Otsu Thresholding Method Research Articles

Automatic Segmentation and Classification for Antinuclear Antibody Images Based on Deep Learning.

Antinuclear antibodies (ANAs) testing is the main serological diagnosis screening test for autoimmune diseases. ANAs testing is conducted principally by the indirect immunofluorescence (IIF) on human epithelial cell-substrate (HEp-2) protocol. However, due to its high variability and human subjectivity, there is an insistent need to develop an efficient method for automatic image segmentation and classification. This article develops an automatic segmentation and classification framework based on artificial intelligence (AI) on the ANA images. The Otsu thresholding method and watershed segmentation algorithm are adopted to segment IIF images of cells. Moreover, multiple texture features such as scale-invariant feature transform (SIFT), local binary pattern (LBP), cooccurrence among adjacent LBPs (CoALBP), and rotation invariant cooccurrence among adjacent LBPs (RIC-LBP) are utilized. Firstly, this article adopts traditional machine learning methods such as support vector machine (SVM), k-nearest neighbor algorithm (KNN), and random forest (RF) and then uses ensemble classifier (ECLF) combined with soft voting rules to merge these machine learning methods for classification. The deep learning method InceptionResNetV2 is also utilized to train on the classification of cell images. Eventually, the best accuracy of 0.9269 on the Changsha dataset and 0.9635 on the ICPR 2016 dataset for the traditional methods is obtained by a combination of SIFT and RIC-LBP with the ECLF classifier, and the best accuracy obtained by the InceptionResNetV2 is 0.9465 and 0.9836 separately, which outperforms other schemes.

APPLICATION OF GOOGLE EARTH ENGINE IN FLOOD MONITORING AND ASSESSMENT OF FLOOD-AFFECTED AGRICULTURAL LAND IN THE BUI RIVER BASIN, HANOI CITY

Tropical storms accompanied by heavy rain often appear and cause severe floods from May to November every year in the Bui river basin, seriously affecting the local agricultural production. Therefore, a quick assessment of the agricultural land area affected by inundation is very important for the people and local government officials. In this study, we propose a new method to quickly estimate the agricultural land area affected by floods using Sentinel 1A (S1A). Firstly, the flood map estimated from the S1A image on Google Earth Engine at the flood peak by the Otsu threshold method does not exclude permanent water area with an overall accuracy of 82,5%. The flood extent are estimated at 1324 hectares, approximately 4% higher than the official data of local authorities. Secondly, the study overlayed the official land map and the flood map to determine the location and area of the affected area by the flood. Calculation results show that storm Son Tinh has affected approximately 33% (1261 ha) of agricultural land ( not accounting forestry) in 5 communes. The difference is about 1.2 % (15 ha) compared with statistical results from state management agencies. The results show the valuable potential of using free Synthetic Aperture Radar (SAR) from S1A images to quickly monitor and assess flood-affected agricultural land over a small and large area using the Google Earth Engine.

A Density and Distance-Based Method for ICESat-2 Photon-Counting Data Denoising

The Ice, Cloud and Land Elevation Satellite-2 (ICESat-2) dynamically monitors water depth in shallow waters around islands and reefs. Noise removal is a prerequisite for accurate reconstruction of seafloor topography based on ICESat-2 data products. To this end, we propose a Density and Distance-Based Method (DDBM) to extract seafloor signal photons from ICESat-2 data. DDBM first separates the photons into three parts: above-water, water surface and water-column. The water-column photons consist of seafloor signal photons and noise photons. DDBM adopts a two-step denoising strategy to remove noise in water-column photons to obtain pure and complete signal photons. In the first step, an orientation-variable adaptive ellipse filter is developed, which can adaptively adjust the parameters according to the water depth to remove low-density noise photons. In the second step, a novel Distance-Based Filter (DBF) is designed for stubborn high-density noise clusters. These noise clusters are far from the signal photons, and the DBF removes them by a distance threshold derived from the Otsu threshold method. We select three high-density ICESat-2 datasets to validate DDBM. Compared with the reference data, the comprehensive evaluation indexes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</i> of DDBM in all datasets are above 0.99 and the highest is 0.998, showing superior performance.

