Książki, monografie, podręczniki, rozdziały (WEEIiA)

Stały URI dla kolekcjihttp://hdl.handle.net/11652/171

Przeglądaj

Filtry

2016 - 201932020 - 20231

Ustawienia

Autorsearch.filters.applied.operator.equals: search.filters.author.Grudzień, KrzysztofMa przypisane plikisearch.filters.applied.operator.equals: Tak

collection.search.results.head

Teraz wyświetlane 1 - 4 z 4
  • Pozycja
    Performance Analysis of Machine Learning Platforms Using Cloud Native Technology on Edge Devices
    (Wydawnictwo Politechniki Łódzkiej, 2023) Cłapa, Konrad; Grudzień, Krzysztof; Sierszeń, Artur
    This article presents the results of an experiment performed on a machine learning edge computing platform composed of a virtualized environment with a K3s cluster and Kubeflow software. The study aimed to analyze the effectiveness of executing Kubeflow pipelines for simulated parallel executions. A benchmarking environment was developed for the experiment to allow system performance measurements based on parameters, including the number of pipelines and nodes. The results demonstrate the impact of the number of cluster nodes on computational time, revealing insights that could inform future decisions regarding increasing the effectiveness of running machine learning pipelines on edge devices.
  • Pozycja
    Hand tracking, palm and finger recognition towards touch-less device interaction
    (Wydawnictwo Politechniki Łódzkiej, 2016) Jelliti, Ibrahim; Grudzień, Krzysztof; Romanowski, Andrzej; Woźniak, Paweł
    Hand recognition is a computer technology used to spot a hand as well as to determine the location of hand and its position in arbitrary digital images. The advances in mobile industry have made the complex calculations possible and feasible in smartphones. Taking advantage of these developments, we aimed to develop a gesture recognition application based on a computer vision and image processing algorithms. The application is be able to recognize the fingers of the hand and tracking their moves to perform some interaction with the mobile environment. Presented system is a technical platform for further study of mobile-mixed reality in the field of human-computer interaction.
  • Pozycja
    Background subtraction algorithm for moving object detection
    (Wydawnictwo Politechniki Łódzkiej, 2016) Saoud, Ayoub; Mosorov, Volodymyr; Grudzień, Krzysztof
    Background subtraction technic is a very important part of computer vision applications for successful segmentation of objects from video sequences. In this paper, a segmentation method for moving object using automated moving object detection in a video image sequence based on background subtraction method. Noise is applied to assess the robustness of the algorithm. The background model method and adaptive thresholding is used to compute the foreground object detection mask. A reference frame is initiatly used and considered as background information. Experimental results, which demonstrate the system's performance, are also shown.
  • Pozycja
    A review of classical and fractional derivative order methods for edge detection in image processing
    (Wydawnictwo Politechniki Łódzkiej, 2016) Zerka, Fadila; Grudzień, Krzysztof; Romanowski, Andrzej
    The main goal of this work is compare between the classical edge detectors and an approach of edge detection based on fractional differentiation. Classical edge detectors based on first order derivative: Prewitt, Sobel and Canny and one edge detector based on second order derivative: Laplacian is discussed. Also the 2nd order fractional differentiation approach of edge detection is presented. To check the effect of image smoothing on edge detection results additionally, for results comparison between different methods, a smoothing filter is applied for Prewitt, Sobel, Laplacian. The comparison is conducted from time consuming point of view and quality of edge detection level.