Yazar "Kocakulak, Mustafa" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Contactless Palmprint Imaging System Design Using Mediapipe Hands(2023) Kocakulak, Mustafa; Acır, NurettınPalmprint has been widely used in biometric systems because of its durability and reliability. To avoid recognition performance degradation, dynamic region of interest extraction is a critical step for these systems. In this study, a low-cost contactless palmprint imaging system has been designed and a dynamic region of interest extraction method has been applied to palmprints using the MediaPipe Hands framework. Since the need for hygienic touchless systems has been realized in the post-COVID-19 pandemic world, a low-cost imaging system has been proposed to capture the user’s hand at a distance without touching any platform. The region of interest of the user's palmprints in a real-time video stream has been extracted dynamically. This study creates a paradigm for future studies on palmprint imaging. With conducted experiments, the potential of MediaPipe Hands in terms of speed and accuracy on mobile palmprint imaging applications has been realized on Raspberry Pi 4. This work demonstrates that the employed hardware and proposed hand-tracking algorithm are suitable for designing low-cost contactless palmprint imaging systems in non-controlled ambient light conditions. For recognition purposes, a database will be released soon.Öğe A study on the monitoring of weld quality using XGBoost with Particle Swarm Optimization(Elsevier, 2024) Avci, Adem; Kocakulak, Mustafa; Acir, Nurettin; Gunes, Emrah; Turan, SertanGas Metal Arc Welding is a joining technique with numerous uses in manufacturing. Since welding process parameters have a considerable impact on the welding quality, online monitoring systems are utilized on production lines to achieve standard welding quality with minimum welding faults. This study presents preliminary work to develop a monitoring system for defect analysis in a Gas Metal Arc Welding process. This study aims to eliminate the need for laboratory tests with a model to reduce welding quality control costs. In this study, welding data such as voltage, current, and wire feeding rate were collected during the welding process in realtime. New features were derived from the gathered data at the preprocessing stage using statistical approaches. The determination of whether the welding process is defective or flawless was made using the Extreme Gradient Boosting Algorithm. The hyperparameters of the algorithm were optimized with Particle Swarm Optimization. The accuracy value was obtained as 93.15% after repeating the conducted experiments ten times. The recall, precision, specificity, and F1 -Score values in these experiments were calculated as 97.22%, 94.75%, 72.35%, and 95.94%, respectively. The mean current value was found to be the most relevant and meaningful feature that describes the welding quality based on intensive experiments. In addition to the proposed algorithm, some other machine -learning algorithms were tested on the welding dataset. With this study, the significance of feature derivation from the acquired welding current data has been discovered to analyze welding quality.Öğe A Survey of Finger-vein Recognition using Deep Learning: Concepts, Challenges, and Opportunities(2025) Kocakulak, Mustafa; Avcı, Adem; Acır, NurettinIn recent years, convolutional neural networks have been frequently used for finger-vein biometrics. Various methodologies have been proposed to improve the recognition performance on available datasets. Deep learning-based approaches have a promising performance, and they have been an effective solution for feature learning. Nevertheless, some problems in the literature need to be solved, such as the lack of test protocol and comparability. In this study, a review of deep learning-based studies on finger-vein biometrics has been presented in two categories: identification and verification. This review contains 68 publications from reputable databases published between 2016 and 2025. The contents of the articles have been discussed in detail. The pros and cons of the proposed algorithms have been stated critically. The arising confusion due to the usage of the term recognition for identification and verification has been removed. The role of the experimental protocol and metrics in performance results on reviewed papers has been stated. The need for comparing the results against the existing results in the literature on the same finger-vein datasets using totally the same test protocol has been highlighted. Lastly, foreseen opportunities have been listed to draw the researcher's attention.