Search

In the drilling process of printed circuit boards, achieving the operation with the least cost depends on the distance travelled by the drilling route. In this study, an integrated method is proposed to carry out the drilling process with the least cost and high speed. In the proposed method, the positions of electronic circuit elements to be placed on the printed circuit board are detected using image processing techniques on a two-dimensional circuit image. Annealing Simulation, Particle Swarm Optimization and Ant Colony Algorithms have been used to solve the travelling salesman problem, and their performances have been examined. When comparing the test results of the obtained models, it is observed that the Ant Colony Algorithm, at the same iteration values, provides solutions with significantly shorter route lengths compared to Simulated Annealing and Particle Swarm Optimization algorithms. [ABSTRACT FROM AUTHOR]

Investigations to increase the level of adaptation to social life and the sense of independence of individuals with visual impairment are very important in terms of social contribution. Facilitating the shopping experiences of these individuals can be among these studies. Research in this field shows that traditional methods are generally used to classify shopping products and to introduce the shelves. In this proposed study, products on supermarket shelves are classified using deep artificial neural networks different from traditional methods. In addition, in order to provide convenience to individuals with visual impairments, the Flutter infrastructure, which can be integrated into smart devices used in daily life and supports all mobile operating systems, will be preferred in the second phase of the study. The application was realized by creating a data set of 2222 images obtained from a market in Erzurum province and 14 different categories. In order to have a balanced number of category-based data, a total of 4585 images were trained and classified with YOLOv5, YOLOv8 and EfficientDet D7TF2 models. In the experiments, YOLOv8 model outperformed the other methods with 92.8% accuracy, 98.6% precision, 95% sensitivity and 96.8% F1 score. [ABSTRACT FROM AUTHOR]

Copyright of Dicle University Journal of Engineering / Dicle Üniversitesi Mühendislik Dergisi is the property of Dicle Universitesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Dicle University Journal of Engineering / Dicle Üniversitesi Mühendislik Dergisi is the property of Dicle Universitesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of International Journal of Advances in Engineering & Pure Sciences is the property of Marmara University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Karayolu esnek üstyapılarındaki çatlaklar genellikle trafik yükleri ve hava koşullarından kaynaklanır. Bu çatlakların genişlemeden tespit edilip gerekli bakımlarının yapılması, yol konforunun sürekliliğini sağlamanın yanı sıra bakım maliyetlerini de azaltacaktır. Bu çalışma, yoldaki çatlakları gerçek zamanlı ve yüksek doğrulukla tespit etmeyi amaçlamaktadır. Bu bağlamda, Geri Yayımlı Birlikte Evrim yaklaşımıyla İyileştirilmiş Derin Sinir Ağları ve görüntü işleme yöntemleri birlikte kullanılmıştır. Ayrıca, çeşitli sayı ve çözünürlüklerde çatlaklı görsel veriler içeren EdmCrack600, AsphaltCrack, CFD ve CrackSegmentation veri setleri kullanılarak yeni bir veri seti oluşturulmuş ve bu veri seti üzerinde Derin Sinir Ağları tabanlı öğrenme gerçekleştirilmiştir. Modelin doğruluğu, CFD veri seti kullanılarak Kesinlik, Duyarlılık ve F1-Skoru ile değerlendirilmiştir. Değerlendirme sonucunda, önerilen yöntemin saniyede 48 görsel üzerinde çatlak tespit edebildiği ve %92,74 Kesinlik, %88,92 Duyarlılık ve %89,61 F1 Skoru başarı oranlarına ulaştığı gözlemlenmiştir.

With the development of technology in terms of unmanned aerial vehicles (UAV), their usage areas and research studies on them are increasing by the time. Although they are called unmanned, UAVs are controlled with the help of a pilot or flight attendant, or their autonomous flights are programmed. In line with the research, it has been determined that most of the problems and accidents occur during the landing of UAVs. In order to reduce this rate, detecting the landing runway with image processing methods and analyzing the obstacles on the runway with the point cloud method during the landing phase is an important step to be taken in this regard. For this reason, this study includes applications that can be used in UAV landing systems and provided with deep learning networks. First of all, the landing runway to be analyzed has been designed. This runway is left in an environment with different vehicles and obstacles around it. Later, real images and video recordings of the runway are taken from different heights and angles with a four-rotor UAV. The captured images have then been used to undergo processing and training stages. UAV landing runway detection has been achieved as a result of taking real images of the runway where the UAV would land, creating a dataset, and processing these images in YOLOv8. After the landing runway has been determined, the presence or absence of obstacles on the runway has been examined and analyzed using the point cloud data. The application has been completed, with depth maps provided in black-and-white and RGB form. [ABSTRACT FROM AUTHOR]

