Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

2016 - 201922020 - 20241

Settings

Author: search.filters.author.Ünlü, Mehmet Zübeyir

Search Results

Now showing 1 - 3 of 3
  • Master Thesis
    Video Surveillance System Based on Action and Event Recognition With Moving Object Detection and Tracking
    (01. Izmir Institute of Technology, 2024) Elçi, Tuğçe; Ünlü, Mehmet Zübeyir
    Lojistik sektörünün son yıllarda hızla büyümesi, depo alanlarının genişlemesine ve kullanılan ekipman sayısının artmasına neden olarak iş kazalarının artmasına neden olmuştur. Depolarda meydana gelen iş kazaları çoğunlukla dikkatsizlik, yorgunluk, yoğun iş temposu, bireysel davranışlar, deneyim eksikliği, yetersiz eğitim ve çalışanların ihmalinden kaynaklanmaktadır. Bu nedenle depo içi emniyetin sağlanması için insan ve ekipman etkileşimini gerçek zamanlı olarak tahmin eden bir sisteme ihtiyaç vardır. Tez kapsamında depo ortamlarında iş güvenliğini artıracak nesne algılama, nesne izleme, eylem algılama ve alarm sınıflandırma bileşenlerinden oluşan kapsamlı bir video gözetim sistemi önerilmektedir. Bu sistemde nesne tespit metodolojisi olarak kullanılan YOLOv7, nesneleri tek bir ağ geçişinde hızlı ve doğru bir şekilde tespit eden bir derin öğrenme modelidir. Deep SORT ise izlenen her nesneye benzersiz bir tanımlayıcı atayan ve izleme sırasında derin öğrenmeyi kullanan bir bilgisayarlı görme izleme teknolojisidir. Sistemin eylem algılama kısmı, anormallikleri ve potansiyel riskleri tanıyarak eylemleri ve hareketleri tanımlamak ve analiz etmek için tasarlanmıştır. Bu bölümde insan ve ekipmanların hız, etiket, hareket yönü ve koordinat bilgileri kullanılarak çeşitli alarm seviyeleri tahmin edilmekte ve bu tahmini alarm seviyelerine bağlı olarak da farklı alarm seviyeleri üretilmektedir. Gerçek zamanlı müdahale ve yüksek başarı oranıyla çalışabilme gibi teknolojik yeterlilikleri sağlaması test edilen bu sistem sayesinde depolardaki kazalar tahmin edilecek, alarmlar üretilecek ve olası iş kazaları büyük ölçüde önlenebilecektir.
  • Master Thesis
    Design of an Offline Ottoman Character Recognition System for Translating Printed Documents To Modern Turkish
    (Izmir Institute of Technology, 2019) Küçükşahin, Naz; Ünlü, Mehmet Zübeyir
    Optical character recognition (OCR) is one of the most studied topics for many years. As a result of these studies, systems developed especially for the Latin alphabet have become more accurate even for handwritten texts. However, there are very limited studies on Ottoman OCR systems in the literature and it is still a subject of interest due to the complexity of the language in grammar, writing and spelling. In this thesis, it is aimed to design an offline OCR system that recognizes Ottoman characters using deep convolutional neural networks. The proposed work consists of several steps such as image processing, image digitization and character segmentation, adaptation of inputs to the network, training of the network, recognition and evaluation of results. Firstly, a character dataset was created by segmenting text images of different lengths that was selected among scanned samples of various Ottoman literature from the digital database of Turkish National Library. Two convolutional neural networks of different complexity were trained with the created character dataset and the relationship between recognition rates and network complexity was evaluated. Secondly, using the Histogram of Oriented Gradients and Principal Component Analysis, the features of the created dataset were extracted and the Ottoman characters were classified with k-Nearest Neighbor Algorithm and Support Vector Machines which are widely used classification methods in the literature. The performed analyzes have shown that both networks provide acceptable recognition rates compared to the conventional classifiers, however complex deep neural network showed better accuracy and lower loss.
  • Master Thesis
    Accelerometer Based Handwritten Character Recognition Using Dynamic Time Warping
    (Izmir Institute of Technology, 2016) Tunçer, Esra; Ünlü, Mehmet Zübeyir
    Character and gesture recognition are one of the most studied topics in recent years. Character recognition studies are generally based on image processing. Only a few studies can be found about character recognition as gesture recognition. Gesture recognition is making the computers understand human body movements by using different kind of knowledge of the environment. This knowledge can be obtained by image or sensor-based efforts. Accelerometer is the most used sensor in gesture recognition, so in this study a 3-axis accelerometer is used. In this thesis, English alphabet‟s lowercase characters are used. A ring-like device which contains accelerometer in it is used. After obtaining the acceleration data of each character with 20 repetitions, we apply filtering, segmentation and normalization preprocessing steps for each signal. Since there are different accelerations and decelerations between each repetitions, Dynamic Time Warping (DTW) algorithm has been chosen to determine the similarities between signals. DTW is an algorithm that uses the amplitude values of the signals, so it is weak to amplitudes that shift in time domain. To overcome this shortcoming, the method called Derivative Dynamic Time Warping (DDTW) has been applied to the acceleration signals. DTW and DDTW methods have been compared and we have found that even we remove the normalization step; DDTW gives better results than DTW. By comparison of linear alignment and DTW, the results show that DTW gives better recognition rates for signals with different accelerations and decelerations. DTW also gives better result for the different length signals.