Image Morphological Operations Research Articles

Detecting diabetic retinopathy using a hybrid ensemble XL machine model with dual weighted-Kernel ELM and improved mayfly optimization

The uncontrolled increase of blood glucose level affects the retina and cause Diabetic Retinopathy (DR), which can permanently damage blood vessels if left untreated for a long time. Early detection helps the patient’s to minimize the severity level. However, the existing Synergic Deep Learning (SDL) model for detecting severity levels of fundus DR images lacks proper filtering methods, suffers from low image quality, and improperly tuned hyperparameters. To address these issues, a hybrid ensemble Extreme Learning (XL) machine model is proposed in detection and classification of DR. The proposed model includes preprocessing steps, such as image filtering, conversion, segmentation, and morphological operations, to improve image quality. Also the parameters are tuned effectively and the weight functions are analyzed based on the extracted features that lower the blurriness of the images. A Dual Weighted-Kernel Extreme Learning Machine (DW-KELM) is developed to classify DR images with improved accuracy, and an Improved Mayfly Optimization (IMO) algorithm is applied to optimize the DW-KELM model’s parameters. Implementing the Weighted Average Ensemble (WAE) technique enhances the model’s performance by allocating different weights. Two datasets, namely the SUSTech-SYSU, APTOS-2019 and IDRID datasets, are used for experimentation, and the results revealed that DW-KELM achieved 99% accuracy, with an overall sensitivity, specificity, precision, and F1-score of 98.52%, 96.32%, 98.10%, and 98.52% respectively. The proposed model achieved better performance in classifying 5 DR classes, including moderate DR, Proliferative DR, no DR, severe DR, and mild DR, with good image quality.

Review on Automatic Detection & Counting of RBC’s by Using Image Processing Technique

Accurate counting of red blood cells (RBCs) in microscopic images is critical for various medical diagnoses and research purposes. Manual counting methods are labor-intensive, time-consuming, and prone to human error. This project aims to automate the RBC counting process using advanced image processing techniques. The primary objective is to improve the efficiency of the counting process, minimize subjectivity, and increase productivity in medical laboratories. The proposed method uses computer vision algorithms to analyze digital images of blood smears captured under a microscope. A combination of image segmentation and morphological operations is then applied to isolate individual RBCs, overcoming challenges posed by overlapping cells and variations in staining. Keywords: Image processing; Segmentation; Red Blood cells; Hough Transformation; RBC count.

A smart fruit size measuring method and system in natural environment

The measurement of fruit size (length, width, and area) is one of the key components in the assessment of fruit ripeness for consumption and fruit quality. Due to issues with fruit shape and ambient occlusion, noncontact measurement of fruits in their natural growth state in natural environment is more difficult. This study proposes a fast and low-cost noncontact measurement solution combining deep learning, image analysis and robotic platform. First, based on the YOLOv5 object detection algorithm and converged dataset, a 95.6% detection accuracy and 0.05 s detection speed was achieved. Second, a Cycle GAN model for fruit occlusion recovery was established, and the occlusion of the fruit under different natural conditions was adaptively repaired, with a 5.48% average relative error under different occlusion conditions. Third, through image morphological operations, the size measurements were achieved, with an average relative error of 8.43% for individual fruits and the 10.12% overall error under the complex natural environment. This method and platform provide a systematic, fast (0.2s) and low-cost solution for the noncontact measurement of fruit size.

Image Segmentation Solutions for Improved Non-Cooperative Target Recognition

The number of failed satellites in space is increasing, and they need to be fueled through space docking to extend their life or clean them out of orbit. Visual measurement is widely used in the docking session because of its real-time performance and economy, but the collected images will have background interference, which directly leads to the degradation of the accuracy of visual measurement. Reduce the difficulty of subsequent image processing by solving these problems. For the non-cooperative target of the star-arrow docking ring and the solar sail panel, which are two significant targets, this paper is based on target detection, according to the image difference, binarization, morphological operations and other methods to complete the accurate segmentation of the two targets, which can be more accurately complete the target detection, and the image segmentation effect is obvious. The target image obtained by image segmentation does not contain background interference, which is convenient for feature extraction and matching of the image.