Coastline changes monitoring induced by man-made structures using synthetic aperture radar: A new simple approach

This study presents a new simple approach to detect the coastline changes due to the construction of man-made structures. The new approach uses low-pass filter to reduce the speckles errors and Otsu thresholding method the create binary image. Then, a closing morphological operation was conducted to improve the binary image. In the final step, the canny edge detection is used for coastline delineation. The coastlines changes analysis was done by using Digital Shoreline Analysis System (DSAS). In general, the processing steps of this new approach is semi-automatic processes, it does not require manual digitization to extract the coastline. This method was tested using two independent synthetic aperture radar (SAR) satellite images, i.e., ALOS-1 and Sentinel-1 SAR data. The results show that this new approach produced better results than other well-known methods. This new approach detects clearly the man-made structure and its impact to the coastal zone, i.e., abrasion and accretion. The study area is located in Pengambengan Port, Jembrana Regency, Bali, Indonesia. In addition, the result of this study can be used as evaluation parameters for future development of Pengambengan port or re-design of present structures.

Applying an adaptive Otsu-based initialization algorithm to optimize active contour models for skin lesion segmentation.

Medical image processing has gained much attention in developing computer-aided diagnosis (CAD) of diseases. CAD systems require deep understanding of X-rays, MRIs, CT scans and other medical images. The segmentation of the region of interest (ROI) from those images is one of the most crucial tasks. Although active contour model (ACM) is a popular method to segment ROIs in medical images, the final segmentation results highly depend on the initial placement of the contour. In order to overcome this challenge, the objective of this study is to investigate feasibility of developing a fully automated initialization process that can be optimally used in ACM to more effectively segment ROIs. In this study, a fully automated initialization algorithm namely, an adaptive Otsu-based initialization (AOI) method is proposed. Using this proposed method, an initial contour is produced and further refined by the ACM to produce accurate segmentation. For evaluation of the proposed algorithm, the ISIC-2017 Skin Lesion dataset is used due to its challenging complexities. Four different supervised performance evaluation metrics are employed to measure the accuracy and robustness of the proposed algorithm. Using this AOI algorithm, the ACM significantly (p≤0.05) outperforms Otsu thresholding method with 0.88 Dice Score Coefficients (DSC) and 0.79 Jaccard Index (JI) and computational complexity of 0(mn). After comparing proposed method with other state-of-the-art methods, our study demonstrates that the proposed methods is superior to other skin lesion segmentation methods, and it requires no training time, which also makes the new method more efficient than other deep learning and machine learning methods.

Pulse coupled neural network optimized with chaotic grey wolf algorithm for breast cancer classification using mammogram images

SummaryBreast cancer is a very hazardous disease that mainly affects women and leads to a high mortality rate. Early detection of this disease only can reduce the mortality rate. Previously, several methods were used to detect this cancer, but none of them provides sufficient accuracy. To deal this issue, a pulse coupled neural network optimized with chaotic grey wolf algorithm is proposed in this article for the classification of breast cancer using mammogram images. The breast cancer images are gathered from MAMMOSET dataset. The images are preprocessed and segmented with the help of Tsalli's entropy based multilevel 3D Otsu (TE‐3D‐Otsu) thresholding method. Then the parameters of the TE‐3D‐Otsu are optimized using the improved shuffled shepherd optimization algorithm. The features are extracted using moment invariant wavelet feature extraction technique. The images are classified using pulse coupled neural network (PCNN). Then, PCNN mass parameters are optimizes utilizing chaotic grey wolf optimization algorithm (chaotic‐GWOA) for categorizing the mammogram breast cancer imageries, such as malignant, benign, and normal. The proposed method is activated on MATLAB, its performance is analyzed with existing methods. The simulation results show that the proposed BC‐PCNN‐CGWOA attains the accuracy 57.86%, 85.94%, and 53.45% is greater than the existing methods.

