Area Thresholding Research Articles

Implementation of Channel Area Thresholding in Early Detection System of Acute Respiratory Infection (ARI)

Acute respiratory infections (ARI) are infectious diseases that affect both children and adults, particularly in the context of climate change. Bacteria are one of the causes of ARI. According to the government, the discovery of the bacteria that cause ARI is an indicator of successful management of infectious diseases. The current obstacle is the limited number of medical analysts, which results in longer microscopic examination times and requires a high level of objectivity. Therefore, a system for the early detection of ARI-causing bacteria was developed using digital image processing techniques, specifically channel area thresholding as one of the segmentation methods. This research employs four shape features for bacterial classification: the number of bacterial colonies, area, perimeter, and shape. The Naïve Bayes intelligent system method is used for the classification process. The system had an accuracy rate of 86.84% in the classification of four types of bacteria: S. aureus, S. pneumoniae, C. diphteriae and M. tuberculosis

Sorting of Mountage Cocoons Based on MobileSAM and Target Detection

The classification of silkworm cocoons is essential prior to silk reeling and serves as a key step in improving the quality of raw silk. At present, cocoon classification mainly relies on manual sorting, which is labor-intensive and inefficient. In this paper, a cocoon detection algorithm S-YOLOv8_c based on the cooperation of MobileSAM and YOLOv8 for the mountage cocoons was proposed. The MobileSAM with a designed area thresholding algorithm was used for the semantic segmentation of mountage cocoon images, which could mitigate the effect of complex backgrounds and maximize the discriminability of cocoon features. Subsequently, the BiFPN was added to the neck of YOLOv8 to improve the multiscale feature fusion capability. The loss function was replaced with the WIoU, and a dynamic non-monotonic focusing mechanism was introduced to improve the generalization ability. In addition, the GAM was incorporated into the head to focus on detailed cocoon information. Finally, the S-YOLOv8_c achieved a good detection accuracy on the test set, with a mAP of 95.8%. Furthermore, to experimentally validate the sorting ability, we deployed the proposed model onto the self-developed Cartesian coordinate automatic cocoon harvester, which indicated that it would effectively meet the requirements of accurate and efficient cocoon sorting.

A study on table tennis landing point detection algorithm based on spatial domain information

To address the limitations of computer vision-assisted table tennis ball detection, which heavily relies on vision acquisition equipment and exhibits slow processing speed, we propose a real-time calculation method for determining the landing point of table tennis balls. This novel approach is based on spatial domain information and reduces the dependency on vision acquisition equipment. This method incorporates several steps: employing dynamic color thresholding to determine the centroid coordinates of all objects in the video frames, utilizing target area thresholding and spatial Euclidean distance to eliminate interference balls and noise, optimizing the total number of video frames through keyframe extraction to reduce the number of operations for object recognition and landing point detection, and employing the four-frame difference slope method and polygonal area determination to detect the landing point and area of the target object, thereby obtaining precise coordinates and their corresponding areas. Experimental results on the above method on the Jetson Nano development board show that the dynamic color thresholding method achieves a detection speed of 45.3 fps. The keyframe extraction method correctly identifies the landing point frames with an accuracy rate exceeding 93.3%. In terms of drop point detection, the proposed method achieves 78.5% overall accuracy in detecting table tennis ball drop points while ensuring real-time detection. These experiments validate that the proposed method has the ability to detect table tennis ball drop points in real time and accurately in low frame rate vision acquisition devices and real environments.

