Image Processing Stage Research Articles

A New Method for Surface-to-Air Video Detection and Tracking of Airborne Vehicles

Detection process of airborne targets may be thought simple because of the incompatible nature of aircraft, choppers, UAVs, and drones regarding clear sky background. When changes in the background are considered, brightness variation of the sky complicates the process. Changes in the shapes and types of clouds add another challenge to the process. Tracking process directly depends on the detection process and type of the data stream. The practical systems used for video detection and tracking of airborne targets are manual, and manual structures have some drawbacks compared to automatic structures. For video surveillance, guidance, regional security, and defense applications in dense environments, automatic detection and tracking process may be an obligation rather than preference. In this study, an automatic detection and tracking algorithm for video streams of airborne targets is proposed. A land-based moving camera captures the video data, and not only the flying objects but probably also the camera are in motion. Although the detection and tracking of moving objects via moving sensors is a relatively arduous task, this is the prevalent case in real-life scenarios. Video detection and tracking systems have one or more moving video sensors, while one or more flying air vehicles are in operation area. The proposed algorithm includes an image processing stage for detection and a tracking stage for initiation and continuation. An assessment study has been conducted for the actual video data and found that the proposed method yields successful results for detection, track formation, and continuation processes.

Features of metal structures digital images containing carbides investigation

The analysis of microsections requires the involvement of highly qualified experts in the field of materials science, which, in turn, does not exclude the influence of the "human factor". On the other hand, the issues of increasing the objectivity of identifying the properties of metals and alloys require the use of modern data processing methods, for example, artificial intelligence in solving problems of classification and identification of macro and micro structures.The paper presents an overview of studying macro and micro structures containing carbides process, determining the specific features inherent in these images, and proposing an information model for their processing. The article is devoted to the development of an information model intended for the analysis of metal structures digital images with carbide inclusions. The analysis of literary sources is carried out, it is established that the study of metal structures is an important tool for assessing qualitative characteristics. The presence of carbides in the metal structure has a significant impact on its quality. A review of the methodology for studying the structure of a metal is given, and the importance of metal structures image processing stage is determined. The main methods for obtaining digital images of the alloy structure are described. Samples of metal structures with carbides are presented. A procedure for digital processing of metal structures images with kibide inclusions is proposed, which consists of image conversion to grayscale, contrasting, and threshold binarization. An analysis of the results of metal structures processing images made it possible to identify areas with carbide inclusions, however, additional artifacts that were not carbides were found in some images. Balancing by the binarization threshold in this case does not improve the detection of carbide inclusions network due to the lack of contrast. Histograms demonstrate the presence of information features in a wide range of gray colors, so for this class of images, more sophisticated image processing technologies need to be developed. In the course of digital images features study of metals and alloys metal structures containing carbides, it was: an information model for processing metal structures containing carbide inclusions is proposed; the proposed information model is applied to digital images of metal structures; it was found that some images of metal structures are characterized by low contrast, which leads to the selection of background artifacts, except for areas with carbide inclusions; the development of complex mathematical methods for the detection of carbide inclusions in images of metal structures characterized by low contrast is proposed. Thus, the article shows the results of carbide inclusions of the using the digital image processing procedure. The advantages and disadvantages of the approach are shown, the directions for its improvement are determined.

Raspberry Pi-based mobile system of the pupil size evaluation

The article considers development of a human pupil measuring system on the Raspberry platform. The system is aimed at evaluating the variations of the human pupil diameter or area in the process of watching test images or video recordings. To reduce the interference from the eye surface the camera uses a band-stop color glass filter PS 13. In order to increase the pupil image contrast, IR LED backlighting of the eye is implemented. To provide the mobility of the system, battery power of the single-board computer was used while the registered image and the measurement results were transmitted via a Wi-Fi channel. The video camera and the single-board computer Raspberry Pi 4 with the battery bay are attached to the head-mounted flexible belt. The article gives the operation duration evaluation of the battery-supplied system. During the first stage of image processing, binarization by the threshold was performed. The threshold is determined by the image brightness histogram. Since the study is focused on relative variations of the pupil size, the pupil diameter or area values in pixels were chosen as informative parameters. The image recording and processing frequency in the system equalled 25 Hz that provides accurate recording of the pupil variations.