A Machine Vision-Based Method for Detecting Surface Hollow Defect of Hot-State Shaft in Cross Wedge Rolling

In order to solve the problems of low detection efficiency and safety of artificial surface defects in hot-state cross wedge rolling shaft production line, a machine vision-based method for detecting surface hollow defect of hot-state shafts is proposed. Firstly, by analyzing the high reflective properties of the metal shaft surface, the best lighting method was obtained. And by analyzing the image contrast between image foreground and image background, the most suitable optical filter type in image acquisition was determined. Then, Fourier Gaussian low-pass filtering method is used to remove the interference noise of rolled shafts surface in frequency domain, such as high-light, oxide skin and surface texture. Finally, by analyzing the characteristics of the surface hollow defect area, a defect identification method combining the Otsu threshold method and the adaptive threshold method is proposed to realize the effective extraction of surface hollow defect of rolled shafts. The test results show that the average recognition rate of the method based on machine vision is 95.7%. The results of this paper provide technical support to meet the production requirements of high quality and high performance of cross wedge rolling.

Estimation of SPIO Nanoparticles Uptakes by Macrophages Using Transmission Electron Microscopy.

Due to their interesting size-dependent magnetic characteristics and relative biocompatibility, magnetic superparamagnetic iron oxide (SPIO) nanoparticles have been widely exploited as probes for cell and subcellular structure identification, as well as medication and gene delivery. A thorough understanding of the mechanics of the interaction between nanoparticles and macrophages is vital in managing dynamic processes in nanomedicine. In this study, the interaction behavior and uptake of SPIO nanoparticles by M1- and M2-type macrophages were investigated. Mice monocytes were differentiated into M1 and M2 macrophages, and the uptake of SPIO nanoparticles was studied using a TEM microscope. A high resolution image of 1 nm resolution, an image processing technique, was developed to extract the SPIO-NPs from tomographic TEM microscopic images. Lysosomes appear to be the zones of high concentrations of SPIO inside macrophages. Lysosomes were first selected in each image, and then segmentation by the Otsu thresholding method was used to extract the SPIO-NPs. The Otsu threshold method is a global thresholding technique used to automatically differentiate SPIOs from the background. The SPIO-NPs appear in red colors, and the other pixels in the image are considered background. Then, an estimation of the SPIO-NP uptakes by lysosomes is produced. Higher uptake of all-sized nanoparticles was observed in M1- and M2-type macrophages. An accurate estimation of the number of SPIO-NPs was obtained. This result will help in controlling targeted drug delivery and assessing the safety impact of the use of SPIO-NPs in nanomedicine for humans.

Research on Road Extraction Algorithm Based on Improved Otsu’s Thresholding Method

In this paper, the widely used method of Otsu's thresholding method is studied. On the basis of the traditional Otsu's thresholding method, according to the distribution characteristics of the target and background in the actual image, a new method based on traditional Otsu's thresholding method is presented.and the road extraction experiment is carried out with GF-2 remote sensing image.The experimental results show that the improved method has the advantages of high segmentation accuracy and strong anti noise ability compared with the traditional Otsu's thresholding method.

Analysis of Multilevel Otsu Thresholding for Corrosion Rate of Anodised AZ91D Magnesium Alloy ​

Magnesium and its alloy are renowned for their high strength-to-weight ratio, excellent machinability and good castability, making it a favourable material for manufacturing various automotive parts. But when exposed to the environment, magnesium and its alloy have a weak ability to resist corrosion. AZ91D magnesium alloy was anodised and immersed in a salt solution to accelerate deterioration. The image of the corroded surface resulting from the immersion test was analysed by quantising the corroded regions. This paper studies the feasibility of an image processing approach using the multilevel Otsu thresholding method by quantising the corroded region on the AZ91D magnesium alloy. This method converts the original colour image to a greyscale image and then converts it to a binary image and RGB image for the multilevel thresholding. The pixel distributions from the multilevel Otsu thresholding display a trend that, with a higher corrosion rate, the pixel’s frequency of occurrence shifted more to the darker regions. This conforms with the Otsu thresholding, where the darker region is identified as the corroded area of the AZ91D magnesium alloy. By implementing the negative image, the binary image is segmented into non-corroded and corroded areas and labelled as 0 (black) and 1 (white,) respectively. As for multilevel Otsu thresholding, the RGB image is assigned in three colours representing different corrosion severity regions. The regions of the corrosion severity are categorised into severe corrosion, moderate corrosion and low corrosion, coloured in dark blue, light blue, and yellow, respectively. Thus, the trend of the corrosion activity can be seen by implementing the multilevel Otsu thresholding and correlating it with the corrosion rate value. Furthermore, obtaining data on corrosion attack severity can provide helpful information in predicting a component’s failure and future maintenance planning.