Öğe An Overview of Wireless Sensor Networks Towards Internet of Things(Ieee, 2017) Kocakulak, Mustafa; Bütün, İsmailWith the advancements in wireless technology and digital electronics, some tiny devices have started to be used in numerous areas in daily life. These devices are capable of sensing, computation and communicating. They are generally composed of low power radios, several smart sensors and embedded CPUs (Central Processing Units). These devices are used to form wireless sensor network (WSN) which is necessary to provide sensing services and to monitor environmental conditions. In parallel to WSNs, the idea of internet of things (IoT) is developed where IoT can be defined as an interconnection between identifiable devices within the internet connection in sensing and monitoring processes. This paper presents detailed overview of WSNs. It also assesses the technology and characteristics of WSNs. Moreover, it provides a review of WSN applications and IoT applications.Öğe An overview of Wireless Sensor Networks towards internet of things(Institute of Electrical and Electronics Engineers Inc., 2017) Kocakulak, Mustafa; Bütün, IsmailWith the advancements in wireless technology and digital electronics, some tiny devices have started to be used in numerous areas in daily life. These devices are capable of sensing, computation and communicating. They are generally composed of low power radios, several smart sensors and embedded CPUs (Central Processing Units). These devices are used to form wireless sensor network (WSN) which is necessary to provide sensing services and to monitor environmental conditions. In parallel to WSNs, the idea of internet of things (IoT) is developed where IoT can be defined as an interconnection between identifiable devices within the internet connection in sensing and monitoring processes. This paper presents detailed overview of WSNs. It also assesses the technology and characteristics of WSNs. Moreover, it provides a review of WSN applications and IoT applications. © 2017 IEEE.Öğe Automated vein verification using self-attention-based convolutional neural networks(Pergamon-Elsevier Science Ltd, 2023) Kocakulak, Mustafa; Avci, Adem; Acir, NurettinVein-based biometric traits have been regarded as trustworthy for biometric applications. With technical advances in deep learning, verification performance has started to be improved in these applications to increase trust level in daily life by providing usage convenience and user satisfaction. In this study, the effect of self-attention mechanism on convolutional neural networks for the performance of finger-vein and hand dorsal vein verification was investigated using an open-set protocol. To provide generalizability to the trained model, self-attention-based convolutional neural networks were used rather than existing architectures and pre-trained models. With the architecture that uses residual blocks and self-attention mechanism, a fair verification performance was suggested. Verification performance was assessed on DHVI-DB and Bosphorus hand dorsal vein datasets and SDUMLA and PolyU-F finger-vein datasets in terms of equal error rate using the distance between feature vectors through the existing and the proposed distance measures. The obtained equal error rates for hand dorsal vein datasets DHVI-DB1, DHVI-DB2, and Bosphorus are 2.17, 2.21, and 18.33, respectively and for finger-vein datasets SDUMLA and PolyU-F, are 1.65 and 10.64, respectively. Moreover, 4 different loss functions were used throughout the conducted experiments to see the discriminative ability of the proposed network for vein verification. The experimental results on these datasets indicate the potential effectiveness of the self-attention mechanism on automated vein verification.Öğe Capsule Network for Finger-Vein-based Biometric Identification(Ieee, 2019) Gumusbas, Dilara; Yildirim, Tulay; Kocakulak, Mustafa; Acır, NurettinMost of the recent researches have determined that finger-vein identification systems have begun to change their direction from hand-crafted feature extraction to automatic feature extraction methods, such as convolutional neural networks (CNN). Although a few ongoing studies still concern handcrafted features, most of the recent works focus on automatic feature extraction via CNN-based algorithms, which has achieved breakthrough results. However, benchmark databases for finger-vein identification have a limited sample size per individual, which makes it difficult for them