Weighted differential evolution algorithm based pansharpening

ABSTRACT Imaging Satellites acquire multispectral images, MIs, in low resolution, LR, and panchromatic images, PANs, in high resolution, HR, due to some advantages provided in satellite design. The pansharpening, PS, is a super resolution image synthesis method that is used to generate the pansharpened image, PI, by fusion of PAN and MI. The use of PS process is unavoidable in applications such as efficient use of communication-bandwidth of imaging satellites and fusion of images derived from various image sensors. The PS process is a multi-step process consisting of various complex image processing stages, such as registration, resampling, synthesis, and fusion. The Weighted Differential Evolution Algorithm-based PS method, WDEPS, has been proposed in this paper. The WDEPS uses WDE to synthesize the intensity image, which is the blended-image of MI -bands. WDE has been used to compute the relevant image-blending weights, efficiently. In the experiments, several satellite images (QuickBird-2, Ikonos-2, and GeoEye-1) with different spatial resolutions were used. The WDEPS’s experimental results have been compared with 17 well-known PS methods by using 9 full-reference and 3 blind image quality assessment metrics. The experimental results exposed that WDEPS generates high-quality PIs than traditional PS methods used in the experimental aspect of qualitative and quantitative assessment.

Detection of Foreign Materials in Wheat Kernels Using Regional Colour Descriptors

Present paper reports the development of an automated machine vision system for detection of foreign materials in wheat kernels using regional color descriptors. The said system was executed in the form of an integrated flowing pipeline after having proper choice of different possible alternatives at different stages of image processing. A new type of surface colour descriptor is also proposed in this work to define wheat kernel uniquely. The fifteen-element colour descriptor is executed after having thorough comparison of six different colour spaces, each having 72 separate quantifiable components. The fifteen elements of the proposed colour-descriptor, extracted from each segmented region of the sample image, are concatenated in the form of an input to the neural classifier. The neural classifier is trained with Levenberg-Marquardt (LM) learning algorithm to achieve extremely fast convergence. The recognition rate of the executed classifier is found to be more than 99.2% for detection of impurity in unconnected wheat kernels. The results of present investigations are quite promising. The proposed pipeline has potential future in the field of machine vision based quality inspection of wheat and other cereal grains.

Neural network classification system for pigmented skin neoplasms with preliminary hair removal in photographs

The article proposes a neural network classification system for pigmented skin neoplasms with a preliminary processing stage to remove hair from the images. The main difference of the proposed system is the use of the stage of preliminary image processing to identify the location of the hair and their further removal. This stage allows you to prepare dermatoscopic images for further analysis in order to carry out automated classification and diagnosis of pigmented skin lesions. Modeling was carried out using the MatLAB R2020b software package on clinical dermatoscopic images from the international open archive ISIC Melanoma Project. The proposed system made it possible to increase the recognition accuracy of pigmented skin lesion images in 10 diagnostically important categories up to 80.81%. The use of the proposed system for the recognition and classification of images of dermatoscopic pigmented lesions by specialists will make it possible to increase the diagnostic efficiency in comparison with methods of visual diagnosis, and will also allow starting treatment at an earlier stage of the disease, which directly affects the survival and recovery rates for patients.

Natural Computing of Human Facial Emotion Using Multi-Learning Fuzzy Approach

Emotions are described as strong feelings that are expressed by an individual in response to reactions to something or someone. Emotions are a very important aspect of day-to-day life interaction. Research shows that more than 90% of communication will happen non-verbally. This paper presents human emotion detection using a fuzzy relational model. The model consists of an image processing stage followed by an emotion recognition phase. The authors additionally made sub-categories in the most important expressions like happy and sad to discover the level of happiness and sadness in one face. Feature extraction along with multi-learning approach will help to test whether the person is truly happy or appearing to be happy. Experimental outcomes on the image dataset point out the accurate performance of the proposed technique. The experiment gives good accuracy results with the authors' own data set and robust with reference to some latest and leading edge.

Unmanned aerial vehicles (UAV) as a tool for visual inspection of building facades in AEC+FM industry

PurposeThe purpose of this paper is to report on the results of an exploratory study on the use of unmanned aerial vehicles (UAV) as a visual data collection tool in the architecture, engineering, construction and facility management industry for the inspection of pathological manifestations in building facades.Design/methodology/approachThe methodology used a field research experimental approach, where three case studies were carried out involving buildings of medium and high elevation. The protocol of activities included image collection and processing stages, as well as detailed analysis of the collected visual data for the identification of pathological manifestations in building facades.FindingsThe findings emphasize the technical feasibility and efficacy of inspections with UAV, showing that among the visual assets produced, digital photographs collected with the aircraft were more effective for the detection of pathologies when compared to the three-dimensional models and orthomosaics generated by digital photogrammetry software.Originality/valueThe research has formulated the protocol for the inspection of facades using UAV and the comparative analysis of visual assets that can be generated for inspection purposes.