Automated Platelet Counter with Detection Using K-Means Clustering

Platelet is a blood cell type that is stored and circulated in the human body. It acts as a blood thickening agent and prevents blood from overflowing whenever bleeding occurs. An excessive or inadequate number of platelets could lead to platelet-related diseases. The current practice of platelet counting involves the manual counting process using a haemocytometer, Wright’s Stain which uses the dyes to facilitate the differentiation of blood cell types, and a tally counter. Yet, this process can be time-consuming, demanding, and exhausting for haematologists, and likely to be prone to errors. Thus, this paper presents a study on automated platelet counter and detection using image processing techniques. The K-Means Clustering was employed to count and detect the presence of platelets in microscopic blood smear images. Several processes were performed prior to the K-means clustering, including image enhancement and YCbCr image formatting. Subsequently, image masking, as well as area thresholding were applied to eliminate every unwanted entity and highlight the visibility of the platelets before the number of platelets could be detected and counted. A comparative experiment was designed in which the K-Means Clustering platelet count and detection were compared with the actual number of platelets reported by haematologists. The platelet counts and detection were categorized into three detection categories which are Less Detection (LD), Accurate Detection (AD), and Over Detection (OD). The proposed study was evaluated to 90 testing platelet images. Out of the 90 testing images, 75 platelet images were perfectly counted and detected which returned 91.67% of accuracy. This signifies that the K-Means Clustering algorithm was discovered to be efficient and dependable for automated platelet counter and detection

Effect on signal magnitude thresholding on detecting student engagement through EEG in various screen size environment

In this study, a new method was developed to detect student involvement in the online learning process. This method is based on convolutional neural network (CNN) as a classifier with an emphasis on the preprocessing process combined with a new feature in the form of signal magnitude area (SMA) thresholding. In this study, the data used as training data is a public dataset that emphasizes the decomposition of electroencephalography (EEG) signals into individual signal processing. Twenty subjects were taken to be used as test data, with each subject watching online learning lectures in the field of computer science on three different devices, either with a flat screen, a curved screen or a smartphone screen that is smaller than two standard computer monitors. Based on the study's results, it is known that the change in screen size is inversely proportional to the level of student attention, the smaller the screen, the lower the student's attention. For classification results, the model equipped with SMA thresholding outperformed the standard classifier by 8.33% with a test set of 20 people.

Effect on signal magnitude thresholding on detecting student engagement through EEG in various screen size environment

In this study, a new method was developed to detect student involvement in the online learning process. This method is based on convolutional neural network (CNN) as a classifier with an emphasis on the preprocessing process combined with a new feature in the form of signal magnitude area (SMA) thresholding. In this study, the data used as training data is a public dataset that emphasizes the decomposition of electroencephalography (EEG) signals into individual signal processing. Twenty subjects were taken to be used as test data, with each subject watching online learning lectures in the field of computer science on three different devices, either with a flat screen, a curved screen or a smartphone screen that is smaller than two standard computer monitors. Based on the study's results, it is known that the change in screen size is inversely proportional to the level of student attention, the smaller the screen, the lower the student's attention. For classification results, the model equipped with SMA thresholding outperformed the standard classifier by 8.33% with a test set of 20 people.

Detection of Essential Thrombocythemia based on Platelet Count using Channel Area Thresholding

Essential Thrombocythemia is one of the Myeloproliferative Neoplasms Syndrome where the mutation of the JAK2V617F gene causes the bone marrow to produce excessive platelets. For early detection of Essential Thrombocythemia disease using a full blood count and peripheral blood smear examination. The main characteristic is that giant platelets are found as large as young lymphocytes with a number of more than 21 cells in one field of view. The purpose of this research is to detect Essential Thrombocythemia by counting the number of platelets in the peripheral blood smear image. This research utilizes computer vision technique where the research stages consist of peripheral blood smear image, color conversion, image enhancement, segmentation, labeling process, feature extraction and K-Nearest Neighbor classification. There are three features used, namely the number of platelet cells, area and perimeter. The K-Nearest Neighbor method is able to classify 215 training data with an accuracy of 98.13% and classify 40 testing data with an accuracy of 100% based on the value of K = 3. 