Clean visual field reconstruction in robot-assisted laparoscopic surgery based on dynamic prediction

Robot-assisted minimally invasive surgery has been broadly employed in complicated operations. However, the multiple surgical instruments may occupy a large amount of visual space in complex operations performed in narrow spaces, which affects the surgeon’s judgment on the shape and position of the lesion as well as the course of its adjacent vessels/lacunae. In this paper, a surgical scene reconstruction method is proposed, which involves the tracking and removal of surgical instruments and the dynamic prediction of the obscured region. For tracking and segmentation of instruments, the image sequences are preprocessed by a modified U-Net architecture composed of a pre-trained ResNet101 encoder and a redesigned decoder. Also, the segmentation boundaries of the instrument shafts are extended using image filtering and a real-time index mask algorithm to achieve precise localization of the obscured elements. For predicting the deformation of soft tissues, a soft tissue deformation prediction algorithm is proposed based on dense optical flow gravitational field and entropy increase, which can achieve local dynamic visualization of the surgical scene by integrating image morphological operations. Finally, the preliminary experiments and the pre-clinical evaluation were presented to demonstrate the performance of the proposed method. The results show that the proposed method can provide the surgeon with a clean and comprehensive surgical scene, reconstruct the course of important vessels/lacunae, and avoid inadvertent injuries.

Soyabean Seed Boundary Detection Algorithm

Glycine max (soyabean) commonly used for oil, soya products, fodder, and protein supplements are inseparable part of human life and therefore its evaluation for high quality to ensure consistent increase had gain importance. In this work, extracting the boundary of soyabean seed from the background is proposed. The images are taken on a white background and using image processing tools and morphological operations the boundary of the seed region is automatically marked and then cropped for analysis. The proposed soybean quality inspection system can be used as an effective tool for real-time online inspection of soybean quality. Image processing and machine learning technique are modified to use the quality grading of soybean seeds. Due to quality grading is a very important process for the soybean industry and soybean farmers. There are still some critical problems that need to be overcome. Therefore, the key contributions of this paper are first, a method to eliminate shadow noise for segment soybean seeds of high quality. Keywords: Soybean Quality, Crushing Rate, Impurity Rate, Image Processing, Improved U-Net Algorithm.

A Novel Hybrid Retinal Blood Vessel Segmentation Algorithm for Enlarging the Measuring Range of Dual-Wavelength Retinal Oximetry

The non-invasive measurement of hemoglobin oxygen saturation (SO2) in retinal vessels is based on spectrophotometry and the absorption spectral characteristics of the tissue. The dual-wavelength retinal images are simultaneously captured via retinal oximetry. SO2 is calculated by processing a series of images and by calculating the optic density ratio of two images. However, existing SO2 research is focused on the thick vessels in the high-clarity region of retinal images. However, the thin vessels in the low-clarity region could provide significant information for the detection and diagnosis of neovascular diseases. To this end, we proposed a novel hybrid vessel segmentation algorithm. Firstly, a median filter was employed for image denoising. Secondly, high- and low-clarity region segmentation was carried out based on a clarity histogram. The vessels in the high-clarity areas were segmented after implementing a Gaussian filter, a matched filter, and morphological segmentation. Additionally, the vessels in the low-clarity areas were segmented using a guided filter, matched filtering, and dynamic threshold segmentation. Finally, the results were obtained through image merger and morphological operations. The experimental results and analysis show that the proposed method can effectively segment thick and thin vessels and can extend the measuring range of dual-wavelength retinal oximetry.

3D-shape formation of blood vessels based on computer aided design system

This paper proposes and tests a computerized approach for constructing a 3D model of blood vessels from angiogram images. The approach is divided into two steps, image features extraction and solid model formation. In the first step, image morphological operations and post-processing techniques are used for extracting geometrical entities from the angiogram image. These entities are the middle curve and outer edges of the blood vessel, which are then passed to a computer-aided graphical system for the second phase of processing. The system has embedded programming capabilities and pre-programmed libraries for automating a sequence of events that are exploited to create a solid model of the blood vessel. The gradient of the middle curve is adopted to steer the vessel’s direction, while the cross-sections of the blood vessel are formed as a sequence of circles lying in planes that are orthogonal to the gradients of the middle curves. The radii for the circles are estimated as a distance between the intersection points of the blood vessel edges with the orthogonal plane to the middle curve gradient. The system then uses these circles and the middle curve gradients to produce a solid volume that represents the 3D shape of the blood vessel. The method was tested and evaluated using different cases of angiogram images, and showed a reasonable agreement between the generated shapes and the tested images.