Determination of the air void content of asphalt concrete mixtures using artificial intelligence techniques to segment micro-CT images

ABSTRACT X-ray micro-computed tomography (micro-CT) is an advanced technique able to provide a comprehensive examination of the volumetric characteristics of asphalt mixtures. A key step for the air void (AV) quantification using micro-CT images is the segmentation, which is a stage of the digital image processing. The most common segmentation technique, the manual threshold (TH) selection, depends significantly on the operator skills, image homogeneity, and material complexity. These factors that can limit the reproducibility of the TH procedure. Machine learning and deep learning recently appeared as promising alternatives to solve this challenge. In this paper, images of an asphalt concrete (AC) specimen were acquired in a modern high-resolution micro-CT scanner to determine its AV content using four different segmentation tools, i.e. TH, watershed, machine learning, and deep learning. All methods presented similar results for the total AV content. The advantages and limitations of using each technique were discussed in terms of computational effort, user-friendliness, and accuracy of the results. Machine learning and deep learning were identified as powerful tools for AC segmentation, being accurate and easy to adjust, however taking longer data processing times.

Object Detection with a Webcam Using the Python Programming Language

Technology developed rapidly along the times, various ways are done to make works easier. One of them is by utilizing artificial intelligence, likes the use of a webcam as a sensor in detecting an object through several stages of image processing. There was research on object recognition previously using three measurement parameters based on color, shape, and size of objects. It is used a webcam as the sensing sensor, and image processing is processed with python programming. In this article, writer described about image processing for the detection of objects used in the research. The results of this device have been tested and are able to detect objects properly based on predetermined color, shape and size. Object detection using a webcam can work properly according to what the author wants.

Detection of Heart Abnormalities Based On ECG Signal Characteristics using Multilayer Perceptron with Firefly Algorithm-Simulated Annealing

Heart disease is one of the causes of death worldwide. Therefore, detecting heart disease is very important to reduce the increased mortality rate. One of the methods used to detect the abnormalities or disorders of the heart is to use computer assistance to determine the characteristics of an electrocardiogram. Electrocardiogram (ECG) is a test that detects and records the activity of the heart through small metal electrodes attached to the skin of one's chest, arms and legs. This test shows how fast the heart beats and whether the rhythm is stable or not. The purpose of this thesis is to apply a multi-layer perceptron model with firefly algorithm and simulated annealing in detecting cardiac abnormalities based on the ECG signal characteristics. The initial step of this research is image processing. The stages of ECG image processing are grayscale, thresholding, edge detection, segmentation and normalization processes. The results of this image processing are used as input matrices in the perceptron multilayer network training using firefly algorithm and simulated annealing. In the training process, we will get optimal weights and biases for validation tests on test data. The training data in this thesis uses 20 ECG images and in the validation test process uses 10 ECG images. The validation results in the validation test show that the accuracy in detecting heart abnormalities based on the characteristics of ECG signals using multi- layer perceptron with firefly algorithm and simulated annealing is 100%.

Mechanical behavior of a sandwich plate with aluminum foam core, using an image-based layerwise model

Functionally graded materials are an advanced type of composite materials whose properties’ spatial evolution can be designed through the definition of the spatial distribution of the constituent phases’ mixture. This feature is particularly important if specific non-homogeneous properties’ requirements are required without introducing abrupt phases’ transitions, as happens in laminated materials. Porosities’ distributions within these materials, may constitute a design requisite for some applications, such as medical implants, but can also be highly undesirable in other cases such as for aeronautical applications. Regardless the specific situation, its characterization is of high importance to the prediction of the resulting materials’ behavior. This work is focused on the static and free vibrations’ analysis of a sandwich plate with a porous aluminum foam core and outer aluminum skins. The porosities’ distribution is modeled by different fitting functions, based on data obtained from a preliminary image processing stage of X-ray CT image of the sandwich plate’ cross-section. A layerwise approach is considered for subsequent numerical simulations’ purpose, where the sandwich skins’ kinematics are modeled using the first order shear deformation theory, while the core is modeled by a higher order shear deformation theory. Fitting functions’ influence on the plate’ behavior is also assessed.