Estimating the Volume of Oil Tanks Based on High-Resolution Remote Sensing Images

The purpose of this study is to obtain oil tank volumes from high-resolution satellite imagery to meet the need to measure oil tank volume globally. A preprocessed remote sensing HSV image is used to extract the shadow of the oil tank by Otsu thresholding, shadow area thresholding, and morphological closing. The oil tank shadow is crescent-shaped. Hence, a median method based on sub-pixel subdivision positioning is used to calculate the shadow length of the oil tank and then determine its height with high precision. The top of the tank and its radius in the image are identified using the Hough transform. The final tank volume is calculated using its height and radius. A high-resolution Gaofen 2 optical remote sensing image is used to evaluate the proposed method. The actual height and volume of the tank we tested were 21.8 m and 109,532 m3. The experimental results show that the mean absolute error of the height of the tank calculated by the median method is 0.238 m, the relative error is within 1.15%, and the RMES is 0.23. The result is better than the previous work. The absolute error between the calculated and the actual tank volumes ranges between 416 and 3050 m3, and the relative error ranges between 0.38% and 2.78%. These results indicate that the proposed method can calculate the volume of oil tanks with high precision and sufficient accuracy for practical applications.

Onboard Automated CME Detection Algorithm for the Visible Emission Line Coronagraph on ADITYA-L1

ADITYA-L1 is India's first space mission to study the Sun from Lagrangian 1 position. { \textit{Visible Emission Line Coronagraph}} (VELC) is one of the seven payloads in ADITYA-L1 mission scheduled to be launched around 2020. One of the primary objectives of the VELC is to study the dynamics of coronal mass ejections (CMEs) in the inner corona. This will be accomplished by taking high resolution ($\approx$ 2.51 arcsec pixel$^{-1}$) images of corona from 1.05 R$_{\odot}$ -- 3 R$_{\odot}$ at high cadence of 1 s in 10 \AA\ passband centered at 5000 \AA. Due to limited telemetry at Lagrangian 1 position we plan to implement an onboard automated CME detection algorithm. The detection algorithm is based on the intensity thresholding followed by the area thresholding in successive difference images spatially re-binned to improve signal to noise ratio. We present the results of the application of this algorithm on the data from existing space- and ground-based coronagraph. Since, no existing space-based coronagraph has FOV similar to VELC, we have created synthetic coronal images for VELC FOV after including photon noise and injected different type of CMEs. The performance of CME detection algorithm is tested on these images. We found that for VELC images, the telemetry can be reduced by a factor of 85\% or more keeping CME detection rate of 70\% or above at the same time. Finally, we discuss the advantages and disadvantages of this algorithm. The application of such onboard algorithm in future will enable us to take higher resolution images with improved cadence from space and also reduce the load on limited telemetry at the same time. This will help in better understanding of CMEs by studying their characteristics with improved spatial and temporal resolutions.

Automated three-dimensional cell counting method for grading uveitis of rodent eye in vivo with optical coherence tomography.

In preclinical vision research, cell grading in small animal models is essential for the quantitative evaluation of intraocular inflammation. Here, we present a new and practical optical coherence tomography (OCT) image analysis method for the automated detection and counting of aqueous cells in the anterior chamber (AC) of a rodent model of uveitis. Anterior segment OCT images are acquired with a 100 kHz swept-source OCT system. The proposed method consists of 2 steps. In the first step, we first despeckle and binarize each OCT image. After removing AS structures in the binary image, we then apply area thresholding to isolate cell-like objects. Potential cell candidates are selected based on their best fit to roundness. The second step performs the cell counting within the whole AC, in which additional cell tracking analysis is conducted on the successive OCT images to eliminate redundancy in cell counting. Finally, 3D cell grading using the proposed method is demonstrated in longitudinal OCT imaging of a mouse model of anterior uveitis in vivo. Rendering of anterior segment (orange) of mouse eye and automatically counted anterior chamber cells (green). Inset is a top view of the rendering, showing the cell distribution across the anterior chamber.

