Global Thresholding Method Research Articles

Lane Detection Based on Two-Stage Noise Features Filtering and Clustering

Lane detection is essential for autonomous vehicles, and vision-based lane detection is widely used in the field of intelligent driving cars because of its low cost. Aiming to solve the problem of false detection caused by surrounding vehicles during lane detection, a new multi-lane detection method with strong anti-interference ability is proposed. The main contribution of this work is the utilization of object detection neural network which is applied to remove vehicles from road images as much as possible. Compared with the traditional feature-based detection algorithms, this method can preserve lane line features more accurately and effectively. Firstly, binarization of global optimal threshold method is utilized to extract the basic features of lanes. In order to further remove non-lane line noises and extract lane features as clear as possible, YOLOv4-tiny object detection network is introduced to detect and filter vehicles on the road. Then the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm with denoising function is applied to cluster the different lane features. Finally, an improved RANSAC (Random Sample Consensus) method is used to perform quadratic curve fitting on the clustered features. The experimental results on dataset show that consumed time of a single frame image is only 0.119 second and the precision of the proposed method can reach 94.4%. Compared with other detection algorithms, the proposed algorithm has good real-time performance, stability and robustness in a variety of complex scenarios.

An Experimental Study of Image Thresholding Based on Refined Histogram using Distinction Neighborhood Metrics

In this study, we aimed to illustrate that the thresholding method gives different results when tested on the original and the refined histograms. We use the global thresholding method, the well-known image segmentation method for separating objects and background from the image, and the refined histogram is created by the neighborhood distinction metric. If the original histogram of an image has some large bins which occupy the most density of whole intensity distribution, it is a problem for global methods such as segmentation and contrast enhancement. We refined the histogram to overcome the big bin problem in which sub-bins are created from big bins based on distinction metric. We suggest the refined histogram for preprocessing of thresholding in order to reduce the big bin problem. In the test, we use Otsu and median-based thresholding techniques and experimental results prove that their results on the refined histograms are more effective compared with the original ones.

Optimization of automatic extraction procedure for particles in asphalt mixture towards superior robustness and accuracy

Three-dimensional image reconstruction plays a pivotal role in microstructure information extraction and virtual mechanical experiments of asphalt mixture. However, the traditional pixel-based reconstruction algorithm tends to be powerless in processing three-dimensional (3-D) mesostructure. Therefore, this paper aims to develop a robust and accurate algorithm for high-quality aggregate particle extraction. To this end, the global thresholding and three-dimensional mathematical morphological methods were conducted directly based on voxel operation. Then the calculated weight-based gradation was utilized to develop the robustness and accuracy analysis map (RAAM), which assesses and compares the traditional and novel reconstruction algorithms. As a sequence, the voxel-based method had higher accuracy and lower perturbation sensitivity than the existing procedures. Additionally, the computed efficiency was improved dramatically by breaking tight bounds and conservatism. Finally, the inevitable algorithm defects caused by multiple morphological treatments in the traditional method have disappeared in the novel one.

On Acquisition Parameters and Processing Techniques for Interparticle Contact Detection in Granular Packings Using Synchrotron Computed Tomography.

X-ray computed tomography (XCT) is regularly employed in geomechanics to non-destructively measure the solid and pore fractions of soil and rock from reconstructed 3D images. With the increasing availability of high-resolution XCT imaging systems, researchers now seek to measure microfabric parameters such as the number and area of interparticle contacts, which can then be used to inform soil behaviour modelling techniques. However, recent research has evidenced that conventional image processing methods consistently overestimate the number and area of interparticle contacts, mainly due to acquisition-driven image artefacts. The present study seeks to address this issue by systematically assessing the role of XCT acquisition parameters in the accurate detection of interparticle contacts. To this end, synchrotron XCT has been applied to a hexagonal close-packed arrangement of glass pellets with and without a prescribed separation between lattice layers. Different values for the number of projections, exposure time, and rotation range have been evaluated. Conventional global grey value thresholding and novel U-Net segmentation methods have been assessed, followed by local refinements at the presumptive contacts, as per recently proposed contact detection routines. The effect of the different acquisition set-ups and segmentation techniques on contact detection performance is presented and discussed, and optimised workflows are proposed.

Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.