A Study on Segmenting Brain Tumor MRI Images

Segmentation of image has traditionally been referred to as the initial stage in image processing. A successful segmentation output will make image processing analysis considerably further easier. There are several image segmentation techniques and methodologies available. Clustering is the most widely used segmentation algorithm for image processing. Segmentation of tumor using magnetic resonance imaging (MRI) data is a critical procedure yet time-consuming process manually carried out by medical specialists. Due to the considerable difference in the tumor tissue appearances across patients, as well as their occasionally similar resemblance to normal tissues, automating this procedure is difficult. MRI is a sort of sophisticated medical imaging that offers precise information on the human soft tissues. To identify and segment the brain tumor using MRI images, several brain tumor segmentation and detection approaches are analyzed. The benefits and drawbacks of these approaches for brain tumor identification and segmentation are analyzed, with an emphasis on illuminating the benefits and limitations of these techniques for brain tumor segmentation and detection. The MRI image usage in segmentation and detection on various processes is also covered. This analysis provides an overview of several segmentation methods for identifying brain tumors from MRI images of the brain, as well as the usage of various Clustering Techniques.

Three-dimensional (3D) reconstruction for non-destructive plant growth observation system using close-range photogrammetry method

Agriculture in Indonesia has recently experienced challenges, especially in terms of meeting market demand that tends to increase. Precision agriculture is an effort to increase productivity through optimizing agricultural production processes by minimizing inputs, maximizing output, and reducing the impact on the environment through the use of information and communication technology. Implementation of the concept of precision agriculture is in observing plant growth and development to estimates of plant volume and mass. So far, conventional plant measurements by direct measurement can pose destructive risks to plants. Therefore, a non-destructive system for observing and measuring plants is needed. The purpose of this study was to develop a plant growth observation system based on three-dimensional modelling with non-destructive measurements using the Close-Range Photogrammetry (CRP) method. This system has a 360 orbital scanner component that consists of a frame, camera arm, NEMA 17 stepper motor, Logitech C270 web-camera, Raspberry Pi 3 B +, Adafruit motor driver, and LED strip lights. The stage of image processing using 3DF Zephyr Pro software for generating the 3D sparse point cloud and cropping the unused point. For the validation purposes and its functionality for modelling and estimating volumetric objects, a plant model with three sizes (small, medium, and large) variations were used. As the result, the developed system could observe and model the plant shape in a three-dimensional manner resemble the actual plant model.

An accurate Cluster chaotic optimization approach for digital medical image segmentation

Image segmentation is a crucial stage in digital image processing used to obtain a more straightforward representation of images. Although classic bi-level segmentation is a relatively simple task, it only suffices to analyze rather simple images. More complex real-life scenarios such as medical imaging processing usually require multi-level segmentation to differentiate between the many regions of interest present in the original images. Traditional histogram-based approaches for multi-level segmentation tend to perform suboptimally, with the best performing being computationally expensive. This difficult compromise between performance and computational cost has led to the proposal of new approaches mixing a variety of optimization algorithms and statistical criteria. Despite the success of these new approaches, there is still room for improvement. It is under these circumstances that evolutionary algorithms like the cluster chaotic optimization (CCO) become relevant. The CCO takes advantage of the classification procedures of clustering techniques and the randomness of chaotic sequences for encouraging the search strategy. This paper proposes a novel method based on the CCO algorithm named minimum cross-entropy multi-level segmentation CCO (CEMS-CCO). The CEMS-CCO employs the cross-entropy as its fitness function and the CCO capabilities to deal with multimodal functions to search for the optimal solution to the multi-level segmentation problem. The CEMS-CCO shows competitive results for medical images multi-level segmentation regarding different quality metrics. Furthermore, its robustness and effectiveness are tested through the analysis of well-known benchmark images. Statistical analysis of the experimental results shows that the proposed CEMS-CCO technique outperforms state-of-the-art algorithms.

Rancangan Alat Pendeteksi Benda dengan Berdasarkan Warna, Bentuk, dan Ukuran dengan Webcam

Along with the times, technology is also developing so rapidly, one of the innovations in technological development is the use of webcams. the use of a webcam can be developed as a sensor in detecting an object through several stages of image processing. The use of a webcam aims to simplify an automation system so that it can be used to perform several tasks at once. Therefore, the author intends to design and manufacture an object detector with measurement parameters of the object's color, shape and size. This tool uses a webcam as a sensing sensor, and uses programming in PYTHON to recognize objects to be detected, and uses a servo motor to drive object actuators. The results of this tool have been tested and are able to detect objects properly based on predetermined color, shape and size. This tool is also able to separate objects that meet specifications from objects that do not meet specifications. Object detection using a webcam and an object separating actuator can work well.