Image processing technique has come up with advancement of computer technology and has recently been widely used. This technique consists of two parts. In the first part, the input such as an image or a video obtained by a camera or a scanner is digitized. In the second part, some characteristics or parameters related to the image is gathered by using algorithms. By the improvements that took place in the area of image processing, the technique is now very popular in agricultural field and is an alternative method in identification of weeds, determination of their intensity and color properties. In this study, the color properties of three weeds; Chenopodium album L., Sonchus hierrensis, Lectuca serriola obtained by a digital camera and a Chroma meter were compared. [ABSTRACT FROM AUTHOR]

This research focuses on the automatic measurement of springback angle using image processing techniques on photographs of bent samples. A program has been developed as an alternative to traditional universal angle gauges, which can exhibit variability due to user error. In this study, springback measurements were made using a universal angle gauge on samples subjected to bending at different angles. In addition, automatic springback values were obtained from photographs of the samples using the developed program. The effects of image processing techniques such as photo filtering and edge detection methods were investigated and different methods were experimented with. The developed program successfully detected springback angles on both original and filtered photographs. The results obtained indicate a high degree of accuracy in the measurements. When measuring, the Gaussian filtering method provides the lowest error rate, while the Sobel and Prewitt algorithms have been determined as the most suitable algorithms based on the tests conducted. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of InformaticsTechnologies is the property of Institute of Informatics, Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of International Journal of InformaticsTechnologies is the property of Institute of Informatics, Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study aims to develop a low-cost, multi-purpose module based on edge computing for bacterial colony counting and classification. Due to the time-consuming and error-prone nature of traditional methods, this new system has been developed with microcontroller integration and artificial intelligence support. The system utilizes the Arduino Nano 33 BLE microcontroller and a 0.3MP OV7675 camera module, employing Gaussian Blur and Adaptive Thresholding techniques for image processing to better define bacterial colonies. The labeling and feature extraction of colonies involve analyzing characteristics such as area, perimeter, and density. Convolutional Neural Networks and Support Vector Machines have been used for bacterial colony counting and classification. The combination of these two algorithms has facilitated colony analysis. The developed system enables tracking of colony numbers and growth rates over time, emphasizing the importance of a microcontroller-integrated and AI-supported system in achieving fast and traceable results in bacterial colony counting and classification. [ABSTRACT FROM AUTHOR]

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cracks in highway flexible pavements are primarily caused by traffic loads and weather conditions. Detecting these cracks before they expand and conducting necessary maintenance will not only ensure the continuity of road comfort but will also reduce maintenance costs. This study aims to detect cracks on the road in real-time and with high accuracy. In this context, Deep Neural Networks Developed via Cooperative Coevolution with Backpropagation and image processing methods were used together. Moreover, a new data set was obtained by using EdmCrack600, AsphaltCrack, CFD, and CrackSegmentation datasets containing cracked visual data in various numbers and resolutions, and Deep Neural Networks-based learning was performed on this dataset. The accuracy of the model was evaluated with Precision, Recall, and F1-Score using the CFD dataset. As a result of the evaluation, it has been observed that the proposed method can detect cracks on 48 images per second, while it can reach 92.74% Precision, 88.92% Recall, and 89.61% F1-Score success rates. [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Forests are an indispensable part of the Earth in terms of their biodiversity and contributions. Fires are one of the most important factors affecting forests, which cover one third of our planet. Forest fires are among the most destructive natural disasters on Earth and are also a very important source of gases and aerosols. The monitoring of forest fires is extremely important for disaster monitoring and prevention. Geographic Information Systems (GIS) and remote sensing, which have been widely used in fire monitoring in recent years, are prominent methods in terms of data collection, analysis and interpretation. This study focuses on the analysis of the forest fire that occurred in Çanakkale on August 22, 2023 and lasted for 3 days with the help of Sentinel-2 and 5P remote sensing images and GIS. The results of the analysis showed that the total area affected by the fire was 4191.93 hectares (ha) and covered a wide range of land cover/use classes. In particular, forests and agricultural lands were the most severely affected in this region. The aerosol index and nitrogen dioxide (NO2) air pollution parameters, which indicate the concentration of pollutants emitted into the atmosphere after the fire, were monitored and their concentrations determined from satellite imagery. The highest NO2 concentration recorded was 0.02624702 mol/m² on August 24, the last day of the fire. The total amount of NO2 emitted into the atmosphere for three days was determined to be 0.06020184 mol/m².

