Salat Error Detecting System

Abstract

Research has become one in every of the foremost talked buzzwords the epoch thanks to knowledge development and practical improvement obtained by research papers. However, choosing the precise research topic from the vast ocean of knowledge fields for an unaware individual person is sort of hard. Sometimes a beginner researcher /students cannot specify the research interest, or they're unknown with trending topic and technology, which are most impactful within the near future. Therefore, we think computer vision is such a very important thing that already helps the individual in a various way and it'll help us in the future. In the Muslim community Salat is the second pillar of Islam and it is the most significant and fundamental worshiping activity that believers have to perform five times every day. From a gesture’s perspective, there are predefined human postures that must be performed in a precise manner. However, for several people these postures are not correctly performed, because of being new to Salat or maybe learned prayers in an incorrect manner. The process of identifying salat errors from a real time salat is one of the promising applications of visual object recognition in computer vision. However, detection of salat error from real time salat is a particularly challenging work due the characteristic of their complex movements. For this we use open cv NumPy matplotlib libraries. For detecting real time movement, we first take image and using function we draw landmarks. Later we compare this image and its angle with the real time detection to compare and get the correct movement.