Sand Soil Image Processing Using the Watershed Transform and Otsu Thresholding Based on Gaussian Noise

Image processing technology is one of the technologies that can help facilitate and speed up human work, especially in the process of determining the grain size distribution of soil in a civil building plan. Its utilization has been widely used to study, analyze, and understand the structure and framework of the soil. Image analysis is carried out as an initial or fundamental step in image processing to discover and comprehend information. With so many image segmentation methods, it is necessary to conduct research to determine which method is best for sandy soil image segmentation based on one of the image segmentation quality criteria, namely gaussian image noise. By testing the watershed transform method and the Otsu thresholding method as two of the area-based methods that are considered suitable for segmenting sandy soil images before and after distorted Gaussian noise based on the calculation of the mean square error (MSE) value.The results showed that the watershed transform method is better for segmenting sandy soil images when compared to the Otsu thresholding method. This is indicated by the average squared error (mse) of 3.08 for the watershed transform method and 4.09 for the Otsu Thresholding method. In addition to the comparison of quality tests of sandy soil based on gaussian noise with standard deviation values of normal distribution and noise intensities of 10, 20, and 30, it proves that the watershed transform method is still better at segmenting noise-distorted sandy soil images than the Otsu thresholding method. However, in terms of processing time, the Otsu Thresholding method is faster or better than the Watershed Transform method. of the results or conclusions brief. There are no citations, tables or figures in abstract.

Comparison of K-Means Clustering and Otsu Thresholding Methods in the Detection of Tuberculosis Extra Pulmonary Bacilli in the HSV Color Space

Tuberculosis Extra Pulmonary (TBEP) is an infectious disease caused by the bacterium Mycobacterium tuberculosis and can cause death. Patients suffering from this disease must be treated quickly without waiting long. Currently, anyone who will be detected caused by this bacterium takes a long time and costs a lot. The biopsy is one of the techniques used to take the patient's lung fluid and give Ziehl Neelsen chemical dye and then observe using a microscope to determine this TBEP disease. This research aims to help detect bacteria quickly and precisely by performing computer-aided image processing by creating an application system. The technique used is to develop the segmentation method. The segmentation process is to develop a Hue Saturation Value (HSV) color space transformation technique with the K-Means and Otsu Thresholding techniques. From the results of the two methods used, it turns out that the Otsu Thresholding method can detect TBEP results with more accuracy than the K-Means method. So the method developed is beneficial in accelerating and minimizing costs for detecting TBEP.

Research on water seepage detection technology of tunnel asphalt pavement based on deep learning and digital image processing

To improve the safety of road tunnel pavement, the research established road tunnel pavement water seepage recognition models based on deep learning technology, and a water seepage area extraction model based on image processing technology to finally achieve accurate detection of water seepage on tunnel pavements. First, the deep learning models EfficientNet water seepage recognition model and MobileNet water seepage recognition model were built, the models were trained with the self-collected pavement seepage data set, and the F1 score was introduced to evaluate the accuracy and comprehensive performance of the two models in predicting different categories of water seepage characteristics. Then three grayscale processing methods, the cvtColor function, mean method and maximum method, six global threshold segmentation methods, Otsu thresholding method, THRESH_BINARY, THRESH_BINARY_INV, THRESH_TRUNC, THRESH_TOZERO and THRESH_TOZERO_INV, three filtering methods, namely Gaussian filtering, median filtering and morphological open operation, as well as small connected domain removal, were used to reduce the noise of the images. Finally, the seepage area image calculation method was proposed based on the processed images to predict the actual pavement seepage area. The results show that the recognition accuracy of the EfficientNet water seepage recognition model is 99.85% and 97.53% in the training and validation sets respectively, which is 2.85% and 0.76% higher than the 97% and 96.77% of the MobileNet model. The average F1 score of the EfficientNet model is 95.22%, which is 5.05% higher than that of the MobileNet model, for the four types of seepage feature images: point seepage, line seepage, surface seepage and no seepage. The cvtColor function for grayscale processing, THRESH_BINARY for threshold segmentation and a combination of median filtering and morphological open operation for image noise reduction can effectively extract the seepage features. The area calculation is performed by the seepage area image calculation method, and the average error between the predicted value and the actual seepage area is 8.30%, which can better achieve the accurate extraction of the seepage area.