Clustering polymorphs of tau and IAPP fibrils with the CHEP algorithm

Recent steps towards automation have improved the quality and efficiency of the entire cryo-electron microscopy workflow, from sample preparation to image processing. Most of the image processing steps are now quite automated, but there are still a few steps which need the specific intervention of researchers. One such step is the identification and separation of helical protein polymorphs at early stages of image processing. Here, we tested and evaluated our recent clustering approach on three datasets containing amyloid fibrils, demonstrating that the proposed unsupervised clustering method automatically and effectively identifies the polymorphs from cryo-EM images. As an automated polymorph separation method, it has the potential to complement automated helical picking, which typically cannot easily distinguish between polymorphs with subtle differences in morphology, and is therefore a useful tool for the image processing and structure determination of helical proteins.

Localization and classification of human facial emotions using local intensity order pattern and shape-based texture features

Facial emotion recognition system (FERS) recognize the person’s emotions based on various image processing stages including feature extraction as one of the major processing steps. In this study, we presented a hybrid approach for recognizing facial expressions by performing the feature level fusion of a local and a global feature descriptor that is classified by a support vector machine (SVM) classifier. Histogram of oriented gradients (HoG) is selected for the extraction of global facial features and local intensity order pattern (LIOP) to extract the local features. As HoG is a shape-based descriptor, with the help of edge information, it can extract the deformations caused in facial muscles due to changing emotions. On the contrary, LIOP works based on the information of pixels intensity order and is invariant to change in image viewpoint, illumination conditions, JPEG compression, and image blurring as well. Thus both the descriptors proved useful to recognize the emotions effectively in the images captured in both constrained and realistic scenarios. The performance of the proposed model is evaluated based on the lab-constrained datasets including CK+, TFEID, JAFFE as well as on realistic datasets including SFEW, RaF, and FER-2013 dataset. The optimal recognition accuracy of 99.8%, 98.2%, 93.5%, 78.1%, 63.0%, 56.0% achieved respectively for CK+, JAFFE, TFEID, RaF, FER-2013 and SFEW datasets respectively.

MODEL PROPOSAL ON THE DETERMINATION OF STUDENT ATTENDANCE IN DISTANCE EDUCATION WITH FACE RECOGNITION TECHNOLOGY

The aim of this study is to present a model proposal on determining the student participation rate in synchronous courses given in Learning Management Systems (LMS). Especially in situations where equal opportunities cannot be provided or opportunities are limited, distance education provides benefits for learning anytime and anywhere (ubiquitous learning) with the support of educational technologies. When the literature is examined, thanks to distance education; It is seen that it offers a very advantageous teaching environment in terms of location, time, convenience in accessing the resources needed and cost-benefit. However, when the literature is analyzed, it is found that there is a problem in determining the participation levels and rates of students in the Learning Management Systems used in distance education. Students access the activity or course in LMS using text-based user information and passwords. Unfortunately, it is not possible to determine with the current LMS whether the participant is the real responsible person or he/she is actively/synchronously following the course. In this context, a design model has been presented using face recognition algorithms to determine attendance in distance education, to ensure more active participation and to increase success indirectly. In the proposed model, tests were made using special filters for image processing, and in cases where the number of samples was increased, more than 80% accuracy was provided. The proposed design model was developed in Visual Studio.Net platform and coded on C# programming language. SQL server is used as database management system and EmguCV library is used for the image processing stages.

A New Hybrid Filter Approach for Image Processing

Today, with the rapidly advancing technology, the importance of image processing techniques is increasing. Image processing is used in many areas from facial recognition to plant disease identification. One of the important image processing stages is the filtering stage used for smoothing images and object detection. Among these filtering techniques, basic filtering techniques such as mean, median and Gaussian are used in image processing. However, these filtering techniques are known to be insufficient to achieve the desired results in some cases. In this study, a new hybrid filtering approach named Mean-Median-Gaussian (MMG) is presented using these three basic filtering techniques. It has been demonstrated that the obtained MMG hybrid algorithm gives more successful results than these three basic filtering techniques in smoothing the images and determining the boundary lines.