2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Yayın Kernel likelihood estimation for superpixel image parsing(Springer Verlag, 2016) Ateş, Hasan Fehmi; Sünetci, Sercan; Ak, Kenan EmirIn superpixel-based image parsing, the image is first segmented into visually consistent small regions, i.e. superpixels; then superpixels are parsed into different categories. SuperParsing algorithm provides an elegant nonparametric solution to this problem without any need for classifier training. Superpixels are labeled based on the likelihood ratios that are computed from class conditional density estimates of feature vectors. In this paper, local kernel density estimation is proposed to improve the estimation of likelihood ratios and hence the labeling accuracy. By optimizing kernel bandwidths for each feature vector, feature densities are better estimated especially when the set of training samples is sparse. The proposed method is tested on the SIFT Flow dataset consisting of 2,688 images and 33 labels, and is shown to outperform SuperParsing and some of its extended versions in terms of classification accuracy.Yayın Microservices-based databank for Turkish hazelnut cultivars using IoT and semantic web technologies(John Wiley and Sons Ltd, 2024-03-30) Aydın, Şahin; Aldara, DieaaInformation and communication technologies (ICTs) can play a crucial role in facilitating access to comprehensive information on the quality standards of Turkish hazelnut cultivars. In this regard, this study introduces a Hazelnut Databank System (HDS) that utilizes the microservices architecture, an integrated software system supported by the Internet of Things (IoT) and semantic web, to categorize Turkish hazelnut cultivars. The study focuses on developing microservices using various programming languages and frameworks. Specifically, C# on the.NET Core Framework was used for both microservices and the web-based application implemented through the ASP.NET Core MVC Framework. Mobile-based software applications were created using Xamarin. Forms, and the IoT application was developed using the Python programming language. The data storage is facilitated through the MS SQL Server database. Additionally, the study incorporates the implementation of a hazelnut species classification system using the DNN + ResNet50 machine learning model, achieving an impressive accuracy rate of 95.77%. The overall usability of the system was evaluated, resulting in a score of 42 out of 50. By providing detailed information on Turkish hazelnut cultivars, the HDS has the potential to greatly improve hazelnut production quality in Turkey and increase awareness of hazelnut agriculture among relevant stakeholders.