We present a trainable segmentation method implemented within the python package ParticleSpy. The method takes user labelled pixels, which are used to train a classifier and segment images of inorganic nanoparticles from transmission electron microscope images. This implementation is based on the trainable Waikato Environment for Knowledge Analysis (WEKA) segmentation, but is written in python, allowing a large degree of flexibility and meaning it can be easily expanded using other python packages. We find that trainable segmentation offers better accuracy than global or local thresholding methods and requires as few as 100 user-labelled pixels to produce an accurate segmentation. Trainable segmentation presents a balance of accuracy and training time between global/local thresholding and neural networks, when used on transmission electron microscope images of nanoparticles. We also quantitatively investigate the effectiveness of the components of trainable segmentation, its filter kernels and classifiers, in order to demonstrate the use cases for the different filter kernels in ParticleSpy and the most accurate classifiers for different data types. A set of filter kernels is identified that are effective in distinguishing particles from background but that retain dissimilar features. In terms of classifiers, we find that different classifiers perform optimally for different image contrast; specifically, a random forest classifier performs best for high-contrast ADF images, but that QDA and Gaussian Naïve Bayes classifiers perform better for low-contrast TEM images.

Determination of Appropriate Thresholding Method in Segmentation Stage in Detecting Breast Cancer Cells

As in all cancer types, the early detection of breast cancer is vital in terms of patients holding on to life. Today, computer-aided image processing systems play an important role in the detection of diseases. Analyzing the images with accurate image processing methods is very important for professionals to interpret the images and to develop the treatment methods for diseases appropriately. The images contain-ing cancer cells (tumoroid) used in this study were obtained from the mini-Opto tomography device that creates 3D images by reconstruction of 2D images taken from different angles. It is an electronic, mechan-ical, and software-based device capable of 3D imaging of tumoroids up to 1 cm in diameter in size. Ob-serving an entire tumor spheroid that has the size of several centimeters in size in a single square image with a microscope is not possible, but with mini-Opto tomography it is possible. In our study, a few layers of 3D images of the tumoroid produced by MCF-7 breast cancer cells obtained on the different days from the mini-Opto device were used. Image thresholding offers many advantages at the segmenta-tion stage in order to distinguish the target objects. In this study, the determination of the most appropriate thresholding method for detecting the main tumor masses in the layered images was investigated. Moreo-ver, the contours of the tumoroid were determined in the original images based on applying the outcomes of thresholding. While various thresholding methods have been applied on diverse images in the literature, we have applied a few thresholding methods to small tumors up to 2 mm in size. As a result of the quali-tative assessment based on the results of the contour drawings on the thresholded images, the global thresholding and adaptive thresholding methods gave the best results.

FWENet: a deep convolutional neural network for flood water body extraction based on SAR images

ABSTRACT As one of the most severe natural disasters in the world, floods caused substantial economic losses and casualties every year. Timely and accurate acquisition of flood inundation extent could provide technical support for relevant departments in the field of flood emergency response and disaster relief. Given the accuracy of existing research works extracting flood inundation extent based on Synthetic Aperture Radar (SAR) images and deep learning methods is relatively low, this study utilized Sentinel-1 SAR images as the data source and proposed a novel model named flood water body extraction convolutional neural network (FWENet) for flood information extraction. Then three classical semantic segmentation models (UNet, Deeplab v3 and UNet++) and two traditional water body extraction methods (Otsu global thresholding method and Object-Oriented method) were compared with the FWENet model. Furthermore, this paper analyzed the water body area change situations of Poyang Lake. The main results of this paper were as follows: Compared with other five water body extraction methods, the FWENet model achieved the highest water body extraction accuracy, its F1 score and mean intersection over union (mIoU) were 0.9871 and 0.9808, respectively. This study could guarantee the subsequent research on flood extraction based on SAR images.

Non-Destructive Evaluation of Mixing and Defects of Friction Stir Welded Dissimilar Aa6061-T6 and Az31b by X-Ray Computed Tomography

As a non-destructive evaluation method for friction stir welded joints, this research aims to develop and corroborate a method for material flow analysis and defect detection based on X-ray computed tomography (X-ray CT). Using a cylindrical FSW tool with a broad shoulder, joints of dissimilar materials AA6061-T6/AZ31b are friction welded employing tool rotary speed ranging from 1000 to 1500 RPM and tool feed from 125 to 400 mm/min. The welded joints are scanned via X-Ray CT with an image bit depth of 16-bit then segmented based on the Hounsfield Units scale (HU) and the global Otsu thresholding method. This segmentation divides the DICOM images into masks for each different material, from which 3D renderings are generated to record volumetric data. For analyzing elemental mixing, measurements of material penetration and transfer are carried out. Corroborating these results was accomplished using destructive cross-sectioning and Energy Dispersive X-ray Spectroscopy (EDX). The results show that this method can detect internal defects and characterize the material mixing with results comparable to that of destructive EDX analysis. The effect of improving scan resolution on reconstructed images was shown to slightly improve the accuracy of the thresholding method while reducing the standard deviation of segmented material ranges.