to capture the best representations in an individuals finger vein. Additionally, with the rise of spoofing attacks, obtaining the best representation of the finger vein has become even more important. Even though these algorithms adapt transfer learning by using pre-trained ImageNet weights, which create a general image feature space, it may be not the most optimal space for finger-vein identification. From this point of view, this paper firstly aims to use Capsule Network to take advantage of using convolutions with a limited number of samples on four finger-vein benchmark sub-databases. Moreover, it aims to extract finger-vein features that are more definable and rationally augments without using any pre-trained weights. Secondly, it compares the CNN-based equivalent and LeNet-5 models to show how Capsule Network is better at approaching representing features. This capsule-based finger-vein identification approach using 32x32 image resolutions achieves an average 95.5% accuracy on four benchmark sub-databases.Öğe Computational analysis of Rsa based attacks(Bursa Teknik Üniversitesi, 2015) Kocakulak, Mustafa; Temel, Turgayİki veya daha fazla asal sayının çarpımından meydana gelen büyük bir sayının, asal bileşenlerine ayrıştırılabilmesinin zorluğu esasına dayanan RSA sistemi, sağlamış olduğu güvenlik seviyesi ve anahtar paylaşımında getirdiği yeniliklerle kriptoloji alanında tartışmasız bir öneme sahiptir. Mevcut algoritmanın beraberinde getirdiği uzun anahtar boyutları, gerektirdiği geniş hafıza alanı ve anahtar paylaşımının dayandığı 'asal bileşenlere ayrıştırmanın zorluğu' esasının güvenlik açısından aşılabilir olması, bu alanda mevcut RSA algoritmasında değişiklikler yapmayı ya da RSA'yı maksimum güvenlikle korumayı sağlayan önlemleri uygulama esnasında almayı gerekli kılmaktadır. Bu çalışmada RSA algoritması birçok yönüyle ele alınacak, uygulanan bazı kriptanaliz yöntemlerine karşı RSA'ya maksimum güvenlik sağlayacak tedbirler gösterilecektir.Öğe Convolutional Neural Network Designs for Finger-vein-based Biometric Identification(Ieee, 2019) Avcı, Adem; Kocakulak, Mustafa; Acır, NurettinWith the increase in the number of publicly available finger-vein datasets, most of the recent studies on finger-vein biometrics have started to use Convolutional Neural Networks (CNNs). Since it is not an easy task to create a biometric dataset with a large number of users due to several privacy reasons, this study uses 4 publicly available finger-vein datasets. However, these datasets have a limited number of samples per user. From this point of view, in order to avoid possible overfitting problems that occur due to limited training samples, this study provides 4 empirical convolutional neural network designs without using any preprocessing operation for each biometric dataset after systematic comparisons.Öğe Driver Drowsiness Detection using MobileNets and Long Short-term Memory(Institute of Electrical and Electronics Engineers Inc., 2021) Aydemir, Gürkan; Kurnaz, Oguzhan; Bekiryazıcı, Tahir; Avcı, Adem; Kocakulak, MustafaDeep learning has been studied extensively for driver drowsiness detection using video data. However, since the proposed deep learning methods are computationally cumbersome, the commercial driver drowsiness detection methods are still using hand-crafted features such as lane deviation and percentage of eye closure. This study investigates a deep learning model that provides a fair drowsiness detection performance with a lightweight architecture. In the proposed method, Dlib library was used to detect the driver's face in individual frames of video data. The detected faces are fed into a pre-defined convolutional neural network architecture. Then, a long short-term memory network was used to capture the temporal information between the frame sequences to assess the state of drowsiness. The proposed model achieves a detection accuracy of 80% in a popular benchmark dataset. It was also verified that the model could be implemented on a commercial and inexpensive development board with a frame rate of 5 frames per second.