Project Home
PDF access
Authors
Ahmed Serag, Ahmed Yehia,John Emad,Karim Mohamed ,Karim Khaled
Supervised By:Walaa Hassan, Hager Sobeah
Publishing Date
November 8, 2021
Abstract
There are many self taught guitarists that view tutorials online in order to learn new songs. Beginning guitarists, however, find it difficult to execute the right technique. Playing guitar focuses mostly on left hand movement as it controls the tunes. Our Project aims to correct new guitarists techniques for their left hand by scanning their hand’s movement and correcting their finger positions. The proposed solution also
captures the frequency of each played note and then produces feedback which would help players to adjust their techniques, making sure they are playing everything correctly and not just copying people playing online. The finger recognition would be done through the MediaPipe a computer vision framework which detects body motion and classifies objects, which can run on most devices. we will also use predictive and classification models to assess the guitarist’s performance.
1.1 Background
To perfectly play any tune on an instrument like the guitar, one must start by tapping and playing on the chords in a certain successive order. A big problem which faces those who are interested in learning online is different styles of playing, for example: Tablature style, which is more focused on symbols and dives into more details, another different style is guitar tabs which uses numbers on different strings, making it a bit simpler, among many more other styles. As a beginner, one would not know which is the better style and would get confused on which style to follow.These difficulties can make new guitarists overwhelmed and bored.Andy Mooney CEO of Fender company which has been making guitars for 70 years states that “45 percent of the guitars that we sold every year went to new players; 90 per cent abandoned the instrument in the first year”(Chris Bird,2019:online). The aim of our project is to help new guitarists improve their playing techniques, no matter what style of playing they would follow.That is done through capturing their finger movements as they play.Capturing the finger positions is done through a framework named MediaPipe which uses a mobileVnet architecture.MobileVnet is a light weight neural network which can run on mobile phones.In addition to capturing the finger positions,We will also classify each note the guitarist played through capturing the frequency of the note and classifying it.then those movements are analyzed and a feedback is sent to the student alerting them to any incorrect techniques or movements that may have occurred.
1.2 Motivation
Our aim is to teach the right movements and techniques. Aspirants who are using this system will be able to learn guitar playing in any style. Using our system will also allow these beginners to save a lot of time and money that would instead be wasted in taking guitar lessons and paying for instructors.
1.3 Problem Statement
New Guitarists when starting out, are stumped by so many problems they encounter at the beginning, causing their progress to break in the first few months. According to Justin Sandercoe, one of the world’s most successful guitar teachers: “one of the major problems that face aspiring guitarists is changing chords fast enough while playing a song”(Justin, 2020:online). This, if not looked after in the short run, will cause problems which will be obvious with rhyming as their strumming patterns will feel a bit off. They are also faced with the question of which style to follow, as there exist many different guitar playing styles.