A System for the Automatic Detection and Evaluation of the Runway Surface Cracks Obtained by Unmanned Aerial Vehicle Imagery Using Deep Convolutional Neural Networks

The timely detection and recognizing of distress on an airport pavement is crucial for safe air traffic. For this purpose, a physical inspection of the airport maneuvering areas is regularly carried out, which might be time-consuming due to its size. One of the modern approaches to speeding up this process is unmanned aerial vehicle imagery followed by an automatic evaluation. This study explores the automatic detection of the transverse crack, its dimension measurement, and position determination within the slab on the concrete runway. The aerial image data were obtained from flights at the given altitude above the runway and processed using commercial multi-view reconstruction software to create a dataset for the training, verification, and testing of a YOLOv2 object detector. Once the crack was detected, the main features were obtained by image segmentation and morphological operations. The YOLOv2 detector was tuned with 3279 images until the detection metrics (average precision AP = 0.89) reached sufficient value for real deployment. The detected cracks were further processed to determine their position within the concrete slab, and their dimensions, i.e., length and width, were measured. The automated crack detection and evaluation system developed in this study was successfully verified on the experimental section of the runway as an example of practical application. It was proven that unmanned aerial vehicle imagery is efficient over broad areas and produces impressive results with the combination of artificial intelligence.

Roadway Snow Detection Using Dual-Spectrum Camera Images and Computer Vision

Unfavorable roadway conditions, such as slippery roads, can negatively affect the safety of highway transportation. We aimed to develop a convenient tool capable of evaluating multi-lane road slippery conditions in winter seasons. In this work, field data collection using a dual-spectrum camera was first performed at a field site in the state of Utah, U.S. We analyzed optical and infrared images covering a field of view over three lanes through two snowstorms. Image processing techniques, including image registration, morphological operation, and segmentation, were implemented on both types of images collected under different illumination and temperature conditions. Moreover, the ratio of snow-covered pixels was computed to quantify the snow coverage rate of individual lanes. Finally, we verified the system performance by comparing our estimation with the ground truth via a confusion matrix. The high accuracy, precision, true positive rate, and true negative rate suggest the developed approach can support satisfactory performance for roadway snow detection. Besides, the performance of the unsupervised k-means clustering algorithm and supervised support vector machine (SVM) were evaluated on a dataset of 22 optical images and 19 infrared images. Both the k-means clustering and SVM can support a reasonable image segmentation for roadway snow coverage estimation. Thus, the developed technique offers the potential to facilitate local agencies’ decision-making on snow-plowing resource planning and performance evaluation and support winter safety for connected vehicles.

Dynamic non-uniform phase shift measurement via Doppler frequency shift in vortex interferometer.

A vortex beam interferometer based on Doppler frequency shift is proposed to retrieve the dynamic non-uniform phase shift from the petal-like fringes produced by the coaxial superposition of high-order conjugated Laguerre-Gaussian modes. Unlike the uniform phase shift measurement in which the petal-like fringes rotate as a whole, the fringes due to the dynamic non-uniform phase shift rotate at different angles at different radii, resulting in highly twisted and stretched petals; this hinders rotation angle identification and phase retrieval via image morphological operation. To address the problem, a rotating chopper combined with a collecting lens and a point photodetector are placed at the exit of the vortex interferometer to introduce a carrier frequency in the absence of the phase shift. Once the phase starts to shift non-uniformly, the petals at different radii generate different Doppler frequency shifts, owing to their different rotation velocities. Thus, identification of spectral peaks near the carrier frequency immediately indicates the rotation velocities of the petals and the phase shifts at those radii. The results verified a relative error of phase shift measurement to be within 2.2% at the surface deformation velocities of 1, 0.5, and 0.2 µm/s. The method manifests itself to have potential in exploiting mechanical and thermophysical dynamics from the nanometer to micrometer scale.

Study on Automatic Electric Vehicle Charging Socket Detection Using ZED 2i Depth Sensor

This article introduces the utilization of the ZED 2i depth sensor in a robot-based automatic electric vehicle charging application. The employment of a stereo depth sensor is a significant aspect in robotic applications, since it is both the initial and the fundamental step in a series of robotic operations, where the intent is to detect and extract the charging socket on the vehicle’s body surface. The ZED 2i depth sensor was utilized for scene recording with artificial illumination. Later, the socket detection and extraction were accomplished using both simple image processing and morphological operations in an object extraction algorithm with tilt angles and centroid coordinates determination of the charging socket itself. The aim was to use well-known, simple, and proven image processing techniques in the proposed method to ensure both reliable and smooth functioning of the robot’s vision system in an industrial environment. The experiments demonstrated that the deployed algorithm both extracts the charging socket and determines the slope angles and socket coordinates successfully under various depth assessment conditions, with a detection rate of 94%.