The analysis of differences at Binary Image in COVID-19 and ARDS Patients from chest X-Ray examination

Corona virus disease 2019 (COVID-19), a viral infection that was discovered at the end of December 2019 in Wuhan, China. The spread and transmission of this virus is very fast even to all countries in the world. Meanwhile, Acute Respiratory Distress Syndrome (ARDS) is an emergency condition in the field of pulmonology that occurs due to fluid accumulation in the alveoli causes gas exchange disorders so that oxygen distribution to tissues were reduced. In this study, Chest X-Ray (CXR) image processing done in COVID-19 and ARDS patients with the aim of analyzing the differences in binary image using the Otsu Thresholding method. This study prioritizes improving the quality of the original CXR image by segmentation using calculating the Peak Signal-to-Noise Ratio (PSNR) and Mean Square Error (MSE) values. The results showed that the difference between CXR images in COVID-19 patients and ARDS lies in the extent of spread, in COVID-19 patients the extent of spread varies depending on the length of time the virus has invaded and not all of it starts from the alveolus, while ARDS tends to be constant and starts from the lungs. The lower part of the lung, specifically the alveoli. ©2022 JNSMR UIN Walisongo. All rights reserved.

Klasifikasi Citra Glaukoma dengan ANN Berdasarkan Pembuluh Darah Pada Citra Fundus Retina Mengguna

Glaucoma is an eye disease that can lead to permanent blindness caused by increased Intraocular Pressure (IOP). There are several methods to detect glaucoma, namely Optical Nerve Hypoplasia Stereo Photographs (ONHSPs), Optical Coherence Tomography (OCT), Scanning Laser Polarimetry (SLP), and Confocal Scanning Laser Ophthalmoscopy (CSLO). However, these methods require a lot of money and expert supervision. In this paper, glaucoma classification will be carried out using the ANN method with a comparison of the otsu-thresholding segmentation method and canny edge detection with the aim of knowing which method gives better results in diagnosing glaucoma images based on the parameters of accuracy, sensitivity, and specificity. The dataset used is RIM-ONE r2 and r3 which will be extracted using 5 features of GLCM and 6 statistical features, and obtained an accuracy of 76% for the otsu-thresholding method, and 79% for canny edge detection.

(Retracted) Hybrid whale optimization algorithm-Levy flight approach for multilevel thresholding image segmentation

Determining the optimal threshold for multilevel image segmentation is a stimulating task. Image segmentation has many applications, such as content-based image retrieval, medical imaging, object detection, object recognition, machine vision, etc. In multilevel thresholding, multiple thresholds are used to segment complex images, and the images are segmented into multiple levels to extract meaningful information for further image analysis. Where threshold number is small, p-tile, Otsu, moment preserving, and entropy thresholding methods attain good accuracy. These classical thresholding methods are time-consuming, computation expensive, and unable to produce good segmentation accuracy with increased threshold numbers. To overcome these problems, the classical thresholding methods are utilized as objective functions with nature-inspired metaheuristic algorithms such as whale optimization algorithm (WOA), simplified swarm optimization (SSO), sine cosine algorithm (SCA), BAT algorithm, WOA-thresholding, and black widow optimization (BWO) to determine optimal multiple thresholds. Nature-inspired metaheuristic algorithms are widely used to search for an optimal solution for global optimization problems. WOA is widely used to find the optimal solution in search space. WOA suffers from entrapment into local optima due to premature convergence behavior. We introduce hybridization of WOA with Levy flight trajectory and named as hybrid whale optimization algorithm-Levy flight (HWOAL), which is utilized to find optimal multiple thresholds for multilevel image segmentation. Levy flight trajectory is utilized to increase diversity in the swarm population. The efficacy of HWOAL is tested on 23 benchmark optimization functions (F1 to F23) and compared with WOA, SSO, SCA, and BAT algorithms. Experiment arms that HWOAL is efficient and makes WOA faster, enhances the ability of exploitation and exploration phase, and can avoid getting stuck into local optima. The segmentation performance of the proposed HWOAL method has been compared with other algorithms, such as WOA, SSO, SCA, BAT, and other two recent segmentation algorithms, such as WOA-TH and BWO on several benchmark images (BSD 300). The experimental result is carried in 30 trials and analyzed based on objective fitness value, optimal multilevel threshold values, segmentation quality measures, such as mean square error, peak signal-to-noise ratio, structural similarity index, average difference, and computation time to compute optimal multilevel threshold values. The experiment conducted by the authors shows that the proposed HWOAL method is efficient, produces better fitness value, and segmentation metrics for multilevel image segmentation than other algorithms.