Fiber materials possess unique properties, including a large active surface area, high surface-to-volume ratio, high porosity, high mechanical performance, and low density. Consequently, they serve as key components in various applications such as energy production and storage cells, batteries, wastewater treatment membranes, sensors, drug-releasing band-aids, and protective clothing. Electrospinning is a simple and versatile method for producing fiber materials. Despite its simplicity in terms of working principles, it faces challenges in achieving homogeneous thickness (evenly on the entire surface) throughout fiber mats due to inherent bending instability during the process. Non-uniform thickness not only diminishes the efficiency of these mats in applications but also adversely impacts their mechanical functionality. In this study, the aim is to develop a thickness measurement system based on image processing and the principle of light transmittance as a solution to the issues encountered in achieving uniform thickness and thickness control of fiber mats produced by electrospinning devices. To accomplish this, a closed mechanism with a light-impermeable encapsulation method was established. Various fiber mats, produced at different times were placed on the acetate floor built on LED lighting on the base of the mechanism. Using a camera with the adjusted settings positioned at the focal point on top of the mechanism, images of the fiber mats were captured, and image processing techniques were employed to determine threshold value ranges for the mat thicknesses. The actual thicknesses of the fiber mats were verified using an optical microscope, revealing that regions defined with the same color in different samples exhibited similar thicknesses.

Early detection of plant diseases holds a central place in the agriculture sector and is indispensable for both increasing yield and maintaining ecosystem balance. The advancements in artificial intelligence technologies have revolutionized this field, enabling rapid and effective identification of diseases. The ResNet model used in this study stands out as one of the best deep learning algorithms, demonstrating the ability to accurately classify a wide spectrum of diseases by detecting complex features on plant leaves. This superior performance of ResNet is a critical step in enhancing agricultural productivity and protecting plant health. The data examined in detail during the training process of the model show that the ResNet model has achieved extraordinary success in detecting plant diseases. The achieved 99% success rate is a clear indicator of how AIbased image processing technologies can play a vital role in agricultural applications. Such accuracy, especially in challenging outdoor conditions and on diverse leaf samples, is particularly impressive and proves the model's ability to understand and classify a wide disease spectrum. These results suggest that the ResNet model could be adopted as an industry standard in diagnosing plant diseases and create a transformation in agricultural applications. The findings of this study underline the contributions and potential of AIsupported plant disease detection systems for the agriculture sector. With the implementation of the advanced ResNet model, early and accurate disease detection is made possible, significantly improving the efficiency and sustainability of agricultural processes. This technological progress allows for the rapid treatment and prevention of diseases, thereby enhancing the overall quality and safety in agricultural production. This success demonstrates the power of ResNet's deep learning approach to offer applicable and effective solutions to real-world agricultural problems. [ABSTRACT FROM AUTHOR]

The rapid and accurate detection of defects in solar energy plants is of great importance to reduce efficiency losses and extend the lifespan of photovoltaic systems. In this study, the effectiveness and advantages of You Only Look Once (YOLO) algorithms for hotspot detection in solar energy plants have been investigated. YOLO algorithms can be efficiently used in large-scale facilities due to their ability to detect objects in images in a single scan at high speeds. In this context, the performances of YOLOv5, YOLOv6, YOLOv7, and YOLOv8 algorithms were compared, and the best-performing model was determined. According to the results of the experiments, 80% of the 100 images obtained by an unmanned aerial vehicle in the dataset were used for training, and the remaining 20% were used for testing the YOLO algorithms. The results indicated that the YOLOv8 algorithm outperformed other models with 88.7% specificity, 80.5% sensitivity, and 83.8% mean Average Precision (mAP) values. The dataset used in the study consisted of images obtained from real solar panels, ensuring that the results of the study were tested in accordance with real-world scenarios. The findings demonstrate that YOLO algorithms are an effective method for detecting hotspot defects in solar panels. This study highlights the importance of using object detection algorithms to make solar energy plants more efficient. Additionally, it can be considered as a guiding and contributing study to the literature, providing insights for future research. [ABSTRACT FROM AUTHOR]