Segmentation algorithm of coal slurry foam with double-point directional extension based on the improved FCM clustering algorithm

In flotation production, the visual surface information of the flotation foam reflects the flotation effects, which are closely related to the flotation conditions and directly reflect the degree of mineralization of the foam layer. In this study, it was proposed a novel and efficient segmentation algorithm to extract the edge information of slime bubbles, as the boundaries are typically blurred and difficult to segment, due to the slime bubbles sticking to each other in the slime flotation foam image. First, the improved clustering algorithm and image morphology operation were used to extract the edges of the foam spots. Second, the image morphological operations were used as a starting point to look around the foam edge points. The pseudo-edge points were then removed using a region and spatial removal algorithm. Finally, the foam edges were extracted using the double-point directed expansion algorithm. A new criterion was proposed for segmentation effect determination based on the particularity of the segmented object. The feasibility and effectiveness of the foam segmentation method were investigated by comparative experiments. The experimental results showed that the proposed algorithm could obtain the foam surface properties more accurately and provide effective guidance for flotation production.

Machine learning framework for Diabetes Retinopathy detection using hybrid logistic regression

Diabetes Retinopathy(DR) occurs due to an injury to the retina, ultimately steering towards sightlessness. DR does not provide any early clues or signs and unnoticeably associates a new blood vessel towards the back portion of the eye, resulting in clots of blood in the eye, bleeding of eyes and distorted vision. The conventional methods are failed to produce the maximum classification accuracy. Therefore, this article is focused on implementation of hybrid logistic regression (HLR)-based machine learning model for classification of DR.Initially, histogram equalization is used to enhance the region of DR image. Then, segmentation of microaneurysmsis performed by using image morphological operations. Further, features extracted using gray level co-occurrence matrix (GLCM), which shows the internal relationship of DR disease. Then, selection of features is carried out using the Gaussian Mixture Model (GMM). Finally, HLR model is applied to perform the multi class classification operation. Simulation results shows that the proposed method resulted in superior performance as compared to state of art approaches

Breast Sentinel Lymph Node Cancer Detection from Mammographic Images Based on Quantum Wavelet Transform and an Atrous Pyramid Convolutional Neural Network

This study proposes an optimal approach to reduce noise in mammographic images and to identify salt-and-pepper, Gaussian, Poisson, and impact noises to determine the exact mass detection operation after these noise reductions. It therefore offers a method for noise reduction operations called quantum wavelet transform filtering and a method for precision mass segmentation called the image morphological operations in mammographic images based on the classification with an atrous pyramid convolutional neural network (APCNN) as a deep learning model. The hybrid approach called a QWT-APCNN is evaluated in terms of criteria compared with previous methods such as peak signal-to-noise ratio (PSNR) and mean-squared error (MSE) in noise reduction and accuracy of detection for mass area recognition. The proposed method presents more performance of noise reduction and segmentation in comparison with state-of-the-art methods. In this paper, we used the APCNN based on the convolutional neural network (CNN) as a new deep learning method, which is able to extract features and perform classification simultaneously, but it is intended as far as possible, empirically for the purpose of this research to be able to determine breast cancer and then identify the exact area of the masses and then classify them according to benign, malignant, and suspicious classes. The obtained results presented that the proposed approach has better performance than others based on some evaluation criteria such as accuracy with 98.57%, sensitivity with 90%, specificity with 85%, and also ROC and AUC with a rate of 86.77.

Extraction of Aquaculture Pond Region in Coastal Waters of Southeast China Based on Spectral Features and Spatial Convolution

To control the negative effects resulting from the disorderly development of aquaculture ponds and promote the development of the aquaculture industry, rapid and accurate identification and extraction techniques are essential. An aquaculture pond is a special net-like water body divided by complex roads and dikes. Simple spectral features or spatial texture features are not sufficient to accurately extract it, and the mixed feature rule set is more demanding on computer performance. Supported by the GEE platform, and using the Landsat satellite data set and corresponding DEM combined with field survey data, we constructed a decision-making model for the extraction of aquaculture ponds in the coastal waters, and applied this method to the coastal waters of Southeast China. This method combined the image spectral information, spatial features, and morphological operations. The results showed that the total accuracy of this method was 93%, and the Kappa coefficient was 0.86. The overlapping proportions of results between the automated extraction and visual interpretation for test areas were all more than 90%, and the average was 92.5%, which reflected the high precision and reliability of this extraction method. Furthermore, in 2020, the total area of coastal aquaculture ponds in the study area was 6348.51 km2, which was distributed primarily in the cities of Guangdong and Jiangsu. Kernel density analysis suggested that aquaculture ponds in Guangdong and Jiangsu had the highest degree of concentration, which means that they face higher regulatory pressure in the management of aquaculture ponds than other provinces. Therefore, this method can be used to extract aquaculture ponds in coastal waters of the world, and holds great significance to promote the orderly management and scientific development of fishery aquaculture.

