The Recognition Of Semaphore Letter Code Using Haar Wavelet And Euclidean Function

Abstract

Semaphore are one way of communicating over long distances using the semaphore flags. In Indonesia semaphore is used in scout activities as a method to send information in the form of a sentence containing the message. Sending the semaphore letter code tends to be difficult. Based on the need to semaphore learning, this research proposes an algorithm with image processing as a way to correct the movement of the semaphore letter code based on the image obtained by using the webcam. Digital image processing, Wavelet feature extraction, and Euclidean distance function are applied in this study to determine the best recognition rate of variation decimation and distance variation to sending semaphore letter code using the webcam. This study resulted in the best recognition rate of 95.4% in the 1st decimation, recognition rate reached 94.6% in decimation 2, and recognition rate reached 94.2% in decimation 3. The result of the introduction of the semaphore letter code is on the introduction of movement as far as 3 to 5 meters.