Advanced camera systems integrated in to unmanned aerial vehicles (UAVs) enable the acquisition of highresolution images. These images are often more advantageous in terms of spatial, temporal, radiometric, and spectral resolution compared to satellite images. However, depending on the size of the scanned areas, the acquired data becomes large and occupies significant storage space. Therefore, processing the data to obtain meaningful information and insights becomes challenging. Various methods have been developed to extract meaningful data from images. While operators used to analyze images one by one in the past, today, objectbased and pixel-based data extractions have been developed. Thanks to these methods, data can be parsed by software rapidly and with high accuracy. Segmentation and classification methods facilitate processes such as categorization, sub-classification, parsing, and detection. Segmentation and classification processes on data are of crucial importance for the analysis of large and complex datasets. Numerous studies demonstrate that these techniques and applications are continuously evolving and gaining prominence in the literature. Within the scope of this study, segmentation and classification efforts conducted with UAVs have been discussed, and the outcomes of these studies have been examined. It is observed that studies utilizing hybrid and deep learning-based techniques tend to yield more efficient results compared to other approaches. [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Natural Hazards & Environment (JNHE) / Doğal Afetler ve Çevre Dergisi (DACD) is the property of Artvin Coruh University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cracks in buildings are a source of concern as they may indicate structural problems. Cracks in buildings are one of the major problems with concrete structures, as they affect the appearance of the building, compromise the integrity of the masonry, jeopardize building safety, and reduce the durability of the structure. Cracks in buildings can be a cause for concern and may indicate a potential structural problem that could jeopardize the safety and stability of the building. Understanding the root causes of these cracks is crucial to determining appropriate preventive measures and repair methods. In this study, crack and slope control in buildings was performed with an image processing-based measurement system developed using CNN deep learning algorithms. A dataset of 294 photographs was used for the study. The data were subjected to image processing, preprocessing, and detection with CNN. The accuracy rate is 0.9716 for the VGG-16 architecture and 0.9513 for the Inception-V3 architecture. It was concluded that there is no significant difference between the accuracy rates of the architectures. All vertical and horizontal cracks with a thickness of 2 mm and a continuity of 4 cm were detected. Thus, crack control in buildings can be done quickly and reliably, and building safety will be ensured. [ABSTRACT FROM AUTHOR]

With the rapid advancement of technology, the use of artificial intelligence (AI) is increasing in various sectors such as education, health, security and defense. A critical application of AI is highway management, especially with the rise of autonomous vehicles. The focus of this study is to address the problem of deformations in highway marking lines that pose challenges for autonomous vehicles and affect traffic safety. The research involves using unmanned aerial vehicle (UAV) to create an original image dataset of highway lines. This data set will be processed with image enhancement techniques and deep learning models. The first stage involves cleaning the images from foreign matter. Deep learning models will then identify potential line deformations. These models will be developed and trained for optimum accuracy using various performance metrics. In the study, the mobilenet v3 model, trained with the images in the data set, reached an accuracy rate of 89.58%, the resnet50 v2 model 77.78% and the Convolutional Neural Network model 92.55%. The ultimate goal is to implement a real-time system to accurately detect and report differences in highway lines by combining the UAV with the computer system on the ground. This will ensure timely notification to authorities and help prevent traffic safety problems related to line deformations. This approach demonstrates the practical applications of artificial intelligence in improving road safety and autonomous vehicle navigation. [ABSTRACT FROM AUTHOR]

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Nowadays, smart cities solutions have been becoming popular day by day. The problem of finding a parking place is one of these implementations. Our study appeals to users who want to park their vehicle quickly and who want to find out whether the parking place is available to park before searching for a parking place. This application aims to find a solution to the problem of searching for a place to park. We have found a novel solution to this problem by using image processing methods and utilizing photographs of streetside parking places in the most effective way. In addition, an Android software has been developed through which we can deliver the results obtained with the image processing module to users via a mobile application. As a result, a parking IoT determination system has been implemented in this study with 92% accuracy value. Thanks to this system, vehicle owners who want to park their vehicles on the side of the street will be able to learn whether the parking places in a street are available in advance and they will be able to save their time by preferring more available streets.

Uykululuk halinin önceden tespit edilmesi, uykululuğa bağlı trafik kazalarını önlemek, fiziksel ve ekonomik kayıpların önüne geçmek açısından önemlidir. Bir kamera yardımı ile kişilerin görüntüleri üzerinde görüntü işleme teknikleri uygulanarak uykululuk halini önceden kestirmek mümkündür. Bu çalışmada, literatürdeki veri kümelerinden yararlanılarak uykululuk halinin tespit edilmesinde büyük bilgiye sahip olan göz bölgesinden gelen öznitelikler ile göz kırpma tespiti yapmak için sabit ve uyarlamalı eşik değerleri ayrı ayrı değerlendirilmiştir. Böylece, kısa süreli göz kırpma ile uzun süreli göz kapamanın daha iyi ayırt edilmesi hedeflenmiştir. Çalışmada önerilen uyarlamalı eşik değerinin sabit bir eşik değerinden çok daha başarılı göz kırpma tespiti sonuçları verdiği, iki farklı veri kümesi üzerinde yapılan deneyler ile doğrulanmıştır.

