Browsing by Author "Sarybay O."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    DATA COLLECTION OF HAND GESTURES ON A HORIZONTAL SURFACE USING MEDIAPIPE LIBRARY
    (СДУ хабаршысы - 2022, 2022) Sarybay O.
    Abstract. The horizontal hand gesture recognition is an innovative, cheaper way for human-computer interaction. Currently, most researchers work with sensors, devices for hand gesture recognition, which require more resources. Instead, the presented horizontal method for hand gesture signal recognition by frames, with trained model algorithms. A key element of this work is the research of a recognition algorithm using only a single camera and collecting dataset to train a hand recognition model. In the presented framework, the hand detection works with computer vision (CV) algorithms, in general MediaPipe as a converting blue, green, red (BGR) image to red, green, blue (RGB) before processing. There are handedness and hand landmarks on the image as a result of a hand detection. Each point of the landmark has coordination x, y. z values. The collected dataset will be used to train a model with machine learning (ML) or neural network algorithms to develop this project as a hand gesture recognition project.
  • Thumbnail Image
    ItemOpen Access
    Recognition of basic hand gestures on a horizontal surface using a single camera
    (2022) Sarybay O.
    The horizontal hand gesture recognition is an innovative, cheaper way for human-computer interaction. Currently, most researchers work with sensors, devices for hand gesture recognition, which require more resources. Instead, the presented horizontal method for hand gesture signal recognition by frames. A key element of this work is the research of a recognition algorithm using only a single camera. In the presented framework, the hand detection works as a converting BGR image to RGB before processing. Then, the palm and fingers are segmented so as to detect and recognize the fingers. There are handedness and hand landmarks on the image as a result of a hand detection. Each point of the landmark has coordination x, y, z values. There is a comparison algorithm of points to recognize hand gestures by fingers. The model has been implemented by getting landmark values on a data set of hand images, which are collected from video frames. In the presented framework, the hand detection works with computer vision (CV) algorithms, in general MediaPipe as a converting blue, green, red (BGR) image to red, green, blue (RGB) before processing. There are handedness and hand landmarks on the image as a result of a hand detection. Each point of the landmark has coordination x, y, z values. The performance of the method highly depends on the result of hand detection on the horizontal surface and collected dataset.