A novel approach of ceramic tile crack detection using morphological operations

In ceramic tiles manufacturing industry, tiles are manufactured at large scale which makes it more challenging to ensure the quality of each tile according to the set standards. Mostly, Statistical Process Control (SPC) is used by tile manufacturers at each step to monitor various processing parameters. SPC procedures are implemented manually that requires sufficient number of experienced human resource to identify defected tiles from a batch of tiles. The manual inspection also gives low accuracy of defect detection due to human errors and hard environment. Considering these drawbacks, in this paper an automated defect detection method is proposed which is based on image processing and morphological operation to ensure the quality and standard of tiles. The proposed method resizes and converts the input RGB image into grayscale image and removes any possible noisy artifacts. An edge detection algorithm is applied on grayscale image to enhance the edges representing the cracks. Afterwards, morphological erosion and dilation operations are applied, one at a time, to get two intermediate images. Finally, edges are detected by subtracting eroded intermediate image from dilated intermediate image. For detection, the proposed algorithm does not require any separate reference image. The algorithm is tested on an image set of sixty different defected tile images and attained 92% average detection accuracy.

Evaluation of Geometric Occlusal Conditions Based on the Image Analysis of Dental Plaster Models

It has been proved that dimensions of the dental arch may change as a result of growth or orthodontic treatment. The most intense transformations can be observed at young age during an occurrence of a mixed dentition period. Based on diagnostic models in a form of plaster casts there is a possibility to measure following features: overbite, overjet, the curve of Spee, arch depth, arch width and Bolton’s ratios. Nowadays computer-aided tools can provide valuable information for dentists or orthodontists and simplify analysis, diagnosis and preparation of a treatment plan. Correct organization of the dental arch in the horizontal plane can be modelled as a parabola for a mandible and as a section of the ellipse for a jaw. A developed system based on the Python programming language provides automated analysis of plaster model images. Proposed methodology includes preprocessing of provided casts’ pictures and segmentation of dental arch using methods such as image morphological operations, edge detection and active contour algorithm. In this research there were also calculated semi-ellipse and parabola fitting functions of dental arches and measured the root mean squared error relative to the original curves. Preliminary results showed 1.29 mm RMSE level for correct occlusion and 2.39 mm in case of malocclusion. Proposed methods can be used for simplifying the analysis of dental arches’ shape and monitoring of changes during orthodontic treatment.

Image enhancement methods on extracted texture features to detect prostate cancer by employing machine learning techniques

Prostate cancer (PCa) is the second most diagnosed cancer of men all over the world. The aim of this research was to improve PCa detection based on image enhancement methods including image adjustment and morphological erosion operations and then compute the texture features. We then employed robust Machine Learning (ML) techniques such as the Naïve Bayes, Support Vector Machine (SVM) kernels: Polynomial, Radial Base Function (RBF), Gaussian and Decision Tree (DT) based on extracted texture features. The Cross validation (Jack-Knife k-Fold) was performed, and performance was evaluated in term of Receiver Operating Curve (ROC), Specificity, Sensitivity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Positive Rate (FPR). The highest detection performance based on morphological erosion operation on texture features was obtained using SVM polynomial with sensitivity (99.82%), specificity (96.63%), accuracy (98.59%) and AUC (0.9994). The image adjustment methods yielded the highest detection performance with sensitivity, specificity, and accuracy of 100% and AUC of 1.00 using ML SVM selected kernels. The results reveal that proposed image enhancement methods have the potential to accurately predict PCa. Thus, this approach can be better utilized by clinicians for early prediction of PCa for further diagnostic and treatment of the patients.

Interest Contour Region Fusion Method based on Gaussian Mixture Model Segmentation

This paper presents an edge feature light-shadow fusion algorithm based on image segmentation. A new edge light shadow feature fusion algorithm based on image segmentation, morphological operation and image filtering is presented to extract target objects from image and fuse them with new background, which is cumbersome, difficult to operate, and lack of fast and effective target acquisition and feature fusion methods. The algorithm first labels the input image through an interactive system, then divides the labeled image to get the image target information, then processes the target object, obtains the edge of the target object, expands the edge to form a mask, combines the target object with the background, and filters through the edge mask to achieve the effect of fusing the target object with the background. The experimental results show that this method can process images with different complexity, not only to generate a combination of portrait and monochrome background, but also to generate a combination of other objects and natural scenery, so that the image can produce transitional natural effects.