Prematüre retinopatisi (ROP) hastalığının teşhisinde, retinadaki kan damarlarının özellikleri oldukça önemlidir. Erken doğan bebeklerde retina kan damarları büyümesini tamamlayamaz. Doğum sonrası, bazı tetikleyici durumlar düzenli damarların oluşumunun durmasına ve anormal kan damarlarının anormal doku oluşturarak genişlemeye başlamasına neden olur. Bu durumunun derecesinin artması ile retina hasarları oluşabilir. Özellikle prematüre doğan bebeklerin, prematüre retinopatisi hastalığı kapsamında olduğu için, damar ağlarında gelişmeleri takip ederek hastalığın seyrini takip etmek önemlidir. Bu çalışmada amacımız, prematüre bebeklerin retina görüntüleri üzerine görüntü işleme yöntemleri uygulayarak ROP görüntülerindeki damar yollarının tespiti ve segmentasyonu için yöntemler geliştirmektir. Uygulanan bu yöntemler, ROP görüntülerine uygulanarak sonuçlar sayısal olarak karşılaştırılmıştır. Sonuç olarak, en uygun görüntü işleme yönteminin, Tepe sinyalinin gürültüye oranı (PSNR) değerlerine göre; eşikleme yönteminde OTSU, filtreleme algoritmasında ise Gaussian filtresinin olduğu saptanmıştır.

Copyright of Dicle University Journal of Engineering / Dicle Üniversitesi Mühendislik Dergisi is the property of Dicle Universitesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Günümüzde otomotiv sektörü hızla büyümekte ve piyasaya çıkan araç sayısı her geçen gün artmaktadır. Araçların üretim esnasında veya kaza sonrasında meydana gelen şasi eğriliklerinin tespiti ve tamir sürecinin ardından, bu eğriliklerin ne ölçüde giderildiğinin tespiti önem arz etmektedir. Bu çalışmada, iki kameralı ve taşınabilir stereo görüntüleme sistemi kullanılarak görüntü üzerinden araçların şasi eğriliklerinin tespiti üzerine gerçek zamanlı bir yöntem sunulmuştur. Bu amaçla, öncelikle 8 MP kameraların self-kalibrasyonu gerçekleştirilmiş, sonrasında bu kameralar bir levha üzerine paralel olarak sabitlenmiştir. Ardından oluşturulan stereo görüntüleme sisteminin dış parametreleri elde edilmiştir. Ölçüm sırasında test edilecek araç, şasi üzerindeki noktaların tamamının görülebileceği minimum seviyeye bir lift vasıtasıyla kaldırılarak görüntüler elde edilmiştir. Şasi üzerinde belirli 8 farklı nokta, görüntüler üzerinde kullanıcı tarafından işaretlenmiştir. İşaretlenen bu noktalar 3B koordinatlara dönüştürülmüş ve elde edilen koordinatlar aracılığıyla da şasi üzerinde x-y düzleminde ve z ekseni doğrultusunda bulunan eğrilikler hesaplanmıştır. Deneysel çalışmalar sonucunda x-y düzlemi üzerinde 0-2 mm ve z yönündeki eğriliklerde 0-4 mm ölçüm hassasiyeti ile eğriliklerin tespit edildiği gösterilmiştir. Bu sistem ek bir ekipmana ihtiyaç duymadan, özellikle ikinci el araç ekspertiz merkezlerinde hızlı, ucuz ve bireysel test yapmayı mümkün hale getirecektir.

The properties of the blood vessels in the retina are very important in the diagnosis of retinopathy of prematurity (ROP). In premature infants, the blood vessels of the retina cannot complete their development. Post-natal, certain triggering circumstances cause the creation of regular veins to cease and abnormal blood vessels begin to enlarge forming abnormal tissue. With the increase in the degree of this condition, retinal damage may occur. It is crucial to follow the progress of the disease by following the developments in the vascular networks, especially since babies born prematurely are at greater risk for ROP. The purpose of this study is to develop methods for the detection and segmentation of vascular pathways in ROP images by applying image processing methods to retinal images of preterm neonatal. These methods have been applied to ROP images and the results have been compared numerically. As a result, according to the Peak Signal to Noise Ratio (PSNR) values of the most appropriate image processing method; It has been determined that there is an OTSU filter as the thresholding method and a Gaussian filter as the filtering algorithm. [ABSTRACT FROM AUTHOR]