Effect of different voxel sizes on the accuracy of CBCT measurements of trabecular bone microstructure: A comparative micro-CT study.

PurposeThe aim of this study was to assess the accuracy of cone-beam computed tomographic (CBCT) images obtained using different voxel sizes in measuring trabecular bone microstructure in comparison to micro-CT.Materials and MethodsTwelve human skull bones containing posterior-mandibular alveolar bone regions were analyzed. CBCT images were obtained at voxel sizes of 0.075 mm (high: HI) and 0.2 mm (standard: Std), while micro-CT imaging used voxel sizes of 0.06 mm (HI) and 0.12 mm (Std). Analyses were performed using CTAn software with the standardized automatic global threshold method. Intraclass correlation coefficients were used to evaluate the consistency and agreement of paired measurements for bone volume (BV), percent bone volume (BV/TV), bone surface (BS), trabecular thickness (TbTh), trabecular separation (TbSp), trabecular number (TbN), trabecular pattern factor (TbPf), and structure model index (SMI).ResultsWhen compared to micro-CT, CBCT images had higher BV, BV/TV, and TbTh values, while micro-CT images had lower BS, TbSp, TbN, TbPf, and SMI values (P<0.05). The BV, BV/BT, TbTh, and TbSp variables were higher with Std voxels, whereas the BS, TbPf, and SMI variables were higher with HI voxels for both imaging methods. For each imaging modality and voxel size evaluated, BV, BS, and TbTh were significantly different (P<0.05). TbN, TbPf, and SMI showed statistically significant differences between imaging methods (P<0.05). The consistency and absolute agreement between micro-CT and CBCT were excellent for all variables.ConclusionThis study demonstrated the potential of high-resolution CBCT imaging for quantitative bone morphometry assessment.

Human Eye Pupil Detection System for Different IRIS Database Images

The pupil detection system plays a vital role in ophthalmology diagnosis equipments because pupil has a center place of human eye to locate the exact position. To identify the exact human eye pupil region in near infrared (NIR) images, this work proposes the Center of gravity method and its real time FPGA hardware implementation. The proposed work involves global threshold method to segment the pupil region from human eye and the bright spot suppression process removes the light reflections on the pupil due to the IR (Infra red) rays then the morphology dilation process removes unnecessary black pixels other than pupil region on the image. Finally, center of gravity (COG) method provides the exact pupil center coordinate and radius of the human eye. CASIA IRIS V4 and UBIRIS iris database images used in this work and achieved 90-95% of recognition rate.

Super-efficient enhancement algorithm for infrared night vision imaging system

This paper presents new three proposed approaches for enhancement of Infrared (IR) night vision images. The first approach is based on merging gamma correction with the Histogram Matching (HM). The second approach depends on hybrid gamma correction with Contrast Limited Adaptive Histogram Equalization (CLAHE). The third approach is based on a trilateral enhancement that the IR images pass through three stages: segmentation, enhancement and sharpening. In the first stage, the IR image is divided into segments based on Optimum Global Thresholding (OTSU) method. The second stage, which is the heart of the enhancement approach, depends on Additive Wavelet Transform (AWT) to decompose the image into an approximation and details. Homomorphic enhancement is performed on the detail components, while Plateau Histogram Equalization (PHE) is performed on the approximation plane. Then, the image is reconstructed and subjected to a post-processing high pass filter. Average gradient, Sobel edge magnitude, entropy and spectral entropy has been used as quality metrics for assessment the three proposed approaches. It is clear that the third proposed approach gives superior results to the two proposed approaches point view the quality metrics. On the other hand, clear that the third proposed approach takes long computation time in the implementation with respect to the two proposed approaches. The first proposed approach gives better results to the two proposed approaches from the computation time perspective.

