interferences like spatter, arc light, and plasma to obtain the accurate weld contour. The accurate contour is then used to calculate precise geometry parameters. The SSEO method is also efficient enough to satisfy the real-time requirements.

Double-sided probing by map of Asplund's distances using Logarithmic Image Processing in the framework of Mathematical Morphology

Abstract: We establish the link between Mathematical Morphology and the map of Asplund's distances between a probe and a grey scale function, using the Logarithmic Image Processing scalar multiplication. We demonstrate that the map is the logarithm of the ratio between a dilation and an erosion of the function by a structuring function: the probe. The dilations and erosions are mappings from the lattice of the images into the lattice of the positive functions. Using a flat structuring element, the expression of the map of Asplund's distances can be simplified with a dilation and an erosion of the image; these mappings stays in the lattice of the images. We illustrate our approach by an example of pattern matching with a non-flat structuring function.

Double-sided probing by map of Asplund's distances using Logarithmic Image Processing in the framework of Mathematical Morphology

Abstract: We establish the link between Mathematical Morphology and the map of Asplund's distances between a probe and a grey scale function, using the Logarithmic Image Processing scalar multiplication. We demonstrate that the map is the logarithm of the ratio between a dilation and an erosion of the function by a structuring function: the probe. The dilations and erosions are mappings from the lattice of the images into the lattice of the positive functions. Using a flat structuring element, the expression of the map of Asplund's distances can be simplified with a dilation and an erosion of the image; these mappings stays in the lattice of the images. We illustrate our approach by an example of pattern matching with a non-flat structuring function.

FPGA-Based Parallel Implementation of Morphological Operators for 2D Gray-Level Images

Abstract: In this study a parallel algorithm and its implementation on hardware platform for 2D gray-level morphological dilation/erosion using rectangular structuring element are presented. A pipelined architecture for morphological opening/closing and open–close filter is designed exploiting inter-operator parallelism among dilation/erosion operator. The proposed parallel algorithm processes pixel onstream resulting in low memory utilization. In addition, it reduces computational time with respect to image dimension. The architecture provides real-time performance for processing large-sized structuring elements on high-resolution images. Additionally, it outperforms the processing capabilities of existing delay-line-based architecture, systolic array architecture and parallel implementation in terms of frame rate. It has been observed that the proposed method achieves a maximum speedup by a factor of two and four to compute opening/closing and open–close filter compared to the equivalent non-pipelined implementation. Experimental results show that the architecture for open–close filter is able to achieve about 591 frames per second on \(566\times 566\) images using \(9\times 9\) rectangular structuring elements.

Algorithmic processing to aid in leukemia detection

Abstract: Background: I present our medical context with some basic concepts in order to understand the results of our work, and then I begin the explanation of mathematical morphology. I will conclude by the description of algorithmic processing propose in this paper. Cancers, including leukemia and lymphoma, can cause uncontrolled growth of an abnormal type of blood cell in the bone marrow, resulting in a greatly increased risk for infection and or serious bleeding. Methods: We present detailed steps of our proposed systems, to obtain a final result that shows the detection of abnormal cells. It typically starts with a median filter pre-processing step and then applies different morphologic operator, which allows us to segment the original image and detect cancerous cells. The basic idea behind all the operators in the mathematical morphology is to compare the set of objects to analyze another object of known form, which is called a structuring element. The structuring element is a geometric figure, simple to form, known or arbitrary, and can be a circle, segment, square, or triangle. Results: We show the different results obtained after testing carried out in algorithmic processing using MATLAB: To ameliorate the visualization of the abnormal blood cells, we have applied the elements basis morphological operations in a different way. We have performed an opening by reconstruction and a closing by reconstruction. The obtained result show that we have obtained an efficient detection of the targeted objects (abnormal blood cells or leukemia). Conclusion: In this paper, we have utilized the operators of the mathematical morphology with the aim to detect abnormal cells for diagnostic aid and transmission of accurate and precise clinical information, which helps specialists in medicine (hematologists) to distinguish abnormal cells or cancerous and to follow the evolution of leukemia. The algorithmic processing presented in this article has been able to perform the task of detection of cancerous cells with success; it has produced remarkable and satisfactory results. We think of the future concept as a system of aid for diagnosis from microelectronics integration to the base of reconfigurable technologies applied to cells for the goal of quantification of the cancer region.

An Adaptive Neighbourhood Structuring Element Based Enhancement Technique for Nuclear Images

Abstract: The application of radioactive isotopes for imaging human body parts developed into nuclear imaging technology, including single photon emission computed tomography imaging (SPECT). Visual inspection and interpretation of SPECT images is a challenging task as there is random scattering of photons during the image reconstruction process which affects its contrast. Recognizing even gradual changes in color intensity aids in the interpretation of images. The paper proposes a new image processing technique to enhance cardiac nuclear images generated by a single photon emission computed tomography device by improving the contrast features. The method utilizes the concept of adaptive techniques in morphology. As an initial step, color space conversion is performed to convert the image to a color space suitable for its processing and each slice or tile corresponding to the gated cardiac cycle is extracted. In the second step, the size of the neighbourhood area is selected for the operation of the structuring element. Morphological processing is done as a final step. This methodology can be used as a pre-processing module for computer aided diagnostic systems. The proposed method employs a novel image dependent technique for the enhancement of cardiac SPECT images making use of morphology in a suitable color space. Qualitative and quantitative evaluations prove the effective performance of the proposed algorithm in enhancing cardiac SPECT images.

PDE for Bivariate Amoeba Median Filtering

Abstract: Amoebas are image-adaptive structuring elements for morphological filters that have been introduced by Lerallut et al. in 2005. Iterated amoeba median filtering on grey-scale images has been proven to approximate asymptotically for vanishing structuring element radius a partial differential equation (PDE) which is known in image filtering by the name of self-snakes. This approximation property helps to understand the properties of both, morphological and PDE, image filter classes. Recently, also the PDEs approximated by multivariate median filtering with non-adaptive structuring elements have been studied. Affine equivariant multivariate medians turned out to yield more favourable PDEs than the more popular \(L^1\) median. We continue this work by considering amoeba median filtering of bivariate images using affine equivariant medians. We prove a PDE approximation result for this case. We validate the result by numerical experiments on example functions sampled with high spatial resolution.

Nonlinear Interpolation in the Fourier Domain Guided by Morphologic Filters

Abstract: Morphologic filters are used here to interpolate missing values from sets of frequency domain measurements, as occurs in Magnetic Resonance Imaging. MRI data acquisition is done in the Fourier domain which is often sub-sampled to reduce the required scan time. Partial recovery of the missing frequency samples permits direct Fourier inversion to provide a rapid and improved initial estimation of the spatial data. The interpolated image should also improve the convergence of subsequent iterative reconstruction that is used in compressed sensing methods. Spectral analysis of morphologic operators appears rarely in prior publications. We examine the non-linear spectral changes that arise from applying morphologic open and close operations. We use a form of alternating sequential filters (like those proposed by Jean Serra in 1988) to expand the content of the Fourier spectrum around the known measured values. The alternating sequence terminates just before the structuring element size that maximises the added spectral energy. The maximum in spectral energy coincides with the optimal reconstructed psnr. This interpolation, being idempotent, at worst, adds nothing to the known data. The method is, of course, sensitive to both the Fourier sub-sampling pattern and to the spectral content of the data. It thus works best for data that contains strong steps between flat zones rather than images comprised mostly of smooth curves. This nonlinear interpolation method can increase the mean psnr values by 3 for sampling rates above 70%. In the most favourable cases, psnr gains well above 20 can be obtained for sampling rates down to 60%, with psnr gains above 10 possible for sampling rates as low as 20%.

Effectiveness of morphological reconstruction operators in change detection for remote sensing images

Abstract: Change detection (CD) in multi-temporal images aims at quantifying the temporal effects or changes in remote sensing images taken at different times of the same area of Earth With huge constellations of satellites setup by various countries, monitoring the Earth's surface for changes helps us understand and respond to various natural phenomenon affecting the Earth's atmosphere In this paper, we have used texture features along with the spectral features for CD The texture features have been extracted after applying three different morphological reconstruction operators, namely, opening by reconstruction, closing by reconstruction and opening of closing by reconstruction Also flat and non-flat structuring elements (SE) have been used for applying morphological reconstruction The paper compares the impact of different types of morphological operators on the accuracy of the CD It also presents the comparison between the effectiveness of flat and non-flat SEs on the accuracy

Morphological edge enhancement techniques on satillite image

Abstract: Satellite image information Enhancement is very important for computer vision and analysis of the data. The satellite image information losses with lack of actualization sensors and different types of noise added at processing stages. Some standard traditional methods and non windowing techniques gave unsatisfactory results, here we proposed new algorithm for advanced morphological techniques with combination of windowing methods for improving Edge enhancement and detection. Obtained satisfactory results and good performance of PSNR and RMSE values. In this proposed method Structuring element (SE) impact on Morphological operations and it introduce with help of Set Theory.

Object Boundary Identification using Enhanced High Pass Frequency Filtering Algorithm and Morphological Erosion Structuring Element

Abstract: Object boundary detection is the process of finding instances of real-world objects such as faces, bicycles and building limitations in an image. Shadow image Boundary detection is a pre-processing technique in image processing. A solid shadow image object contains boundaries of the type Step, Roof, Ramp and Spike. The traditional methods of shadow image boundary detection are sensitive to the noise and cannot identify the boundaries correctly. Photon noise, Blurring, Irregularities of the surface structure of objects are the factors affecting the state of arts boundary detection techniques. This paper presents a content based boundary detection technique with the help of a highpass frequency filtering algorithm and morphological erosion structural element. The erosion element is used to reconstruct the damaged region of the shadow image boundary. The boundary detection technique Canny,Prewitt, Sobel and proposed algorithm experiment over the entire Shadow image dataset and the proposed algorithm shows a better result in the peak-signal-to-noise ratio (PSNR).The performance evaluation of the proposed technique based on the peak-signal-to-noise ratio is presented.

Quality enhancement of degraded sundanese lontar images using direct subtraction and retrospective correction methods in several color space

Abstract: Enhancing quality of degraded images is important preliminary step for automatic extraction of the Sundanese digitized ancient manuscript known as lontar. The degraded lontar images have circular, inhomogeneity illumination characteristics which are represented by more brightness on inner center of images and darker in the outer ellipse-like area of the images. The purpose of enhanced image processing is to distribute the pixel's intensity so the images can have similar characteristics. The proposed method used in this paper is primarily based on background subtraction technique which is implemented in three color spaces. Background images are estimated using morphological mathematics using specific type and size of structuring element. This estimation process has to be performed due to unavailability of exact background image captured during image acquisition step. Theoretical foundations of the proposed method along with experimental results are reported in this paper. The proposed method has been tested on 12 Sundanese lontar images which denotes this approach different and unique from most of the existing methods in this field of study. Conducted experiment demonstrated the successful results of the method which is represented by displaying profile characteristics of each images on row 128.

Partial volume morphology: eliminating precision loss in binary morphology

Abstract: Binary morphology has innumerable applications in biomedical imaging, from segmentation to denoising. However, it suffers from inherently low precision. This is primarily because binary morphology is a binary technique, where each image voxel is all-or-nothing included or excluded. Many desirable structuring element shapes, especially circles or spheres, are poorly approximated on regular grids. Making things worse, common workflows involving multiple binary morphology iterations, such as opening or closing, compound this error. Also, small structuring elements often cannot be applied to 3D anisotropic image volumes. This work describes an extension to the theory of binary morphology, dubbed partial volume morphology or PVM, which allows the structuring element and/or image to hold fractional gray values to account for partial volumes. Partial volume morphology enables arbitrarily shaped structuring elements to be used, regardless of the underlying image resolution, with arbitrary precision. This technique also extends to 3D anisotropic volumes, allowing high precision morphological operations in anisotropic datasets heretofore impossible with binary morphology. This technique can be applied to a binary segmentation, where it provides subtle improvements and eliminates precision error in the intermediate steps of a multiple-operation workflow. Additionally, PVM is particularly suited for use on ‘soft’ segmentated data, where the partial volume contribution or probability at each point can be found. With segmentation and structuring elements both partial volume aware, partial volume morphology reaches its full potential as a high precision analytical tool. An open source reference implementation in Python, pvmpy, is provided.

A Guided Tour of Connective Morphology: Concepts, Algorithms, and Applications

Abstract: Connective morphology has been an active area of research for more than two decades. Based on an abstract notion of connectivity, it allows development of perceptual grouping of pixels using different connectivity classes. Images are processed based on these perceptual groups, rather than some rigid neighbourhood imposed upon the image in the form of a fixed structuring element. The progress in this field has been threefold: (i) development of a mathematical framework; (ii) development of fast algorithms, and (iii) application of the methodology in very diverse fields. In this talk I will review these developments, and describe relationships to other image-adaptive methods. I will also discuss the opportunities for use in multi-scale analysis and inclusion of machine learning within connected filters.

Spatially-variant mathematical morphology for color images

Abstract: In this paper, we present an approach of the generalization of the Spatially-Variant Morphological Operators to the color images, that preserves the concept of the structuring function. Two methods are suggested. The first method is based on total ordering and the second on marginal treatment of each component of the image. For each method, we define the notion of Spatially-Variant (SV) structuring elements, the basic color operators (dilation, erosion, opening and closing). The former operators allow the construction of morphological filters obtained by infimum, supremum and composition operations. Examples are provided through simulations to show the potential power of the defined operators for image filtering.