Autonomous vehicles are increasingly used in daily life and industrial applications. Mobile robot technologies lead to autonomous architectures in these areas. The path planning methods of mobile robots contain differences in the purpose they realize. This trajectory planning from a determined starting point to the target point brings many techniques from image processing to artificial intelligence. In the study, an application with a unique design has been carried out on the tracking of circular objects with different diameters and colors by a mobile robot. Moving object is detected with CIE L^* a^* b^* color space with RGB-D camera by utilizing the ROS server-client architecture. The mobile robot tracks the detected object at a certain distance at a constant speed. Image filtering parameters are processed by the mobile robot in the Matlab environment together with the publisher-subscriber parameters. Thus, two circular objects with different colors, detected because of image processing and determined beforehand, are continuously followed by the mobile robot at a certain speed. Experiments were carried out using different diameter, size tolerance and color parameters in the image depending on the CIE L^* a^* b^* color space.

Bu çalışmada farklı bir yaklaşımla yeni orkide sınıflandırmalarını test etmek, yaprak damar deseninin bu sınıflandırmaları ne derecede temsil ettiğini araştırmak ve diagnostik olan damarlanma özelliklerinin belirlenmesi amaçlanmıştır. Sistematik kategorisi değişen türler ile birlikte Orchis üyelerinden simpatrik yayılış gösteren 8 tür araştırmaya konu edilmiştir. Bitki örnekleri Karadeniz Bölgesi’ndeki çeşitli lokalitelerden toplanmıştır. Olgun yapraklara saydamlaştırma ve boyama işlemi uygulanarak stereo mikroskopta fotoğraflanmış, damar ve areol yapılarına ait 15 morfometrik özellik analiz edilmiştir. Yaprak damar özellikleri açısından türler arasındaki farklılığın anlamlı olup olmadığını test etmek amacıyla oneway ANOVA uygulanmış ve analiz sonucunda gruplandırmada etkili olanlar ayrım analizi ile belirlenmiştir. Analiz sonucunda yeni sınıflandırmayı destekleyen veriler elde edilmiştir. Neotinea üyelerini diğer taksonlardan ayıran özellikler arasında areollerin çevresi, daireselliği, en/boy oranı gibi areol özellikleri ön plana çıkarken Anacamptis üyeleri birim alandaki damar yoğunluğu, damar uzunluğu gibi özellikler açısından farklılaşmaktadır. Bu sonuçlar damarlanmanın topolojik ve morfometrik karakterlerinin orkidelerin sistematik ve filogenetik ilişkilerini yansıtabileceğini ve özellikle problemli gruplarda sınıflandırmaya ilişkin problemlerin çözümünde etkili olabileceğini işaret etmektedir.

Various proposed approaches for autonomous driving basically involve an image processing and a machine learning process. It is extremely important to use appropriate image processing techniques and a comprehensive data set in these approaches. Moreover, the proposed model must work in real-time. On the other hand, designing and manufacturing an autonomous vehicle model results in serious hardware costs. In addition, the design and manufacturing processes need to be repeated to develop new approaches. In this context, utilizing a real-time simulation environment can be seen as a suitable approach for a less costly prevalidation of such models. In this study, a real-time simulation architecture is developed with Unity framework to test an autonomous driving model. In addition, an autonomous driving model that includes lane tracking and object recognition approaches is proposed, and an autonomous vehicle simulation is created. Finally, the feasibility of the proposed simulation architecture is tested with the convolutional neural networks-based YOLO algorithm and R-CNN algorithm versions. According to the findings, it is observed that Faster R-CNN, Mask R-CNN and YOLO-v4 algorithms produce results with 91%, 93% and 95% accuracy, respectively. It has been determined that these results are close to the accuracy rates obtained on different traffic sign data sets in the literature. Considering the outcomes, it is argued that a vehicle simulation with an autonomous driving model has been successfully tested in the proposed system architecture. [ABSTRACT FROM AUTHOR]