Investigation on dual-domain data processing algorithm used in thermal non-destructive evaluation

ABSTRACT The paper presents the results of research on the data processing algorithm used to detect material defects using active thermography. The algorithm allows the analysis of thermogram sequences in both time and image domain. In the first stage of the algorithm operation, mathematical morphology or filtered contrast methods are used to remove the uneven heating from the sample, as well as to segment and detect defects using local and global thresholding methods. In the next stage, it is possible to determine the number of defects as well as automatically estimate their depth and characteristics (insulator/conductor) in relation to the background material (material without defect). The presented algorithm was tested on two material samples, i.e. PMMA and Expanded PVC, for two phases of the thermal process, i.e. heating and cooling. The study found that the best defect detection and characterisation results are obtained when processing thermographic data from the cooling phase in combination with a Top Hat morphological transformation, local thresholding (for defect detection), and relative incremental filtered contrast (for defect size estimation).

Segmentation and Pore Structure Estimation in SEM Images of Tissue Engineering Scaffolds Using Genetic Algorithm.

A python computer package is developed to segment and analyze scanning electron microscope (SEM) images of scaffolds for bone tissue engineering. The method requires only a portion of an SEM image to be labeled and used for training. The algorithm is then able to detect the pore characteristics for other SEM images acquired at different ambient conditions from different scaffolds with the same material as the labeled image. The quality of SEM images is first enhanced using histogram equalization. Then, a global thresholding method is used to perform the image analysis. The thresholding values for the SEM images are obtained using genetic algorithm (GA). The image analysis results include pore distributions of pore size, pore elongation and pore orientation. The results agree satisfactorily with the experimental data for the chitosan-alginate porous scaffolds considered. Applications of the method developed for image segmentation is not limited to scaffold pore structure analysis. The method can also be used for any SEM image containing multiple objects such as different types of cells and subcellular components.

Implementation face based cancelable multi-biometric system

This paper suggests novel two proposed cancellable biometric realization techniques recognition and template protection. In this paper, the Homomorphic Key (HK) encoding algorithm is utilized for cancelable face system. In the first suggested scheme, the HK algorithm is applied on the face images. The resultant map is encrypted, in order to the second HK utilized in the HK is produced from the image. This approach can be used to develop a frequency domain procedure for making this system for biometric template protection. The second algorithm presents a new approach to detect the features of face images depending the Speeded Up Robust Features (SURF) and Optimum Global Thresholding (OTSU) method. This algorithm is relied on scale space analysis with the number of SURF feature points as the key parameters for classification. Simulation results using evaluation metrics False Positive Rate (FPR), False Negative Rate (FNR), Equal Error Rate (EER), Receiver Operating Characteristic (ROC) and Area under ROC (AROC) prove that the first proposed cancelable biometric technique with the second key are best with comparing the other keys. The obtained results clear that the second suggested technique has sucesseded in detection the features of the skin, eyes, nose, hair, ears images and the face positions.

Study on precise detecting and controlling technology of lag angle based on image processing

A precise method of detecting and controlling of lag angle during the optical fiber winding procedure is described in this paper. The system is composed of three modules, image collection, image processing and PC controller. Images of lag angle are collected by an industrial high-speed camera. Binary treatment on lag angle images of the motive optical fiber is done by global threshold method. Image identification of lag angle of the motive optical fiber is realized by Hough transform, thus the digital values of lag angel are obtained. PC outputs controlled variables to modify the winding motion based on detecting results so as to limit the lag angel in a precise range. The research result indicates that application of image collection and identification technology to optical fiber winding can avoid winding flaw effectively such as gap and lamination thus to improve the quality and efficiency of optical fiber winding.

Study on precise detecting and controlling technology of lag angle based on image processing

A precise method of detecting and controlling of lag angle during the optical fiber winding procedure is described in this paper. The system is composed of three modules, image collection, image processing and PC controller. Images of lag angle are collected by an industrial high-speed camera. Binary treatment on lag angle images of the motive optical fiber is done by global threshold method. Image identification of lag angle of the motive optical fiber is realized by Hough transform, thus the digital values of lag angel are obtained. PC outputs controlled variables to modify the winding motion based on detecting results so as to limit the lag angel in a precise range. The research result indicates that application of image collection and identification technology to optical fiber winding can avoid winding flaw effectively such as gap and lamination thus to improve the quality and efficiency of optical fiber winding.

Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask

Image fusion integrates complex information about a target scene from multiple sensors into a single image. The fused image can further be utilized for human perception or different machine vision tasks. In the case of infrared and visible images, infrared images have the advantage of capturing thermal radiation intensity, whereas visible images are superior in gradient texture. In order to effectively fuse thermal intensity of infrared image and texture advantage of visible image, we propose a novel fusion method based on L0 decomposition and intensity mask. The proposed method first acquires base and detail layers of images (visible & infrared) using L0 decomposition. Next, an intensity mask is obtained using the basic global thresholding method on base layers of infrared image. The layers (base layers and detail layers) and visible images are divided images into three parts by the use of intensity mask, namely, mask-base layers, mask-detail layers, and texture-background. The first and second parts effectively achieve intensity blending, whereas the third part achieves the fused image with a clear gradient texture. The proposed method shows superior performance when compared with five state-of-the-art methods (on publicly available databases).

A local thresholding approach to flood water delineation using Sentinel-1 SAR imagery

Emergency response to floods requires timely information on water extents, which can be produced by satellite-based remote sensing. As the synthetic aperture radar (SAR) can emit and receive signal in nighttime or cloudy conditions, it is particularly suitable to delineate water extent during flood events. Thresholding SAR imagery is one of the most widely used approaches to delineate water extent for its effectiveness and efficiency. However, most thresholding methods rely on a single threshold to separate water and land without considering the complexity and variability of different land surface types in an image. To account for the heterogeneous surface characteristics, this paper proposes a new local thresholding method to water delineation with SAR images. Specifically, our method follows four major steps. First, a global threshold is applied to the SAR imagery to delineate initial water pixels, from which non-water pixels are further clustered into several land surface types. This divides the SAR imagery into one water cluster and several land clusters. Second, local thresholds are estimated at each subset of land cluster paired with water cluster by fitting Gamma distributions to the backscatter intensities of the combined water/land pixels in each subset. Third, local water extents are delineated from each subset and then merged as the union of all subsets. The results are combined across multiple polarizations by taking an intersection operation to generate the global inundation extent. Finally, the flood water extent is further improved by imposing basic hydrologic constraints. This approach is fast and fully automated for flood detection. Our experiments using Sentinel-1 SAR imagery show that the proposed local thresholding approach could distinguish water from non-water with significantly higher accuracy (4–13% improvement in the harmonic mean of user’s and producer’s accuracy of water) than conventional global-thresholding methods.

Brain tumor classification based on DWT fusion of MRI sequences using convolutional neural network

Tumor in brain is an anthology of anomalous cells. It leads to increase in death rate among humans. Therefore, in this manuscript, a fusion process is proposed to combine structural and texture information of four MRI sequences (T1C, T1, Flair and T2) for the detection of brain tumor. A discrete wavelet transform (DWT) along with Daubechies wavelet kernel is utilized for fusion process which provides a more informative tumor region as compared to an individual single sequence of MRI. After the fusion process, a partial differential diffusion filter (PDDF) is applied to remove noise. A global thresholding method is used for segmenting tumor region which is then fed to proposed convolutional neural network (CNN) model for finally differentiating tumor and non-tumor regions. Five publicly available datasets i.e., BRATS 2012, BRATS 2013, BRATS 2015, BRATS 2013 Leader board and BRATS 2018 are used for proposed method evaluation. The results show that fused images provide better results as compared to individual sequences on benchmark datasets.

Segmentation of Irrelevant Regions Using Color Thresholding Method: Application in Breast Histopathology Images

Segmentation of irrelevant regions in the breast histopathology image is essentially performed in preliminary or post processing stages. This study presents a color thresholding method to segment the irrelevant regions, specifically blood cells and hemorrhage in the RGB breast histopathology images. The conventional gray level global thresholding method was extended to color images by modifying the thresholding algorithm. The color thresholding method was performed by decomposing the RGB input image into coherent regions based on similarity in color feature. Area Overlap Measure (AOM) and Combined Equal Importance (CEI) are two statistical metrics used to evaluate the performance of the color thresholding method. The obtained AOM and CEI for the overall dataset in blood cells are 0.92 and 0.89, respectively. The color thresholding method is found to be effective and is able to produce plausible thresholding results in segmentation of irrelevant regions in RGB breast histopathology images.