Automated detection of Coronal Mass Ejections in Visible Emission Line Coronagraph (VELC) on-board ADITYA-L1

AbstractAn onboard automated coronal mass ejections (CMEs) detection algorithm has been developed for Visible Emission Line Coronagraph (VELC) onboard ADITYA-L1. The aim of this algorithm is to reduce the load on telemetry by sending the high spatial (~ 2.51 arcsec pixel−1) and temporal (1 s) resolution images of corona from 1.05 R⊙ to 3 R⊙, containing CMEs and rejecting others. It is based on intensity thresholding followed by an area thresholding in successive running difference images which are re-binned to lower resolution to improve signal to noise. Here we present the results of application of the algorithm on synthetic corona images generated for the VELC field of view (FOV).

DEM–compartment–population balance model for particle coating in a horizontal rotating drum

A multi-scale modeling approach combining the discrete element method (DEM), a compartment model, and a population balance (PB) has been used to predict inter-particle coating variability in a horizontal, rotating drum. In previous studies using compartment models, compartments were devised using a least squares fit to the spray zone residence time per pass (the time particles spend in the spray during a single pass through the spray zone) and the cycle time (the time between successive visits to the spray zone) distributions. In this work, the difficulties associated with measuring these time distributions are highlighted. In particular, the use of time and area thresholds used to eliminate short duration residence time correlations results in significant differences in the time distributions. A new approach that does not require area or time thresholding is used here. A compartment model consisting of a spray zone and active and passive bed zones is proposed based on the motion of the particles in a rotating drum. The parameters for the resulting coupled set of PB equations are estimated by fitting the time varying coating mass variability curve from the first few tens of seconds (35–85s) of DEM simulation data. The long term coating mass variability (1000s) is predicted using the PB model and compared with direct measurements from the DEM simulations. Excellent agreement was obtained between the model and DEM simulations with a relative error of less than 5% for the three cases studied. A sensitivity analysis of the parameters on the model predictions shows that the size of the active bed zone and the time scale of the exchange between the active and passive bed zones have a strong influence on the coating variability. The effective time distributions for the PB-generated spray zone residence time per pass and the cycle time were also found to be significantly different than those obtained from DEM using time or area thresholding. This new modeling approach significantly reduces the computational time required to study the particle coating process as compared to only using DEM.

WEED AND CROP SEGMENTATION AND CLASSIFICATION USING AREA THRESHOLDING

In the agricultural industry, the weed and crop identification and classification are major technical and economical importance. Two classification algorithms are focused in this paper. And the better classification algorithm has been selected to classify weed and crop from the images. There are three main parts of proposed system are segmentation, classification and error calculation. The developed algorithm based on area thresholding has been tested on weeds and various locations. Forty one sample images have been tested and the result of some weed coverage rate is illustrated. Moreover, the misclassification rate is also computed. An algorithm has been done to automate the tasks of segmentation and classification. The overall process is implemented in MATLAB.

An Approach to Identifying Litchi Fruits under Nature Scenes

In order to detect litchi fruit under nature scenes, an identification method was studied. A simple process was proposed to segment the image and remove noises. Its key steps include image converting; segmenting by Two-Cluster K-means clustering; labeling by white and black; small noises removing by open-close combined morphology; and big noises removing by blob area thresholding. A new contribution has been made to weighing by ultrasonic sensor and machine vision which allows for identifying litchi weight under nature scenes. A max error of 27% was recorded in tests of such weighing method.

Green citrus detection using hyperspectral imaging

The goal of this study was to develop an image processing method to detect green citrus fruit in individual trees. This technology can be applied for crop yield estimation at a much earlier stage of growth, providing many benefits to citrus growers. A hyperspectral camera of 369–1042 nm was employed to acquire hyperspectral images of green fruits of three different citrus varieties (Tangelo, Valencia, and Hamlin). First, a pixel discrimination function was generated based upon a linear discriminant analysis and applied to all pixels in a hyperspectral image for image segmentation of fruit and other objects. Then, spatial image processing steps (noise reduction filtering, labeling, and area thresholding) were applied to the segmented image, and green citrus fruits were detected. The results of pixel identification tests showed that detection success rates were 70–85%, depending on citrus varieties. The fruit detection tests revealed that 80–89% of the fruit in the foreground of the validation set were identified correctly, though many occluded or highly contrasted fruits were identified incorrectly.