Facial Skin Color Segmentation Using Otsu Thresholding Algorithm

The development of technology and information is currently very fast. One of the fields of technology and information that is experiencing development is the field of digital image processing. There are many technologies today that utilize digital images such as facial recognition, object detection and many others. Skin is one of the largest components of the human body. Currently, technology in the identification of skin color is widely used in recognizing the human race. In this study, skin color detection uses the YCbCr color space, which in this study only uses the range of Cb and Cr values, and ignores the Y value. Where Y is the lighting in the image. So if not changed, the image will contain light effects that can change the characteristics of skin color. However, problems were found because the detected images were not segmented properly, such as clothes and hair from the tested images were still detected as skin. Therefore, the HCbCr color space method is proposed where the Hue value will represent the color of visible light. While the Otsu Thresholding method will separate the background from the object in the digital image.

Detection and Diagnosis of Brain Tumor Using Wavelet Transform and Machine Learning Model

Brain tumor diagnosis using magnetic resonance images (MRI) is one of the hot topics of interest in medical field. In this paper, a novel approach for brain tumor diagnosis is proposed. Four major phases are involved in the proposed approach which are preprocessing, tumor segmentation, feature extraction and classification. Hybrid median filtering method is implemented to suppress noise. Otsu thresholding method is used for isolating tumor from its background tissues. Wavelet transform is adopted for feature extraction. Support vector machined is used for classifying the brain tumors. Classification potential of the proposed system is tested on Harvard and BRATS data set.

Curtain-type phase unwrapping algorithm

A curtain-type phase unwrapping algorithm is proposed. First, the 2 × 2 closed curve method is used to find out the residual point of the wrapped phase to form the residual template, and the Otsu threshold method is used to binary the modulation of the deformed pattern to form the shadow template. Second, the effective phases of up-down symmetrical points about the starting point are simultaneously unwrapped in turn until all the points in the column are completed. Third, the starting point is taken as the center of left-right symmetry, the effective phases of the nearest symmetric points are simultaneously unwrapped, and the corresponding columns are unwrapped in the same way as above. Fourth, in this way, the effective phases in the corresponding symmetric columns are successively unwrapped in the form of curtain opening until the whole phases are completely unwrapped. In the previous procedure, the shadow template and residual template guide the curtain-type phase unwrapping to avoid error diffusion. Finally, the 8-neighborhood mean algorithm and the cubic b-spline algorithm are employed to unwrap the phase values of residual points and shadow areas, respectively. The proposed method realizes the whole phase unwrapping without phase error diffusion. Experimental results show that the efficiency of the proposed method is 26% higher than that of the diamond algorithm, and its accuracy is significantly improved.

A Health Care Image Compression Scheme using Discrete Wavelet Transform and Convolution Neural Network

Medical image processing is an important field that directly impacts the health care system. It recognizes disease and also provides information for diagnosis and surgical process. The objectives of medical image compression are to reduce the computational complexity, storage size, and transmission bandwidth. This research has proposed an image compression scheme (MIC-DWT-CNN) based on discrete wavelet transform and convolutional neural networks. Region-growing and otsu-thresholding methods have separated the interested area and non-interested area of the medical image. The DWT has compressed the region of interest, and CNN has compressed the non-interested area in the medical image. The MIC-DWT-CNN scheme has experimented on the images of the medical image dataset using the python platform. The research objective is to achieve better compression efficiency and image quality. The performance of the MIC-DWT-CNN method has been evaluated using Mean square error (MSE), Peak Signal to Noise Ratio (PSNR), and Compression Ratio (CR). The existing techniques have been used to compare with the MIC-DWT-CNN method. The MIC-DWT-CNN method has achieved a better compression performance than the existing methods. The MIC-DWT-CNN method has achieved a higher CR, i.e., 25.01, than existing methods. Also, the model has provided the required level of MSE and PSNR values.