Öğe Dynamic ROI Extraction for Palmprints using MediaPipe Hands(Ieee, 2022) Kocakulak, Mustafa; Acir, NurettinHand-based biometric traits have been widely used in recognition systems. Dynamic region of interest extraction is an important preprocessing step for these systems to avoid recognition performance degradation. In this study, a dynamic region of interest extraction method that can be used for palm vein, palmprint, and dorsal hand vein has been proposed using Google's MediaPipe Hands framework. Since 3 biometric traits focus on nearly the same region that contains biometric information on the images, this study aims to show that the proposed extraction method can be utilized for these traits on mobile biometric applications. This method has been implemented on IIT Delhi Touchless Palmprint Database and 93% accuracy was obtained. The average processing time per image for ROI extraction was recorded as 2.64 seconds. With this study, a paradigm for future studies on hand biometrics has been created and the required processing time for a dynamic extraction has been reduced considerably.Öğe Enhancement of Finger Vein Images Using Gabor Filter(Ieee, 2018) Kocakulak, Mustafa; Acır, NurettinIn this study, rather than locating a fixed region of interest directly on finger vein images, spatial filtering is applied and a texture-based edge detection method is used to give stable results. Koschmieder's Law, which eliminates the scattering effect of light on these images, is applied to the designated region of interest through white balancing process. After this step, Gabor filter bank was created in different scales and orientations. These bank elements were convolved with various images and Gabor filter application was completed. In this study, by applying Gabor filter to the images enhanced by Koschmieder's Law, it is verified that the biometric information extraction of a person is facilitated.Öğe Enhancement of finger vein images using Gabor filter(Institute of Electrical and Electronics Engineers Inc., 2018) Kocakulak, Mustafa; Acir, NurettinIn this study, rather than locating a fixed region of interest directly on finger vein images, spatial filtering is applied and a texture-based edge detection method is used to give stable results. Koschmieder's Law, which eliminates the scattering effect of light on these images, is applied to the designated region of interest through white balancing process. After this step, Gabor filter bank was created in different scales and orientations. These bank elements were convolved with various images and Gabor filter application was completed. In this study, by applying Gabor filter to the images enhanced by Koschmieder's Law, it is verified that the biometric information extraction of a person is facilitated. © 2018 IEEE.Öğe Makine öğrenmesi algoritmalarını kullanarak otomatik parmak damarı tanıma sistemi(Bursa Teknik Üniversitesi, 2023) Kocakulak, Mustafa; Acır, Nurettin; Gürkan, HakanHızla artan dünya nüfusu ve durmadan gelişen teknoloji ile hayatın hemen her alanında, güvenlik ve erişim kontrolü gibi çeşitli sebeplerle biyometrik sistemlere ihtiyaç duyulmaktadır. Son yıllarda duyulan ihtiyacı karşılamak için makine öğrenmesi bilhassa da derin öğrenme, biyometrik sistemlerde yaygın olarak kullanılmaktadır. Bu sistemlere hızlı ve düşük maliyetli çözümler sunan parmak damarı, kişiye özgü olmak, zamanla değişime uğramamak ve dış müdahalelere kapalı olmak gibi çeşitli avantajlara sahip olan bir biyometri türüdür. Bu tez, parmak damarı biyometrisini başta parmak damarı tanıma olmak üzere 3 ana başlıkta inceleyip bu başlıklar altında karşılaşılan 3 farklı probleme, makine öğrenmesi algoritmalarını kullanarak çözüm getirmeyi amaçlamaktadır. İlk olarak, derin öğrenme uygulamalarının başarımına katkı sağlayacak sayıda kişi ve bu kişilerden alınan yeterli sayıda örnek içeren halka açık herhangi bir parmak damarı veri seti bulunmamaktadır. Bu sebeple yazılımsal bir çözüm kullanarak sentetik parmak damar görüntüleri içeren kapsamlı bir veri seti oluşturulmuş ve bu veri seti erişime açılmıştır. İkinci olarak, oluşturulan sentetik veri seti kullanılarak, yeterli sayıda kişi ve örnek içeren bir veri seti sağlandığında literatürdeki tanıma uygulamalarında elde edilen performansın ulaşabileceği değerler kestirilmiştir. Yapılan çalışmalarda, bu uygulamalarda elde edilen başarıma kişi ve örnek sayısının etkisi gözlemlenmiştir. Buna ek olarak birkaç halka açık veri seti kullanılarak tasarlanan çeşitli derin öğrenme modelleri aracılığıyla elde edilen tanıma ve doğrulama performanslarının ulaştığı başarım değerlendirilmiştir. Son olarak piyasada bulunan parmak damarı tanıma cihazları, kullanıcıların ham verilere erişmesine izin vermediğinden, bu çalışmada tasarlanan görüntüleme cihazı ile kullanıcılara, platformdan alınan parmak damarı görüntülerine erişim hakkı verilmektedir. Bu cihaz ile bazı el tabanlı biyometrik özelliklerin parmak damarı ile aynı anda kullanılmasını kolaylaştıran, herhangi bir fiziksel sensör kullanmayan ve çok kipli biyometrik sistemlerin önünü açan makine öğrenmesi tabanlı bir çözüm önerilmiştir.