Image Denoising by Statistical Area Thresholding

Area openings and closings are morphological filters which efficiently suppress impulse noise from an image, by removing small connected components of level sets. The problem of an objective choice of threshold for the area remains open. Here, a mathematical model for random images will be considered. Under this model, a Poisson approximation for the probability of appearance of any local pattern can be computed. In particular, the probability of observing a component with size larger than k in pure impulse noise has an explicit form. This permits the definition of a statistical test on the significance of connected components, thus providing an explicit formula for the area threshold of the denoising filter, as a function of the impulse noise probability parameter. Finally, using threshold decomposition, a denoising algorithm for grey level images is proposed.

A climatology of mesoscale convective systems over Europe using satellite infrared imagery. I: Methodology

AbstractAn automated method aimed at producing a significant European mesoscale convective system (MCS) climatology is presented. It uses Meteosat infrared window channel images and is composed of two main tools: an automated cloud‐shield tracking method and a robust method of discriminating between convective and nonconvective cloud shields.The automated cloud‐tracking method defines cloud systems as connected sets of pixels, named ‘cells’, after temperature and area thresholding and it is based on the overlapping between cells in successive images. It handles splits and merges of cells and takes cell movement into account. It has three parameters: the temperature and area thresholds and a minimum overlapping threshold. It is concluded that it performs a correct tracking at any temperature threshold between −30°C and −55°C and for an area threshold greater than 1000 km2, so that it allows the tracking of MCSs during most of their life cycle.The automated discrimination between convective and non‐convective cloud shields uses a discrimination parameter based on brightness‐temperature gradients on the edges of cells, because strong values of this gradient are observed at the beginning of the life cycle of MCSs when cold anvils develop. A seasonal study, and the sensitivity of the method to the temperature threshold, are presented. The method shows significant quality during the entire warm season (from April to September): it correctly discriminates 80% of MCSs and more than 90% of the most electrically active ones, while showing a low false‐alarm rate around 8%; therefore the method seems to be useful for climatological purposes. Copyright © 2002 Royal Meteorological Society

An adaptive logical method for binarization of degraded document images

This paper describes a modified logical thresholding method for binarization of seriously degraded and very poor quality gray-scale document images. This method can deal with complex signal-dependent noise, variable background intensity caused by nonuniform illumination, shadow, smear or smudge and very low contrast. The output image has no obvious loss of useful information. Firstly, we analyse the clustering and connection characteristics of the character stroke from the run-length histogram for selected image regions and various inhomogeneous gray-scale backgrounds. Then, we propose a modified logical thresholding method to extract the binary image adaptively from the degraded gray-scale document image with complex and inhomogeneous background. It can adjust the size of the local area and logical thresholding level adaptively according to the local run-length histogram and the local gray-scale inhomogeneity. Our method can threshold various poor quality gray-scale document images automatically without need of any prior knowledge of the document image and manual fine-tuning of parameters. It keeps useful information more accurately without overconnected and broken strokes of the characters, and thus, has a wider range of applications compared with other methods.

Automatic computer detection of clustered calcifications in digital mammograms

The automatic detection of clusters of calcifications in digital mammograms has been investigated using image analysis techniques. The calcifications were segmented from the background of normal breast structure in the mammogram using a local area thresholding process. This procedure also identified other breast structures and the digital image properties of all segmented objects were analysed to extract clusters of calcifications. Seventy five clinical mammograms were digitised. These were divided into training and test sets of 25 and 50 films respectively. The results for the test set of 50 complete clinical mammograms show that the computer system achieves a 25/25 true positive film classification (i.e. those containing clusters of calcifications) with false positive clusters detected in 4/50 films. There were no false negative film classifications.