As Android devices occupy more of people's lives, they have also become a target of malicious software. It is important to detect malicious software and to prevent the losses and damages that may arise from this software. For this purpose, various studies are being carried out about malware detection. Recently, imagebased methods and machine learning studies have come to the fore. In these studies, binary files used in static and dynamic analysis are converted into image files. Global and local features extracted from the images are classified by various machine learning methods. In this study, global features were extracted on the malimg dataset and a feature matrix (2000, 532) long was obtained. The obtained features were classified using machine learning methods (LR, LDA, K-NN, CART, RF, NB, SVM). The results were evaluated using the K-fold crossover validation method, and a highest accuracy rate of 96.72% was obtained with K-NN and 97.44% with RF. This study contributes to the literature by reaching a higher accuracy value compared to other studies on the same data set. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Engineering & Architectural Faculty of Eskisehir Osmangazi University / Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi is the property of Eskisehir Osmangazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Currently, image sensors (cameras), are widely used for image analysis (classification, segmentation, etc.) and synthesis (object detection, tracking, distance detection, etc.). The aim of the study is to lay the theoretical foundations for the development of an image meter based measurement device (image meter) that can be used for laser-meter, lidar-meter, radar and similar industrial purposes. For this purpose, distance detection methods based on image processing in the literature have been studied. The main factors that negatively affect the performance of these methods have been identified, and a new method has been developed that is not affected by these factors. The measuring device, which is planned to be developed, is based on theoretical foundations. The operation of these theoretical foundations is based on hardware and software components. In the study, these theoretical foundations were given and designs of hardware and software components were realized. In study, as a result of calculations made for 1-1000m, it was determined that a success rate below 0.2% could be achieved. The study consists of an electro-mechanical component have hardware and software projects. It is obvious that errors caused by hardware and software components will reduce the success rate. These errors will consist of standard and random errors. In the study, these errors are foreseen and added to the distance measurement equation. Detection of predicted errors will be determined in the future study with the development of the hardware prototype and software components. [ABSTRACT FROM AUTHOR]

Son yıllarda internet kullanımında hem kullanıcı sayısının hem de bağlantı hızlarının artması nedeniyle sayısal bilgilerin çoğaltılması ve işlenmesi yaygın hale gelmiştir. Bu nedenle dijital resimlerin kopyalanma riskine karşı korunması ihtiyacı doğmuştur. Telif hakkının korunması için önerilen yöntemlerden birisi de sayısal görüntünün damgalanmasıdır. Bu çalışmada, ayrık kosinüs dönüşümü (AKD) uzayında katsayıların değiştirilmesiyle dayanıklı bir sayısal damgalama yöntemi gerçekleştirmek ve mevcut yöntemlerin başarımını arttırmak amaçlanmıştır. Çoklu-adaptif ölçekleme faktörleri kullanan önerilen yöntemde, damgalanacak görüntünün tüm blokları uzaysal resim frekansı (URF) metriği ile değerlendirilmiş ve her bloğa doku miktarıyla orantılı olarak bir ölçekleme faktörü atanmıştır. Böylece, damgalanan görüntünün en az bozulmayla ataklara karşı en fazla dayanımı göstermesi amaçlanmıştır. Gerçekleştirilen deneylerde, önerilen çoklu-adaptif ölçekleme faktörü kullanan damgalama yönteminin sabit ve ikili-adaptif ölçekleme faktörü kullanan yöntemlere göre aynı saydamlık düzeyinde ataklara karşı daha başarılı olduğu görülmüştür.

Grasshoppers damage crops and causes millions of tons of food to be destroyed every year. The development of effective and accurate locust identification systems is critical in controlling locust species and preventing food loss. In this study, 11 different plant pest grasshopper species seen in various parts of our country and the world were classified using various convolutional neural network models. The dataset used in the study was obtained by observing the Eastern and Southeastern Anatolia regions of our country. The novelity of this study is that a dataset named GHCD11 has been created for 11 different plant pest grasshopper species in our country. In addition, VGG16, VGG19, ResNet50, DenseNet121, EfficientNet, MobileNet, which are in the Keras library and are widely used in image classification, were used for the automatic classification of 11 different grasshopper species in the study. As a result of experimental studies on the GHCD11 dataset with learning transfer, remarkable classification accuracies in the range of 95% to 99% were obtained. The study is important because it not only presents a novel dataset, but also demonstrates that automatic identification and detection of plant pest grasshopper species can be done with high accuracy using convolutional neural network architectures. [ABSTRACT FROM AUTHOR]

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this study, the Finsler curve evolution model, which was established with Finsler geometry and turned into a curved evolution model with the calculation of variations, will be examined. This model is not constructed by considering only locations in the image space as in the Riemann curve evolution model. It was established in an anisotropic space by considering both locations and directions. The model offers a flexible operation in the image by eliminating the necessity of isotropic spaces. Therefore, it has become a model that researchers working on image processing mostly work on. It is aimed to contribute to future studies in the field of image processing by using the mathematical analysis of the Finsler curve evolution model discussed in this study. [ABSTRACT FROM AUTHOR]

