KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Kitjaidure, YuttanaSubject: search.filters.subject.Feature Extraction

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    The Walking Assistance System using the Lower Limb Exoskeleton Suit Commanded by Backpropagation Neural Network
    (2019-01-10)
    Karantarat, Obnithi
    ;
    Kitjaidure, Yuttana
    Currently there are many elderly people who have walking problems. This paper aims to develop and solve these problems by introducing walking assistance system which can recognize 3 types of gestures, include walking, sitting and standing. Our system is divided into 3 main parts including Feature extraction which consists of Time domain and Frequency domain, Classification and Exoskeleton suit system. Conjugate Gradient Backpropagation Neural Network is used to classify sEMG signal of lower limb posture after extracted the features. Then the output of classification is used to command the Exoskeleton suit to perform the gesture according to the results of the recognition. In addition, our paper uses PID controller to control DC motor of Four Bar Linkages Mechanisms of Lower Limb Exoskeleton suit in order to reduce the number of motors and increase stability during the Stance Phase. The results from the experiment have concluded that all feature in time domain has the most recognition rate which up to 99.39%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Novel Feature Extraction for American Sign Language Recognition Using Webcam
    (2019-01-10)
    Thongtawee, Ariya
    ;
    Pinsanoh, Onamon
    ;
    Kitjaidure, Yuttana
    Sign language is physical communication for contributing the meaning instead of using voice to demonstrate communicator's opinion. This paper introduces a simple and efficient algorithm for feature extraction to recognize American Sign Language alphabets from both static and dynamic gestures. The proposed algorithm comprises of four different techniques: Number of white pixels at the edge of the image (NwE), Finger length from the centroid point (Fcen), Angles between fingers (AngF) and Differences of angles between fingers of the first and last frame (delAng). After extracting features from video images, an Artificial Neural Network (ANN) is used to classify the signs. The result of these experiments is achieved up to 95% recognition rate, which is clearly to be the highest accuracy comparing with the other research worked in this field.