Artırılmış gerçeklik ve makine öğrenmesi teknikleri kullanılarak akıllı sistemlerin geliştirilmesi

The aim of the thesis is to develop intelligent systems using augmented reality and machine learning techniques. Particularly, we focused on managing and checking onshelf availability (OSA) in the retail sector since providing high OSA is a key factor to increase profits in grocery stores. Recently, there has been a growing interest in computer vision approaches to monitor OSA. However, the large and well-known computer vision datasets do not provide annotation for store products, and therefore a huge effort is needed to manually label products on images. To tackle the annotation problem, this thesis proposes a new method. Our study combines two concepts "semi-supervised learning" and "on-shelf availability" (SOSA) for the first time. Moreover, it is the first time that "You Only Look Once" (YOLOv4) deep learning architecture is used to monitor OSA. Furthermore, this thesis provides the first demonstration of explainable artificial intelligence (XAI) on OSA. It presents a new software application, called SOSA XAI, with its capabilities and advantages. In addition, a new augmented reality (AR) application was developed to monitor the latest status of the shelf, called SOSA AR. In the experimental studies, the effectiveness of the proposed SOSA method was verified on a real-world image dataset, with different ratios of labeled samples varying from 20% to 80%. The experimental results show that the proposed approach outperforms the existing approaches (RetinaNet and YOLOv3) in terms of accuracy.