Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/171413
Title: Visual recognition of guitar chords using neural networks
Author: Mitjans Coma, Albert
Director/Tutor: Carnicer González, Arturo
Keywords: Música per a guitarra
Xarxes neuronals (Informàtica)
Treballs de fi de grau
Guitar music
Neural networks (Computer science)
Bachelor's thesis
Issue Date: Jun-2020
Abstract: In this paper, we use deep learning to study high-level features for guitar chord detection. In particular, the goal of this project is to build a neural network capable of recognizing finger patterns on the frets of a guitar. Given an input image, the network is able to identify fingers, frets, strings and the corresponding chord. Using a 2-stack Hourglass network for the detection and applying a post-processing algorithm to its corresponding output heatmaps, a 97% accuracy on the detection of chords of 205 different images is obtained
Note: Treballs Finals de Grau de Física, Facultat de Física, Universitat de Barcelona, Curs: 2020, Tutor: Artur Carnicer
URI: http://hdl.handle.net/2445/171413
Appears in Collections:Treballs Finals de Grau (TFG) - Física

Files in This Item:
File Description SizeFormat 
MITJANS COMA ALBERT_1338767_assignsubmission_file_TFG-Mitjans-Coma-Albert.pdf14.87 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons