Binary Morphological Operations Research Articles

A Robust Image Segmentation Framework Based on Nonlocal Total Variation Spectral Transform

Image segmentation plays an important role in various computer vision tasks. Nevertheless, noise always inevitably appears in images and brings a big challenge to image segmentation. To handle the problem, we study the nonlocal total variation (NLTV) spectral theory and build up an image segmentation framework with NLTV spectral transform to segment images with noise. Firstly, we decompose an image into the NLTV flow in the NLTV spectral transform, with which the max response time of each pixel is calculated. Secondly, a separation surface is constructed with the max response time to distinguish the objects and preserve the structure details in segmentation. Thirdly, the image is filtered by the surface in the NLTV spectral domain, and a rough segmentation result is obtained by means of an inverse transform. Finally, we use a binary process and morphological operations to refine the segmentation result. Experiments illustrate that our method can preserve edge structures effectively and has the ability to achieve competitive segmentation performance compared with the state-of-the-art approaches.

Automated drill cuttings size estimation

Estimation of drill cuttings particle sizes provides near real-time information that can be utilized in drilling operations. The analysis and interpretations of these rock samples is largely manual. Results are qualitative and can be inconsistent. We propose a practical automated method for estimating drill cuttings particle sizes using digital images. The proposed method is robust and combines several well-known and time-tested techniques like: K-means clustering, numerically stable ellipse fitting, and standard morphological operations. Images are first preprocessed and clustered based on color values. The resultant grain mask is enhanced using binary morphological operations. Measurements are then extracted from the mask based on the major and minor axis fitted to the particles. The developed method is tested on drill cuttings digital images from four wells with varying lithologies and particle sizes. Sensitivity analysis on imperfect images shows the robustness of the methodology. The automated results validated against manual measurements show a difference of less than ten percent. Performance of the algorithm is in the order of seconds, which allows for its use in near real-time applications.

Geometry model extraction for perfusion modeling in liver surgery

Background: Planning of liver surgery especially in changed liver parenchyma (cirhosis, steatofibrosis) needs to know liver perfusion status. This can be described by liver perfusion modeling, which basic elements are models of organ geometry and vascular system. However, nowadays Methods does`t produce the model suitable for flow modeling. Due to the imperfections of the scanning Methods, the model’s vascular wall is not smooth enough to faithfully imitate the real blood vessels. Based on computed tomography images, it is necessary to create a model that is suitable for flow modeling. Methods: The model of parenchyma was created by delineation of CT data using 3D Graph-Cut method and user interaction. Liver density is modeled by the Gaussian Mixture as well as the density model of other tissues. Model of the vascular system geometry was obtained by the Connected Threshold method with pre-processing using Gaussian Filter and post-processing based on Binary Morphological Operations. Branch analysis was performed on skeletonized image to determine parameters of vascular segments: length, diameter and orientation. Results: For basic parameters of the model quality we considered the uniformity of hepatic parenchyma coverage by the vascular system. Uniformity was measured as the ratio of the maximum distance of any voxel and the average distance of all voxels. A new geometry model for blood flow modeling has been established. Conclusions: Extraction of the liver blood vessel tree geometry is the starting element for perfusion modeling, that are absolutely crucial for lanning of extended liver resections in diffuse liver parenchyma diseases. The proposed modeling algorithm meets the basic requirements for uniformity of stromal tree distribution in the parenchyma. The Results will be used in preparation of liver surgery analysis and planning. Acknowledgment: This study was supported by the Centrum of Clinical and Experimental liver surgery (UNCE/MED/006) and National Sustainability Program I Nr.LO1503.

The System of Automatic Visual Recognition of Meter Indications

The system for automatic remote reading of meter indications is suggested. Two existing alternative solutions of the system implementation are considered. The main drawback of both solutions is specified, which particularly consists in the necessity of using of the specialized meters. The proposed system, in contrast, is universal, does not require meter replacement, has high reliability due to the absence of moving parts, and permits manual remote diagnostics. The general structure of the proposed system is described. It consists of primary reading device, based on a low-cost videosensor, a microcontroller and a wireless data transmission module, as well as the receiver (server part) with optical recognition software. The software component is considered in more details. Specifically, it is suggested to be implemented using the two-stage procedure. In the first stage, the meter scale is detected and partitioned into separate digit positions. The search of meter scale is proposed to be implemented using the Hough transform, which performs the lines location. Since the Hough transform, which takes binary images as an input is employed, the Canny edge detection algorithm is supposed to be applied first. The meter scale detection is based on the location of lines that forms a rectangular region with specific proportions. When the detection of the scale is performed, the located region is segmented into a separate digit subregions using the binary morphological operations and connected components analysis. The described process is applied relatively seldom (usually when the primary reading device is (re)installed), thus the operator of the system may manually correct the results of the detection and segmentation (these results will be valid for the further use). It reduces the quality requirements for the results, which obtained in the first stage. In the second stage, the recognition of each digit is performed. For these purposes, the use of convolutional neural network is suggested. This network is based on the architecture similar to the LeNet: it operates on small grayscale images and has seven layers (three convolutional, two max pooling, one ReLU and one fully connected layer). The training of network was performed on a specially composed training set. The training itself was conducted using the standard stochastic gradient descent (SGD) with momentum. The “softmax” was used as the loss function. In the result of the training, the correct digit recognition rate in 99,2% is achieved.Ref. 16, fig. 6.

3D skeletonization feature based computer-aided detection system for pulmonary nodules in CT datasets

Pulmonary nodule detection has a significant impact on early diagnosis of lung cancer. To effectively detect pulmonary nodules from interferential vessels in chest CT datasets, this paper proposes a novel 3D skeletonization feature, named as voxels remove rate. Based on this feature, a computer-aided detection system is constructed to validate its performance. The system mainly consists of five stages. Firstly, the lung tissues are segmented by a global optimal active contour model, which can extract all structures (including juxta-pleural nodules) in the lung region. Secondly, thresholding, 3D binary morphological operations, and 3D connected components labeling are utilized to extract candidates of pulmonary nodules. Thirdly, combining the voxels remove rate with other nine existing 3D features (including gray features and shape features), the extracted candidates are characterized. Then, prior anatomical knowledge is utilized for preliminary screening of numerous invalid nodule candidates. Finally, false positives are reduced by support vector machine. Our system is evaluated on early stage lung cancer subjects obtained from the publicly available LIDC-IDRI database. The result shows the proposed 3D skeletonization feature is a useful indicator that efficiently differentiates lung nodules from the other suspicious structures. The computer-aided detection system based on this feature can detect various types of nodules, including solitary, juxta-pleural and juxta-vascular nodules.

Target recognition in synthetic aperture radar images using binary morphological operations

Feature extraction and matching are two important steps in synthetic aperture radar automatic target recognition. This paper uses the binary target region as the feature and proposes a matching scheme for the target regions using binary morphological operations. The residuals between the testing target region and its corresponding template target regions are processed by the morphological opening operation. Then, a similarity measure is defined based on the residual remains to evaluate the similarities between different targets. Afterward, a Bayesian decision fusion is employed to fuse the similarities gained by different structuring elements to further enhance the recognition performance. The nonlinearity of the opening operation as well as the Bayesian decision fusion makes the proposed method robust to the nonlinear deformations of the target region. Experimental results on the moving and stationary target acquisition and recognition dataset demonstrate the validity of the proposed method.

OpenCL accelerated GPU binary morphology image filters for ITK

Binary morphological operations are fundamental tools in image processing but the processing time scales with the number of pixels thus making them expensive operations on the CPU for larger 3D datasets that typically appear in medical imaging. Since erosion and dilatation are special neighborhood operators, each pixel in the output depends only on the neighborhood region which makes them fit for massive GPU parallelization. This document introduces a new ITK module that implements generic (OpenCL based) GPU accelerated binary morphology image filters for erosion and dilatation. The filter can be executed within the standard ITKGPU pipeline.

Error minimization in Brain tissue extractionfor T1 weighted MR images

In the current paper, a simple algorithm is proposed that employs an efficient and unique histogram analysis. A fundamental component of this analysis is an algorithm that partitions a histogram based on the position of the maximum deviation from a Gaussian fit. In the first step, the proposed partitioning algorithm is applied to delimit the highest peak in the gray-level histogram, aiming at identifying and discarding the background region. In the second step, Gaussian distribution is applied twice to the histogram of the head. The goal is to find two thresholds that encompass the gray-level range of the brain tissues and partition the histogram into two regions. A rough binary mask is then generated. Finally, a sequence of binary morphological operations is applied to the mask in order to completely isolate the brain. The significance of the work lies in the fact that it can successfully remove the unwanted regions found in Otsu’s method

Robust Skull-Stripping Segmentation Based on Irrational Mask for Magnetic Resonance Brain Images.

This paper proposes a new method for simple, efficient, and robust removal of the non-brain tissues in MR images based on an irrational mask for filtration within a binary morphological operation framework. The proposed skull-stripping segmentation is based on two irrational 3 × 3 and 5 × 5 masks, having the sum of its weights equal to the transcendental number π value provided by the Gregory-Leibniz infinite series. It allows maintaining a lower rate of useful pixel loss. The proposed method has been tested in two ways. First, it has been validated as a binary method by comparing and contrasting with Otsu's, Sauvola's, Niblack's, and Bernsen's binary methods. Secondly, its accuracy has been verified against three state-of-the-art skull-stripping methods: the graph cuts method, the method based on Chan-Vese active contour model, and the simplex mesh and histogram analysis skull stripping. The performance of the proposed method has been assessed using the Dice scores, overlap and extra fractions, and sensitivity and specificity as statistical methods. The gold standard has been provided by two neurologist experts. The proposed method has been tested and validated on 26 image series which contain 216 images from two publicly available databases: the Whole Brain Atlas and the Internet Brain Segmentation Repository that include a highly variable sample population (with reference to age, sex, healthy/diseased). The approach performs accurately on both standardized databases. The main advantage of the proposed method is its robustness and speed.

Automatic detection of blood vessels in retinal images for diabetic retinopathy diagnosis.

Diabetic retinopathy (DR) is a leading cause of vision loss in diabetic patients. DR is mainly caused due to the damage of retinal blood vessels in the diabetic patients. It is essential to detect and segment the retinal blood vessels for DR detection and diagnosis, which prevents earlier vision loss in diabetic patients. The computer aided automatic detection and segmentation of blood vessels through the elimination of optic disc (OD) region in retina are proposed in this paper. The OD region is segmented using anisotropic diffusion filter and subsequentially the retinal blood vessels are detected using mathematical binary morphological operations. The proposed methodology is tested on two different publicly available datasets and achieved 93.99% sensitivity, 98.37% specificity, 98.08% accuracy in DRIVE dataset and 93.6% sensitivity, 98.96% specificity, and 95.94% accuracy in STARE dataset, respectively.

Edge-detection method using binary morphology on hexagonal images

This paper proposes a new edge-detection and noise-removal method for hexagonally sampled images by using binary morphology edge detection on hexagonally sampled images. This is achieved by applying binary morphological operators on hexagonal images. This approach presents a framework for conversion of hexagonally sampled images and processing to detect edges on a hexagonal grid. The proposed study shows that a method combining horizontal, 60° and 120° directional hexagonal structuring elements achieves results superior to those of a rectangular image. The experimental results showed that the proposed method was more efficient for binary hexagonal image edge detection and noise removal than the commonly used rectangular image.

Non‐subsampled contourlet transform based image Denoising in ultrasound thyroid images using adaptive binary morphological operations

Speckle noise reduction is an important preprocessing stage for ultrasound medical image processing. In this paper, a despeckling algorithm is proposed based on non‐subsampled contourlet transform. This transform has the property of high directionality, anisotropy and translation invariance, which can be controlled by non‐subsampled filter banks. This study aims to denoise the speckle noise in ultrasound images using adaptive binary morphological operations, in order to preserve edges, contours and textures. In morphological operations, structural element plays an important role for image enhancement. In this work, different shapes of structural element have been analysed and filtering parameters have been changed adaptively depending on the nature of the image and the amount of noise in the image. Experimental results of proposed method for natural images, Field II simulated images and real ultrasound images, show that the proposed method is able to preserve edges and image structural details compared with existing methods.

Automated road markings extraction from mobile laser scanning data

Road markings are used to provide guidance and instruction to road users for safe and comfortable driving. Enabling rapid, cost-effective and comprehensive approaches to the maintenance of route networks can be greatly improved with detailed information about location, dimension and condition of road markings. Mobile Laser Scanning (MLS) systems provide new opportunities in terms of collecting and processing this information. Laser scanning systems enable multiple attributes of the illuminated target to be recorded including intensity data. The recorded intensity data can be used to distinguish the road markings from other road surface elements due to their higher retro-reflective property. In this paper, we present an automated algorithm for extracting road markings from MLS data. We describe a robust and automated way of applying a range dependent thresholding function to the intensity values to extract road markings. We make novel use of binary morphological operations and generic knowledge of the dimensions of road markings to complete their shapes and remove other road surface elements introduced through the use of thresholding. We present a detailed analysis of the most applicable values required for the input parameters involved in our algorithm. We tested our algorithm on different road sections consisting of multiple distinct types of road markings. The successful extraction of these road markings demonstrates the effectiveness of our algorithm.

Analysing some R-Implications and its application in fuzzy mathematical morphology

The fuzzy mathematical morphology extends the binary morphological operators to gray-scale and coloured images using concepts of fuzzy logic. To define the morphological operators of fuzzy erosion and dilatation it is used the implications and conjunctions respectively. This work presents an analysis of some R-implications to verify if the pairs of implications and T-norms (conjunctions) were adjunctions. It was used a fuzzy application developed in the Matlab for implementation and tests with the respectively results.

Parallel algorithms for erosion and dilation of label images.

It is sometimes useful to be able to apply binary morphological operations, such as erosions and dilations, to labelled images in a fashion that preserves the labels. This article introduces a specialised class implementing parallel methods described in beare et al [2011] that provide very fast dilations by circles and spheres of arbitary size. Comparisons with other implementations using currently available building blocks are also made.

Spatially-Variant Morphology Operators in Boolean Lattice

Base on the representation of the spatially-variant (SV) binary mathematical morphology operators, we develop a representation of the mathematical morphology on Boolean lattice through the automorphisms group and sup-generating family. Moreover, the spatially-variant (SV) Euclide mathematical morphology operators in the Boolean lattice case are unified.

Narrowband signal localization based on enhanced LAD method

In this paper, an enhanced localization algorithm based on double thresholds (LAD) is proposed for localizing narrow band signals in the frequency domain. A simplified LAD method is first studied to reduce the computational complexity of the original LAD method without performance loss. The upper and lower thresholds of the simplified LAD method are directly calculated by running the forward consecutive mean excision algorithm only once. By combining the simplified LAD method and binary morphological operators, the enhanced LAD method is then proposed and its performance is simply discussed. The simulation results verify the correctness of discussion and show that the enhanced LAD method is superior to the LAD with adjacent cluster combining method, especially at low signal-to-noise ratio.

Unsupervised colour image segmentation using dual-tree complex wavelet transform

In this paper we present an effective unsupervised colour image segmentation algorithm which uses multiscale edge information and spatial colour content. The multiscale edge information is extracted using the dual-tree complex wavelet transform. Binary morphological operators are applied to the edge information to detect seed regions which are large enough to exclude boundary-only regions. The segmentation of homogeneous regions is obtained using region growing followed by region merging in the CIE L ∗ a ∗ b ∗ colour space. We also present an edge preserving smoothing filter as a pre-process for the algorithm. We compare our algorithm with state-of-the-art algorithms and show its superior performance.

Multilevel Training of Binary Morphological Operators

The design of binary morphological operators that are translation-invariant and locally defined by a finite neighborhood window corresponds to the problem of designing Boolean functions. As in any supervised classification problem, morphological operators designed from training sample also suffer from overfitting. Large neighborhood tends to lead to performance degradation of the designed operator. This work proposes a multi-level design approach to deal with the issue of designing large neighborhood based operators. The main idea is inspired from stacked generalization (a multi-level classifier design approach) and consists in, at each training level, combining the outcomes of the previous level operators. The final operator is a multi-level operator that ultimately depends on a larger neighborhood than of the individual operators that have been combined. Experimental results show that two-level operators obtained by combining operators designed on subwindows of a large window consistently outperforms the single-level operators designed on the full window. They also show that iterating two-level operators is an effective multi-level approach to obtain better results.

3D binary morphological operations using run-length representation

In this paper, we propose fast three-dimensional (3D) dilation and erosion methods using run-length encoding (RLE). RLE is an alternative way of representing a binary image using a run, which is a sequence of ‘one’ pixels. We extend the principle of two-dimensional (2D) RLE to 3D RLE and show that the proposed RLE-based 3D morphological operations can save a considerable amount of computation time. From our analysis, we found that the proposed method reduces computation time by more than 30% over voxel-wise processing. This reduction in computational time and complexity increases as more voxels, and consequently more operations, are processed. We describe a complete and detailed set of procedures for deriving the proposed 3D dilation and erosion. Since a morphological operator is a widely accepted tool for various applications, we believe that the proposed 3D morphological methods will reduce the processing time and increase the performance efficiency of these popular filters.