Image processing is used in many sectors in parallel with the developing software and hardware technology. Differences are observed in the image techniques used according to the needs of the sectors. In this context, very precise measurements and powerful algorithms are required to be used in the field of health. In this article, an image mosaic was made on retinal images using datasets such as D-EYE and FIRE. Feature detection, feature matching, image matching, image wrapping and image mosaicing processes are applied on the images. Harris corner detector was used to find the corners in the image. The positions of the points in the 2 corresponding images were found with the corner detector. Scale-Invariant Feature Transform (SIFT) was used as the feature recognition algorithm between the coordinates. Feature and image matching processes were performed between the determined features. Weak spots are eliminated with the help of Random Sample Consensus (RANSAC). The homography is defined for the projective transformation with the remaining points. In the last step, a geometric transformation was made with the homography matrix. The image mosaic application in our study; It can be applied to a wide area, especially retinal images, unmanned aerial vehicle images, bacteria or tomography images. It has been tested with different data sets and a successful result has been obtained. [ABSTRACT FROM AUTHOR]

Türkiye’de bir yılda tespit edilen kanser vakalarının büyük çoğunluğu olan akciğer kanseri toplam vaka sayısının yaklaşık %20’sini oluşturmaktadır. En çok ölüm oranını oluşturan akciğer kanseri günümüzde Türkiye ve dünya için önemli bir sağlık sorunu durumundadır. Bu sorunun en önemli kaynağı erken tanısında tedavisi çok daha mümkün olan birçok vakanın erken teşhis edilememesidir.Bu çalışmada Bilgisayarlı Tomografi (BT) görüntüleri kullanılarak tümörlerin ve nodüllerin tespit edilmesi, görüntülerden çıkarılan özelliklerin farklı sınıflandırma algoritmaları ile sınıflandırılması amaçlanmıştır.Kullanılan görüntüler DICOM formatında olup RIDER-Lung CT veri setine ait 26 görüntü üzerinde çalışılmıştır. Tümör bölgesi farklı akciğer segmentasyon yöntemleri kullanılarak elde edilmiş, tümöre ait pek çok özellik hesaplanmıştır. Hesaplanan özelliklerden istatistiksel olarak anlamlı (p

Gold is one of the most counterfeited precious metals. The color of copper is like gold. For this reason, copper is one of the most used materials for color counterfeiting. When the chemical properties are concerned, wolfram is like gold (density of gold and tungsten are 19.30 g/ml and 19.25 g/ml, respectively), so it can be used as a chemical counterfeit. The purity of gold can be determined by X-ray, but this method is costly. The current low-cost methods of jewelers have been experimented with for counterfeit gold detection in this paper. When a gold matter is hit by a subject, the sound frequency is higher than the frequency of sound when the same experiment is done with copper. Furthermore, counterfeit gold color is brighter than real ones. The color of gold is unique, and it is called "gold yellow". In this research, by employing sound and image processing, counterfeit and original gold are differentiated. For the image processing part, first a Convolutional Neural Network (CNN)-based toolbox for segmenting the gold material is applied. Then, deep CNNs for differentiating the color of the gold and copper materials are employed. Promising results are achieved with both sound and image processing techniques.

Son yıllarda orman ve şehir yangınlarının artması tüm dünya için önemli bir sorun oluşturmaktadır. Ekolojik ve ekonomik açıdan büyük kayıplara sebep olan yangınlar, karbon döngüsünü bozarak orman dinamiklerine de ciddi zarar vermektedir. Bu doğrultuda yaşamın gerekliliği açısından önemli ekosistemlerden olan ormanların ve doğanın korunması önem arz etmektedir. Orman ve şehir yangınları ile mücadelede yangının erken tespiti büyük kayıpların önüne geçmektedir. Teknolojinin gelişimi ile birlikte yangınların erken tespit edilebilmesi amacıyla insansız hava araçları (İHA), yapay zekâ ve görüntü işleme tekniklerinden yararlanılmaktadır. Çalışmada, yangının erken tespiti üzerinde duruldu ve yangının erken tespit edilebilmesi için insansız hava aracı tasarlandı. Çalışmada, görüntü işleme ve yapay zekâ tekniklerinden yararlanılarak görüntülerde ateş tespiti yapılmakta ve akabinde yangın tespit edilen konum belirlenmektedir. Çalışmada sonuç olarak kullanılan mimarinin karmaşıklık matrisine göre performansı değerlendirilerek, %96 doğruluk, %98 duyarlılık, %89 özgüllük ve %96 kesinlik değerleri bulunmuştur. Gerçekleştirilen çalışma sayesinde yangının erken tespiti sağlanacak ve hızlı müdahale gerçekleştirilecektir.